@article{21366,
author       = {de Boer, V. and Wielemaker, J. and van Gent, J. and O'Connell, J. and Oosterbroek, M and Hildebrand, M. and Isaac, A. and van Ossenbruggen, J. R. and Schreiber, G.},
title        = {Amsterdam {Museum} {Linked} {Open} {Data}},
journal      = {Semantic Web},
pages        = {237 - 243},
year         = {2013},
number       = {3},
volume       = {4},
publisher    = {IOS Press},
issn         = {1570-0844},
refereed     = {y},
size         = {p.},
keywords     = { Cultural heritage, museum, thesaurus, Europeana Data Model },
group        = {INS2},
scndgroup    = {IA},
language     = {en},
abstract     = {In this document we describe the Amsterdam Museum Linked Open Data set. The dataset is a five-star Linked
 Data representation and comprises the entire collection of the Amsterdam Museum consisting of more than 70,000 object descriptions.
 Furthermore, the institution's thesaurus and person authority files used in the object metadata are included in the Linked
 Data set. The data is mapped to the Europeana Data Model, utilizing Dublin Core, SKOS, RDA-group2 elements and the OAI-ORE
 model to represent the museum data. Vocabulary concepts are mapped to GeoNames and DBpedia. The two main contributions of
 this dataset are the inclusion of internal vocabularies and the fact that the complexity of the original dataset is retained.},
url          = {http://oai.cwi.nl/oai/asset/21366/21366D.pdf},
url          = {http://dx.doi.org/10.3233/SW-2012-0074},
}

In this document we describe the Amsterdam Museum Linked Open Data set. The dataset is a five-star Linked Data representation and comprises the entire collection of the Amsterdam Museum consisting of more than 70,000 object descriptions. Furthermore, the institution's thesaurus and person authority files used in the object metadata are included in the Linked Data set. The data is mapped to the Europeana Data Model, utilizing Dublin Core, SKOS, RDA-group2 elements and the OAI-ORE model to represent the museum data. Vocabulary concepts are mapped to GeoNames and DBpedia. The two main contributions of this dataset are the inclusion of internal vocabularies and the fact that the complexity of the original dataset is retained.

@inproceedings{21367,
author       = {Gligarov, R. and Hildebrand, M. and van Ossenbruggen, J. R. and Aroyo, L. and Schreiber, G.},
editor       = {Serdyukov, P. and Braslavski, P. and Kuznetsov, S. O. and Kamps, J. and Ruger, S. M. and Agichtein, E. and Segalovich, I. and Yilmaz, E.},
title        = {An {Evaluation} {Of} {Labelling-{Game}} {Data} {For} {Video} {Retrieval}},
booktitle    = {Proceedings of the European Conference on Information Retrieval (ECIR, 2013)},
conferencetitle    = {European Conference on Information Retrieval},
conferencedate     = {2013, March 24-27},
conferencelocation = {Moscow, Russia},
journal      = {Advances in Information Retrieval - 35th European Conference  on IR Research},
pages        = {50 - 61},
year         = {2013},
volume       = {7814},
publisher    = {Springer},
refereed     = {y},
size         = {p.},
group        = {INS2},
scndgroup    = {IA},
language     = {en},
url          = {http://oai.cwi.nl/oai/asset/21367/21367B.pdf},
url          = {http://dx.doi.org/10.1007/978-3-642-36973-5},
}

@inproceedings{21386,
author       = {Boom, B. J. and Huang, P. X. and Spampinato, C and Palazzo, S. and He, J. and Beyan, C. and Beauxis-Aussalet, E. M. A. L. and van Ossenbruggen, J. R. and Nadarajan, G. and Chen-Burger, J. Y. and Giordano, D. and Hardman, L. and Lin, F.-P. and Fisher, R. B.},
title        = {Long-{Term} {Underwater} {Camera} {Surveillance} {For} {Monitoring} {And} {Analysis} {Of} {Fish} {Populations}},
booktitle    = {Proceedings of Workshop on Visual observation and Analysis of Animal and Insect Behavior 2012 (VAIB )},
conferencetitle    = {Workshop on Visual observation and Analysis of Animal and Insect Behavior},
conferencedate     = {2012},
conferencelocation = {Tsukuba, Japan},
pages        = {1 - 4},
year         = {2013},
refereed     = {y},
size         = {4p.},
group        = {INS2},
scndgroup    = {Information},
language     = {en},
abstract     = {Long-term monitoring of the underwater environment is still labour intensive work. Using underwater surveillance
 cameras to monitor this environment has the potential advantage to make the task become less labour intensive. Also, the
 obtained data can be stored making the research reproducible. In this work, a system to analyse long-term underwater camera
 footage (more than 3 years of 12 hours a day underwater camera footage from 10 cameras) is described. This system uses video
 processing software to detect and recognise fish species. This footage is processed on supercomputers, which allow marine
 biologists to request automatic processing on these videos and afterwards analyse the
results using a web-interface that
 allows them to display counts of fish species in the camera footage.},
url          = {http://oai.cwi.nl/oai/asset/21386/21386B.pdf},
url          = {http://homepages.inf.ed.ac.uk/rbf/Fish4Knowledge/PAPERS/boomvaib.pdf},
}

Long-term monitoring of the underwater environment is still labour intensive work. Using underwater surveillance cameras to monitor this environment has the potential advantage to make the task become less labour intensive. Also, the obtained data can be stored making the research reproducible. In this work, a system to analyse long-term underwater camera footage (more than 3 years of 12 hours a day underwater camera footage from 10 cameras) is described. This system uses video processing software to detect and recognise fish species. This footage is processed on supercomputers, which allow marine biologists to request automatic processing on these videos and afterwards analyse the results using a web-interface that allows them to display counts of fish species in the camera footage.

@inproceedings{21391,
author       = {Dijkshoorn, C. and Leyssen, M. H. R. and Nottamkandath, A. and Oosterman, J. and Traub, M. C. and Aroyo, L. and Bozzon, A. and Fokkink, W. J. and Houben, G. J. and Hovelman, H. and Jongma, L. and van Ossenbruggen, J. R. and Schreiber, G. and Wielemaker, J.},
editor       = {Berkovsky, S. and Herder, E. and Lops, P. and Santos, O. C.},
title        = {Personalized {Nichesourcing}: {Acquisition} {Of} {Qualitative} {Annotations} {From} {Niche} {Communities}},
booktitle    = {Proceedings of the Workshop on Personalized Access to Cultural Heritage (PATCH, 2013)},
conferencetitle    = {Workshop on Personalized Access to Cultural Heritage},
conferencedate     = {2013, June 10 - June 14},
conferencelocation = {Rome, Italy},
journal      = {Workshop on Personalized Access to Cultural Heritage},
pages        = { - },
year         = {2013},
month        = {June},
refereed     = {y},
size         = {1p.},
keywords     = {cultural heritage, nichesourcing, annotation framework, qualitative annotations},
group        = {INS2},
scndgroup    = {IA},
language     = {en},
abstract     = {Diversity and profundity of the topics in cultural heritage collections make experts from outside the institution
 indispensable for acquiring qualitative and comprehensive annotations. We define the concept of nichesourcing and present
 challenges in the process of obtaining qualitative annotations from people in these niches. We believe that experts provide
 better annotations if this process is personalized. We present a framework called Accurator, that allows to realize and
 evaluate strategies and applications for personalized nichesourcing.},
url          = {http://oai.cwi.nl/oai/asset/21391/21391B.pdf},
}

Diversity and profundity of the topics in cultural heritage collections make experts from outside the institution indispensable for acquiring qualitative and comprehensive annotations. We define the concept of nichesourcing and present challenges in the process of obtaining qualitative annotations from people in these niches. We believe that experts provide better annotations if this process is personalized. We present a framework called Accurator, that allows to realize and evaluate strategies and applications for personalized nichesourcing.

@article{21400,
author       = {Spampinato, C and Beauxis-Aussalet, E. M. A. L. and Palazzo, S. and Beyan, C. and van Ossenbruggen, J. R. and He, J. and Boom, B. and Huang, X.},
title        = {A {Rule-{Based}} {Event} {Detection} {System} {For} {Real-}{Life} {Underwater} {Domain}},
journal      = {Machine Vision and Applications},
pages        = {1 - 19},
year         = {2013},
month        = {May},
publisher    = {Springer},
issn         = {0932-8092},
refereed     = {y},
size         = {p.},
keywords     = {Event detection, Fish detection, Fish recognition, Trajectory classification, Behaviour understanding},
group        = {INS2},
scndgroup    = {IA},
language     = {en},
abstract     = {Understanding and analyzing fish behaviour is a fundamental task for biologists that study marine ecosystems
 because the changes in animal behaviour reflect environmental conditions such as pollution and climate change. To support
 investigators in addressing these complex questions, underwater cameras have been recently used. They can continuously monitor
 marine life while having almost no influence on the environment under observation, which is not the case with observations
 made by divers for instance. However, the huge quantity of recorded data make the manual video analysis practically impossible.
 Thus machine vision approaches are needed to distill the information to be investigated. In this paper, we propose an automatic
 event detection system able to identify solitary and pairing behaviours of the most common fish species of the Taiwanese
 coral reef. More specifically, the proposed system employs robust low-level processing modules for fish detection, tracking
 and recognition that extract the raw data used in the event detection process. Then each fish trajectory is modeled and
 classified using hidden Markov models. The events of interest are detected by integrating end-user rules, specified through
 an ad hoc user interface, and the analysis of fish trajectories. The system was tested on 499 events of interest, divided
 into solitary and pairing events for each fish species. It achieved an average accuracy of 0.105, expressed in terms of
 normalized detection cost. The obtained results are promising, especially given the difficulties occurring in underwater
 environments. And moreover, it allows marine biologists to speed up the behaviour analysis process, and to reliably carry
 on their investigations.},
url          = {http://oai.cwi.nl/oai/asset/21400/21400D.pdf},
url          = {http://link.springer.com/article/10.1007/s00138-013-0509-x},
}

Understanding and analyzing fish behaviour is a fundamental task for biologists that study marine ecosystems because the changes in animal behaviour reflect environmental conditions such as pollution and climate change. To support investigators in addressing these complex questions, underwater cameras have been recently used. They can continuously monitor marine life while having almost no influence on the environment under observation, which is not the case with observations made by divers for instance. However, the huge quantity of recorded data make the manual video analysis practically impossible. Thus machine vision approaches are needed to distill the information to be investigated. In this paper, we propose an automatic event detection system able to identify solitary and pairing behaviours of the most common fish species of the Taiwanese coral reef. More specifically, the proposed system employs robust low-level processing modules for fish detection, tracking and recognition that extract the raw data used in the event detection process. Then each fish trajectory is modeled and classified using hidden Markov models. The events of interest are detected by integrating end-user rules, specified through an ad hoc user interface, and the analysis of fish trajectories. The system was tested on 499 events of interest, divided into solitary and pairing events for each fish species. It achieved an average accuracy of 0.105, expressed in terms of normalized detection cost. The obtained results are promising, especially given the difficulties occurring in underwater environments. And moreover, it allows marine biologists to speed up the behaviour analysis process, and to reliably carry on their investigations.

@inproceedings{21472,
author       = {Hildebrand, M. and Hoekstra, R and van Ossenbruggen, J. R.},
title        = {Using {Semantic} {Web} {Technologies} {To} {Reproduce} {A} {Pharmacovigilance} {Case} {Study}},
booktitle    = {Proceedings of International Workshop on Linked Science 2013 (LISC 3)},
conferencetitle    = {International Workshop on Linked Science},
conferencedate     = {2013, October 21},
conferencelocation = {Syndey},
pages        = { - },
year         = {2013},
month        = {October},
refereed     = {y},
size         = {p.},
group        = {IA},
scndgroup    = {INS2},
language     = {en},
abstract     = {We provide a detailed report of a reproduction study of a paper published in
the International Journal of
 Medical Sciences (IJMS). We first use the PROV-O
ontology to model our reconstruction of the computational workflow of
 the
original experiment and to systematically explicate all information that is
needed for an reproduction study. We then
 identify which part of the required
information is published in the IJMS paper and what part is missing. We then
discuss
 our reproduction of this workflow, following the original as much as
possible. Again, we use PROV-O to precisely define
 our version of the
workflow, including our version of the information that was missing in the
IJMS paper of the study.
 Finally, we generalize from the specific cased
described in the original paper by providing a web service that allows mining
for
 arbitrary drug-adverse event pairs},
url          = {http://oai.cwi.nl/oai/asset/21472/21472B.pdf},
}

We provide a detailed report of a reproduction study of a paper published in the International Journal of Medical Sciences (IJMS). We first use the PROV-O ontology to model our reconstruction of the computational workflow of the original experiment and to systematically explicate all information that is needed for an reproduction study. We then identify which part of the required information is published in the IJMS paper and what part is missing. We then discuss our reproduction of this workflow, following the original as much as possible. Again, we use PROV-O to precisely define our version of the workflow, including our version of the information that was missing in the IJMS paper of the study. Finally, we generalize from the specific cased described in the original paper by providing a web service that allows mining for arbitrary drug-adverse event pairs

@inproceedings{21531,
author       = {Leyssen, M. H. R. and van Ossenbruggen, J. R. and de Vries, A. P. and Hardman, L.},
title        = {Manipulating {Social} {Roles} {In} {A} {Tagging} {Environment}},
booktitle    = {Proceedings of Human Computing $1 Crowdsourcing 2013 (HCOMP 1)},
conferencetitle    = {Human Computing $1 Crowdsourcing},
conferencedate     = {2013, 6-9 November},
conferencelocation = {Palm Springs, CA, USA},
pages        = {44 - 45},
year         = {2013},
refereed     = {y},
size         = {2p.},
group        = {INS2},
scndgroup    = {Information},
language     = {en},
abstract     = {Social roles structure daily life because people adjust their behavior according to the role that they have
 in a specific situation. Online social roles are not necessarily the same as those in daily life and, because they are not
 so strictly assigned, the question arises whether they can be manipulated. We conducted a structured experiment to investigate
 whether the manipulation of online social roles can affect user behavior in a tagging task.},
url          = {http://oai.cwi.nl/oai/asset/21531/21531D.pdf},
}

Social roles structure daily life because people adjust their behavior according to the role that they have in a specific situation. Online social roles are not necessarily the same as those in daily life and, because they are not so strictly assigned, the question arises whether they can be manipulated. We conducted a structured experiment to investigate whether the manipulation of online social roles can affect user behavior in a tagging task.

@inproceedings{21872,
author       = {Beauxis-Aussalet, E. M. A. L. and Arslanova, E. and Hardman, L. and van Ossenbruggen, J. R.},
title        = {A {Case} {Study} {Of} {Trust} {Issues} {In} {Scientific} {Video} {Collections}},
booktitle    = {Proceedings of the Workshop on Multimedia Analysis for Ecological Data (MAED, 2013)},
conferencetitle    = {Workshop on Multimedia Analysis for Ecological Data},
conferencedate     = {2013},
series       = {ACM Digital Library},
pages        = { - },
year         = {2013},
month        = {October},
publisher    = {ACM},
refereed     = {y},
size         = {1p.},
keywords     = {Data Provenance; Video Analysis; Information Design},
group        = {INS2},
scndgroup    = {A&C},
language     = {en},
abstract     = {In-situ video recording of underwater ecosystems is able to provide valuable information for biology research
 and natural resources management, e.g. changes in species abundance. Searching the videos manually, however, requires costly
 human effort. Our video analysis tool supports the key task of counting different species of fish, allowing marine biologists
 to query the video collection without watching the videos. To be suitable for scientific research on changes in species
 abundance, the video data must include data provenance information that reflects the potential biases introduced through
 the video processing.In order to trust the analyses made by the system, we need to provide expert users with sufficient
 information to allow them to interpret these potential biases. We conducted two user studies to design a user interface
 that includes data provenance information. Our qualitative analysis discusses the support for understanding the reliability
 of video analysis, and trusting the results it produces. Our main finding is that disclosing details about the video processing
 and provenance data allows biologists to compare the results with their traditional statistical methods, thus increasing
 their trust in the results.},
url          = {http://dx.doi.org/10.1145/2509896.2509907},
}

In-situ video recording of underwater ecosystems is able to provide valuable information for biology research and natural resources management, e.g. changes in species abundance. Searching the videos manually, however, requires costly human effort. Our video analysis tool supports the key task of counting different species of fish, allowing marine biologists to query the video collection without watching the videos. To be suitable for scientific research on changes in species abundance, the video data must include data provenance information that reflects the potential biases introduced through the video processing.In order to trust the analyses made by the system, we need to provide expert users with sufficient information to allow them to interpret these potential biases. We conducted two user studies to design a user interface that includes data provenance information. Our qualitative analysis discusses the support for understanding the reliability of video analysis, and trusting the results it produces. Our main finding is that disclosing details about the video processing and provenance data allows biologists to compare the results with their traditional statistical methods, thus increasing their trust in the results.

@inproceedings{18859,
author       = {Hildebrand, M. and van Ossenbruggen, J. R.},
title        = {Linking {User-{Generated}} {Video} {Annotations} {To} {The} {Web} {Of} {Data}},
booktitle    = {Proceedings of 18th International Conference on Multimedia Modeling 2012 },
conferencetitle    = {International Conference on Multimedia Modeling },
conferencedate     = {2012, Jan 4 - Jan 6},
conferencelocation = {Klagenfurt, Austria},
year         = {2012},
month        = {January},
refereed     = {y},
group        = {INS2},
language     = {en},
abstract     = {In the audiovisual domain tagging games are explored as a method to collect user-generated metadata. For
 example, the Netherlands Institute for Sound and Vision deployed the video labelling game "Waisda?" to collect user tags
 for videos from their collection. These tags are potentially useful to improve the access to the content within the videos.
 However, the uncontrolled and often incomplete tags allow for multiple interpretations, preventing long term access. In
 this paper we investigate a semi-automatic process to define the interpretation of the tags by linking them to concepts
 from the Linked Open Data cloud. More specifically, we investigate if existing web services are suited to find a number
 of candidate concepts, and if human users can select the most appropriate concept from these suggestions in the context
 of the video. We present a prototype application that supports this process and discuss the results of a user experiment
 where this application is used with different data sources.
},
url          = {http://homepages.cwi.nl/%7Ejrvosse/publications/2012/mmm2012.pdf},
}

In the audiovisual domain tagging games are explored as a method to collect user-generated metadata. For example, the Netherlands Institute for Sound and Vision deployed the video labelling game "Waisda?" to collect user tags for videos from their collection. These tags are potentially useful to improve the access to the content within the videos. However, the uncontrolled and often incomplete tags allow for multiple interpretations, preventing long term access. In this paper we investigate a semi-automatic process to define the interpretation of the tags by linking them to concepts from the Linked Open Data cloud. More specifically, we investigate if existing web services are suited to find a number of candidate concepts, and if human users can select the most appropriate concept from these suggestions in the context of the video. We present a prototype application that supports this process and discuss the results of a user experiment where this application is used with different data sources.

@inproceedings{19651,
author       = {de Boer, V. and Wielemaker, J. and van Gent, J. and Hildebrand, M. and Isaac, A. and van Ossenbruggen, J. R. and Schreiber, G.},
title        = {Supporting {Linked} {Data} {Production} {For} {Cultural} {Heritage} {Institutes}: {The} {Amsterdam} {Museum} {Case} {Study}},
booktitle    = {Proceedings of European Semantic Web Conference 2012},
conferencetitle    = {European Semantic Web Conference},
conferencedate     = {2012, May 27 - May 31},
conferencelocation = {Crete},
year         = {2012},
month        = {May},
refereed     = {y},
group        = {INS2},
language     = {en},
url          = {http://oai.cwi.nl/oai/asset/19651/19651B.pdf},
}

@techreport{20690,
author       = {Leyssen, M. H. R. and Traub, M. C. and van Ossenbruggen, J. R. and Hardman, L.},
title        = {Is {It} {A} {Bird} {Or} {Is} {It} {A} {Crow}? {The} {Influence} {Of} {Presented} {Tags} {On} {Image} {Tagging} {By} {Non-}{Expert} {Users}},
type         = {CWI Technical Report},
origin       = {other},
series       = {Information Systems [INS]},
year         = {2012},
month        = {December},
number       = {INS-1202},
publisher    = {CWI},
issn         = {1386-3681},
note         = {This document is under submission. This technical report has been published to ensure early dissimination of results.},
keywords     = {image tagging, cultural heritage, tagging support, user interface, user behavior, crowdsourcing},
group        = {INS2},
language     = {en},
abstract     = {Cultural heritage institutes often make use of tags to facilitate searching their collections. While professionals
 associated with these institutes are able to add high quality descriptions to objects in the collections, both their time
 and their areas of expertise are limited. As a result, online tagging by non-professional users is more frequently becoming
 deployed to increase the number of tags. When these users are asked to tag objects in the collection, they can be confronted
 with tags submitted by other users. These tags may be of varying quality and present in differing numbers, both of which
 may influence users' tagging behavior. We report on a study on the impact of presenting different types of tags on the quality
 and quantity of tags added by users. We conclude that there is no difference in the quality and quantity of added tags in
 all experimental conditions, with the exception of the condition in which incorrect tags were presented. In this condition,
 the quality of the tags added by users decreased. We discuss the implications of these findings on the design of tagging
 interfaces.},
url          = {http://oai.cwi.nl/oai/asset/20690/20690D.pdf},
}

Cultural heritage institutes often make use of tags to facilitate searching their collections. While professionals associated with these institutes are able to add high quality descriptions to objects in the collections, both their time and their areas of expertise are limited. As a result, online tagging by non-professional users is more frequently becoming deployed to increase the number of tags. When these users are asked to tag objects in the collection, they can be confronted with tags submitted by other users. These tags may be of varying quality and present in differing numbers, both of which may influence users' tagging behavior. We report on a study on the impact of presenting different types of tags on the quality and quantity of tags added by users. We conclude that there is no difference in the quality and quantity of added tags in all experimental conditions, with the exception of the condition in which incorrect tags were presented. In this condition, the quality of the tags added by users decreased. We discuss the implications of these findings on the design of tagging interfaces.

@inproceedings{20926,
author       = {Spampinato, C and Mezaris, V and van Ossenbruggen, J. R.},
editor       = {Babaguchi, N and et al},
title        = {Multimedia {Analysis} {For} {Ecological} {Data}},
booktitle    = {Proceedings of the 20th ACM Multimedia Conference},
conferencetitle    = {ACM International Conference on Multimedia},
conferencedate     = {2012, October 29 - November 02},
conferencelocation = {Nara, Japan},
pages        = {1507 - 1508},
year         = {2012},
month        = {November},
publisher    = {ACM},
isbn         = {978-1-4503-1089-5},
refereed     = {y},
size         = {2p.},
group        = {INS2},
language     = {en},
url          = {http://doi.acm.org/10.1145/2393347.2396540},
}

@article{21160,
author       = {Spampinato, C and Palazzo, S. and Boom, B. and van Ossenbruggen, J. R. and Kavasidis, I. and Di Salvo, R. and Lin, F.-P. and Giordano, D. and Hardman, L. and Fisher, R. B.},
title        = {Understanding {Fish} {Behavior} {During} {Typhoon} {Events} {In} {Real-{Life}} {Underwater} {Environments}},
journal      = {Multimedia Tools and Applications},
pages        = {1 - 38},
year         = {2012},
publisher    = {Springer},
issn         = {1380-7501},
refereed     = {y},
size         = {38p.},
group        = {INS2},
scndgroup    = {INS},
language     = {en},
abstract     = {The study of fish populations in their own natural environment is a task
that has usually been tackled in
 invasive ways which inevitably influenced the
behavior of the fish under observation. Recent projects involving the installation
of
 permanent underwater cameras (e.g. the Fish4Knowledge (F4K) project, for the
observation of Taiwan’s coral reefs) allow
 to gather huge quantities of video data,
without interfering with the observed environment, but at the same time require
the
 development of automatic processing tools, since manual analysis would be
impractical for such amounts of videos. Event
 detection is one of the most interesting aspects from the biologists’ point of view, since it allows the analysis of fish
 activity
during particular events, such as typhoons. In order to achieve this goal, in this paper
we present an automatic
 video analysis approach for fish behavior understanding
during typhoon events. The first step of the proposed system, therefore,
 involves
the detection of “typhoon” events and it is based on video texture analysis and on
classification by means
 of Support Vector Machines (SVM). As part of our behavior
understanding efforts, trajectory extraction and clustering have
 been performed to
study the differences in behavior when disruptive events happen. The integration
of event detection
 with fish behavior understanding surpasses the idea of simply
detecting events by low-level features analysis, as it supports
 the full semantic
comprehension of interesting events.},
url          = {http://oai.cwi.nl/oai/asset/21160/21160D.pdf},
}

The study of fish populations in their own natural environment is a task that has usually been tackled in invasive ways which inevitably influenced the behavior of the fish under observation. Recent projects involving the installation of permanent underwater cameras (e.g. the Fish4Knowledge (F4K) project, for the observation of Taiwan’s coral reefs) allow to gather huge quantities of video data, without interfering with the observed environment, but at the same time require the development of automatic processing tools, since manual analysis would be impractical for such amounts of videos. Event detection is one of the most interesting aspects from the biologists’ point of view, since it allows the analysis of fish activity during particular events, such as typhoons. In order to achieve this goal, in this paper we present an automatic video analysis approach for fish behavior understanding during typhoon events. The first step of the proposed system, therefore, involves the detection of “typhoon” events and it is based on video texture analysis and on classification by means of Support Vector Machines (SVM). As part of our behavior understanding efforts, trajectory extraction and clustering have been performed to study the differences in behavior when disruptive events happen. The integration of event detection with fish behavior understanding surpasses the idea of simply detecting events by low-level features analysis, as it supports the full semantic comprehension of interesting events.

@inproceedings{21163,
author       = {Baltussen, L. B. and Oomen, J. and Hardman, L. and Leyssen, M. H. R. and B Group and Blom, J. and van Ossenbruggen, J. R. and van Leeuwen, P.},
title        = {Antiques {Interactive}},
booktitle    = {Proceedings of European Interactive TV demo session 2012},
conferencetitle    = {European Interactive TV Conference},
conferencedate     = {2012},
conferencelocation = {Berlin},
pages        = {1 - 2},
year         = {2012},
month        = {June},
refereed     = {y},
size         = {2p.},
group        = {INS},
scndgroup    = {INS2},
language     = {en},
abstract     = {We demonstrate the potential of automatically linking content
from television broadcasts in the context
 of enriching the
experience of users watching the broadcast. The demo focusses
on (1) providing smooth user interface
 that allows users to look
up web content and other audiovisual material that is directly
related to the television content
 and (2) providing means for
social interaction.},
url          = {http://oai.cwi.nl/oai/asset/21163/21163B.pdf},
}

We demonstrate the potential of automatically linking content from television broadcasts in the context of enriching the experience of users watching the broadcast. The demo focusses on (1) providing smooth user interface that allows users to look up web content and other audiovisual material that is directly related to the television content and (2) providing means for social interaction.

@media{17980,
author       = {Hardman, L. and van Ossenbruggen, J. R.},
title        = {Visjes {Tellen} : {Hoe}?{Zo}! {Radio}, 15.02.2011, {N{TR}} [21:57]},
year         = {2011},
month        = {February},
group        = {INS},
scndgroup    = {INS2},
language     = {nl},
abstract     = {Zet maandenlang een camera op een stukje koraal, en ga dan maar eens de visjes tellen. Geen beginnen aan.
 Dat moeten ook de biologen gedacht hebben van het project Fish4Knowledge. Slim als ze zijn, schakelden zij informatici in
 die wél goed kunnen omgaan met gigantische hoeveelheden data.
Lynda Hardman en Jacco van Ossenbruggen van het Centrum
 Wiskunde $1 Informatica in Amsterdam (CWI) lichten toe hoe informatica gebruikt kan worden voor meer inzicht in de bewoners
 van het koraal.
},
url          = {http://oai.cwi.nl/oai/asset/17980/17980D.mp3},
}

Zet maandenlang een camera op een stukje koraal, en ga dan maar eens de visjes tellen. Geen beginnen aan. Dat moeten ook de biologen gedacht hebben van het project Fish4Knowledge. Slim als ze zijn, schakelden zij informatici in die wél goed kunnen omgaan met gigantische hoeveelheden data. Lynda Hardman en Jacco van Ossenbruggen van het Centrum Wiskunde $1 Informatica in Amsterdam (CWI) lichten toe hoe informatica gebruikt kan worden voor meer inzicht in de bewoners van het koraal.

@inproceedings{18472,
author       = {van Ossenbruggen, J. R. and Hildebrand, M. and de Boer, V.},
title        = {Interactive {Vocabulary} {Alignment}},
booktitle    = {Proceedings of the International Conference on Theory and Practice of Digital Libraries 2011},
conferencetitle    = {International Conference on Theory and Practice of Digital Libraries},
conferencedate     = {2011, September 26 - September 28},
conferencelocation = {Berlin},
series       = {Lecture Notes in Computer Science},
year         = {2011},
month        = {September},
volume       = {6966},
publisher    = {Springer},
issn         = {0302-9743},
refereed     = {y},
class        = { H.5; H.3.7; J.5},
group        = {INS2},
language     = {en},
abstract     = {In many heritage institutes, objects are routinely described 
using terms from predefined vocabularies.
 When object collections need 
to be merged or linked, the question arises how those vocabularies relate. 
In practice
 it often unclear for data providers how well alignment tools 
will perform on their specific vocabularies. This creates
 a bottleneck to 
align vocabularies, as data providers want to have tight control over the 
quality of their data. We
 will discuss the key limitations of current tools 
in more detail and propose an alternative approach. We will show how
 
this approach has been used in two alignment use cases, and demonstrate 
how it is currently supported by our Amalgame
 alignment platform. 
},
url          = {http://semanticweb.cs.vu.nl/lod/tpdl2011/paper.pdf},
}

In many heritage institutes, objects are routinely described using terms from predefined vocabularies. When object collections need to be merged or linked, the question arises how those vocabularies relate. In practice it often unclear for data providers how well alignment tools will perform on their specific vocabularies. This creates a bottleneck to align vocabularies, as data providers want to have tight control over the quality of their data. We will discuss the key limitations of current tools in more detail and propose an alternative approach. We will show how this approach has been used in two alignment use cases, and demonstrate how it is currently supported by our Amalgame alignment platform.

@inproceedings{18473,
author       = {Tordai, A. and van Ossenbruggen, J. R. and Schreiber, A. T. and Wielinga, B.},
title        = {Let's {Agree} {To} {Disagree}: {On} {The} {Evaluation} {Of} {Vocabulary} {Alignment} },
booktitle    = {Proceedings of the International Conference on Knowledge Capture 2011},
conferencetitle    = {International Conference on Knowledge Capture},
conferencedate     = {2011, June 25 - June 29},
conferencelocation = {Banff, Canada},
year         = {2011},
month        = {June},
publisher    = {ACM Press},
refereed     = {y},
group        = {INS2},
language     = {en},
url          = {http://homepages.cwi.nl/%7Ejrvosse/publications/2011/kcap2011_tordai.pdf},
}

@inproceedings{18476,
author       = {Gligarov, R. and Hildebrand, M. and van Ossenbruggen, J. R. and Schreiber, G. and Aroyo, L.},
title        = {On {The} {Role} {Of} {User-}{Generated} {Metadata} {In} {Audio} {Visual} {Collections}},
booktitle    = {Proceedings of the International Conference on Knowledge Capture 2011},
conferencetitle    = {International Conference on Knowledge Capture},
conferencedate     = {2011, June 25 - June 29},
conferencelocation = {Banff, Canada},
pages        = {145 - 151},
year         = {2011},
month        = {June},
publisher    = {ACM Press},
isbn         = {978-1-4503-0396-5},
refereed     = {y},
size         = {7p.},
class        = { H.2.5; J.5},
group        = {INS2},
language     = {en},
abstract     = {Recently, various crowdsourcing initiatives showed that targeted efforts of
user communities result in massive
 amounts of tags. For example, the
Netherlands Institute for Sound and Vision collected a large number of tags
with the
 video labeling game \emph{Waisda?}. To successfully utilize these
tags, a better understanding of their characteristics
 is required.
The goal of this paper is twofold: (i) to investigate the vocabulary that
users employ when describing videos
 and compare it to the vocabularies used by
professionals; and (ii) to establish which aspects of the video are typically
described
 and what type of tags are used for this. We report on an analysis of
the tags collected with \emph{Waisda?}. With respect
 to the first goal, we
compared the the tags with a typical domain thesaurus used by professionals,
as well as with a more
 general vocabulary. With respect to the second goal, we
compare the tags to the video subtitles to determine how many tags
 are derived
from the audio signal. In addition, we perform a qualitative study in which a
tag sample is interpreted in
 terms of an existing annotation classification
framework. The results suggest that the tags complement the metadata provided
by
 professional cataloguers, the tags describe both the audio and the visual
aspects of the video, and the users primarily
 describe objects in the video
using general descriptions.
},
url          = {http://oai.cwi.nl/oai/asset/18476/18476D.pdf},
url          = {http://homepages.cwi.nl/%7Ejrvosse/publications/2011/kcap2011_gligorov.pdf},
}

Recently, various crowdsourcing initiatives showed that targeted efforts of user communities result in massive amounts of tags. For example, the Netherlands Institute for Sound and Vision collected a large number of tags with the video labeling game \emphWaisda?. To successfully utilize these tags, a better understanding of their characteristics is required. The goal of this paper is twofold: (i) to investigate the vocabulary that users employ when describing videos and compare it to the vocabularies used by professionals; and (ii) to establish which aspects of the video are typically described and what type of tags are used for this. We report on an analysis of the tags collected with \emphWaisda?. With respect to the first goal, we compared the the tags with a typical domain thesaurus used by professionals, as well as with a more general vocabulary. With respect to the second goal, we compare the tags to the video subtitles to determine how many tags are derived from the audio signal. In addition, we perform a qualitative study in which a tag sample is interpreted in terms of an existing annotation classification framework. The results suggest that the tags complement the metadata provided by professional cataloguers, the tags describe both the audio and the visual aspects of the video, and the users primarily describe objects in the video using general descriptions.

@inproceedings{18477,
author       = {van de Akker, C. and Legêne, S and van Erp, M. and Aroyo, L. and Segers, R. and van der Meij, L. and van Ossenbruggen, J. R. and Schreiber, G. and Wielinga, B. and Oomen, J. and Jacobs, G.},
title        = {Digital {Hermeneutics}: {Agora} {And} {The} {Online} {Understanding} 
{Of} {Cultural} {Heritage} 
},
booktitle    = {Proceedings of Web Science 2011},
conferencetitle    = {Web Science},
conferencedate     = {2011, June 14 - June 17},
conferencelocation = {Koblenz},
year         = {2011},
month        = {June},
publisher    = {ACM},
refereed     = {y},
group        = {INS2},
language     = {en},
url          = {http://www.websci11.org/fileadmin/websci/Papers/116_paper.pdf},
}

@inproceedings{18478,
author       = {van Erp, M. and Oomen, J. and Segers, R. and van de Akker, C. and Aroyo, L. and Jacobs, G. and Legêne, S and van der Meij, L. and van Ossenbruggen, J. R. and Schreiber, G.},
title        = {Automatic {Heritage} {Metadata} {Enrichment} {With} {Historic} {Events} },
booktitle    = {Proceedings of International Conference for Culture and Heritage On-line-Museums and the Web 2011},
conferencetitle    = {International Conference for Culture and Heritage On-line-Museums and the Web},
conferencedate     = {2011, April 6 - April 9},
conferencelocation = {Philadelphia, PA},
year         = {2011},
month        = {April},
publisher    = {Archimuse},
refereed     = {y},
group        = {INS2},
language     = {en},
abstract     = {Most digitised and online available objects from GLAMs (Galleries, Libraries, Archives, Museums) can be browsed
 through a predefined set of formal metadata, such as its creator, year of creation, and type of material. Standards for
 metadata management and exchange have matured and are being adopted widely. They enable intra-collection search and exploration,
 and are also main drivers behind supporting domain and cross-boundary access to collections.

However, these formal metadata
 often do not give access to information pertaining to the content of the object, such as its topic, or what is depicted.
 This information is often given through textual descriptions which are mostly only accessible through keyword search. Keyword
 search is limited in the sense that it does not facilitate sorting, or retrieving objects whose descriptions contain terms
 that are synonymous to the search term.

This paper provides results of an interdisciplinary research project, Agora,
 that is taking collection access one step further by enabling users to search and browse museum collections through the
 content descriptions of objects in a structured way. The three-year Agora project is funded by the Netherlands Organisation
 for Scientific Research and brings together computer scientists, cultural heritage experts, and humanities researchers.},
url          = {http://conference.archimuse.com/mw2011/programs/automatic_metadata_enrichment_and_linking_fo},
}

Most digitised and online available objects from GLAMs (Galleries, Libraries, Archives, Museums) can be browsed through a predefined set of formal metadata, such as its creator, year of creation, and type of material. Standards for metadata management and exchange have matured and are being adopted widely. They enable intra-collection search and exploration, and are also main drivers behind supporting domain and cross-boundary access to collections. However, these formal metadata often do not give access to information pertaining to the content of the object, such as its topic, or what is depicted. This information is often given through textual descriptions which are mostly only accessible through keyword search. Keyword search is limited in the sense that it does not facilitate sorting, or retrieving objects whose descriptions contain terms that are synonymous to the search term. This paper provides results of an interdisciplinary research project, Agora, that is taking collection access one step further by enabling users to search and browse museum collections through the content descriptions of objects in a structured way. The three-year Agora project is funded by the Netherlands Organisation for Scientific Research and brings together computer scientists, cultural heritage experts, and humanities researchers.

@incollection{19265,
author       = {Hildebrand, M. and van Ossenbruggen, J. R. and Hardman, L.},
editor       = {Troncy, R. and Huet, B. and Schenk , S.},
title        = {The {Role} {Of} {Explicit} {Semantics} {In} {Search} {And} {Browsing}},
booktitle    = {Multimedia Semantics: Metadata, Analysis and Interaction},
pages        = {261 - 278},
year         = {2011},
month        = {August},
publisher    = {Wiley},
isbn         = {978-0-470-74700-1},
size         = {18p.},
group        = {INS2},
scndgroup    = {INS},
language     = {en},
url          = {http://oai.cwi.nl/oai/asset/19265/19265C.pdf},
}

@inproceedings{19578,
author       = {Boscarino, C. and de Vries, A. P. and Hollink, V. and van Ossenbruggen, J. R.},
title        = {Implicit {Relevance} {Feedback} {From} {A} {Multi-{Step}} {Search} {Process}: {A} {Use} {Of} {Query}{-{Logs}}},
booktitle    = {Proceedings of ECIR 2011 Workshop on Information Retrieval Over Query Sessions 2011},
conferencetitle    = {ECIR 2011 Workshop on Information Retrieval Over Query Sessions},
conferencedate     = {2011, 2011-04-18},
conferencelocation = {Dublin (IRL)},
year         = {2011},
month        = {March},
publisher    = {Springer},
refereed     = {y},
keywords     = {clickthrough data, language models, retrieval over sessions},
group        = {INS2},
language     = {en},
abstract     = {We evaluate the use of clickthrough information as implicit relevance feedback in sessions. We employ records
 of user interactions with a search system for pictures retrieval: issued queries, clicked images, and purchased content;
 we investigate whether and how much of the past search history should be used in a feedback loop. We also assess the benefit
 of using clicked data as positive tokens of relevance to the task of estimating the probability of an image to be purchased.},
url          = {http://oai.cwi.nl/oai/asset/19578/19578B.pdf},
}

We evaluate the use of clickthrough information as implicit relevance feedback in sessions. We employ records of user interactions with a search system for pictures retrieval: issued queries, clicked images, and purchased content; we investigate whether and how much of the past search history should be used in a feedback loop. We also assess the benefit of using clicked data as positive tokens of relevance to the task of estimating the probability of an image to be purchased.

@inproceedings{15288,
author       = {Amin, A. K. and Hildebrand, M. and van Ossenbruggen, J. R. and Hardman, L.},
title        = {Designing {A} {Thesaurus-}{Based} {Comparison} {Search} {Interface} {For} {Linked} {Cultural} {Heritage} {Sources}},
booktitle    = {Proceedings of the international conference on Intelligent user interfaces 2010 (14)},
conferencetitle    = {International Conference on Intelligent User Interfaces},
conferencedate     = {2010, February 07 - 10},
conferencelocation = {Hong Kong, China},
pages        = {249 - 258},
year         = {2010},
month        = {February},
publisher    = {ACM},
isbn         = {978-1-60558-515},
refereed     = {y},
size         = {10p.},
class        = { H.5.2},
keywords     = {comparison search, thesauri, cultural heritage},
group        = {INS2},
language     = {en},
project      = {Non-NWO Project 1},
abstract     = {Comparison search is an information seeking task where a user examines individual items or sets of items
 for similarities and differences. While this is a known information need among experts and knowledge workers, appropriate
 tools are not available. In this paper, we discuss comparison search in the cultural heritage domain, a domain characterized
 by large, rich and heterogeneous data sets, where different organizations deploy different schemata and terminologies to
 describe their artifacts. This diversity makes meaningful comparison difficult. We developed a thesaurus-based comparison
 search application called LISA, a tool that allows a user to search, select and compare sets of artifacts. Different visualizations
 allow users to use different comparison strategies to cope with the underlying heterogeneous data and the complexity of
 the search tasks. We conducted two user studies. A preliminary study identifies the problems experts face while performing
 comparison search tasks. A second user study examines the effectiveness of LISA in helping to solve comparison search tasks.
 The main contribution of this paper is to establish design guidelines for the data and interface of a comparison search
 application. Moreover, we offer insights into when thesauri and metadata are appropriate for use in such applications.},
url          = {http://oai.cwi.nl/oai/asset/15288/15288D.pdf},
url          = {http://doi.acm.org/10.1145/1719970.1720005},
}

Comparison search is an information seeking task where a user examines individual items or sets of items for similarities and differences. While this is a known information need among experts and knowledge workers, appropriate tools are not available. In this paper, we discuss comparison search in the cultural heritage domain, a domain characterized by large, rich and heterogeneous data sets, where different organizations deploy different schemata and terminologies to describe their artifacts. This diversity makes meaningful comparison difficult. We developed a thesaurus-based comparison search application called LISA, a tool that allows a user to search, select and compare sets of artifacts. Different visualizations allow users to use different comparison strategies to cope with the underlying heterogeneous data and the complexity of the search tasks. We conducted two user studies. A preliminary study identifies the problems experts face while performing comparison search tasks. A second user study examines the effectiveness of LISA in helping to solve comparison search tasks. The main contribution of this paper is to establish design guidelines for the data and interface of a comparison search application. Moreover, we offer insights into when thesauri and metadata are appropriate for use in such applications.

@techreport{15324,
author       = {Hildebrand, M. and van Ossenbruggen, J. R. and Hardman, L. and Wielemaker, J. and Schreiber, G.},
title        = {Searching {In} {Semantically} {Rich} {Linked} {Data}: {A} {Case} {Study} {In} {Cultural} {Heritage}},
type         = {CWI Technical Report},
origin       = {other},
series       = {Information Systems [INS]},
pages        = {1 - 24},
year         = {2010},
month        = {February},
number       = {INS-1001},
publisher    = {CWI},
issn         = {1386-3681},
institution  = {CWI},
size         = {24p.},
keywords     = {Semantic search, linked data, cultural heritage, user study},
group        = {INS2},
language     = {en},
project      = {Non-NWO Project 1},
abstract     = {Traditionally the relations between concepts from a controlled vocabulary, such as the hierarchical and associative
 relations in a thesaurus, have been used to support users in their search process. In the context of the Semantic Web, multiple
 interlinked vocabularies are becoming available, providing a large number of different relations between concepts. However,
 for a specific search task, only a small fraction of these will be meaningful to the user, and currently we have little
 understanding of which methods can be used to determine this. In this paper, we describe a case study in the cultural heritage
 domain that investigates support for the specific task of finding artworks in a data set of multiple linked art collections
 and vocabularies. In a first experiment a number of use cases from domain experts are collected and the paths in the data
 graph by which artworks can be found are analysed. A number of different types of paths are identified and their usefulness
 is qualitatively evaluated. In a second experiment we explore how the different path types can be used in a semantic search
 algorithm to support the intended search behavior indicated by the experts. We conclude that effective end-user support
 requires a highly interactive application in which the user can explore multiple search strategies. Based on our findings
 we discuss the implications on the design of such an interactive search application.},
url          = {http://oai.cwi.nl/oai/asset/15324/15324D.pdf},
}

Traditionally the relations between concepts from a controlled vocabulary, such as the hierarchical and associative relations in a thesaurus, have been used to support users in their search process. In the context of the Semantic Web, multiple interlinked vocabularies are becoming available, providing a large number of different relations between concepts. However, for a specific search task, only a small fraction of these will be meaningful to the user, and currently we have little understanding of which methods can be used to determine this. In this paper, we describe a case study in the cultural heritage domain that investigates support for the specific task of finding artworks in a data set of multiple linked art collections and vocabularies. In a first experiment a number of use cases from domain experts are collected and the paths in the data graph by which artworks can be found are analysed. A number of different types of paths are identified and their usefulness is qualitatively evaluated. In a second experiment we explore how the different path types can be used in a semantic search algorithm to support the intended search behavior indicated by the experts. We conclude that effective end-user support requires a highly interactive application in which the user can explore multiple search strategies. Based on our findings we discuss the implications on the design of such an interactive search application.

@inproceedings{16987,
author       = {Boscarino, C. and de Vries, A. P. and van Ossenbruggen, J. R.},
title        = {Better {Search} {Applications} {Through} {Domain} {Specific} {Context} {Descriptions}: {A} {Position} {Paper}},
booktitle    = {Proceedings of the Fourth Workshop on Human-Computer Interaction and Information Retrieval},
conferencetitle    = {Workshop on Human-Computer Interaction and Information Retrieval },
conferencedate     = {2010, 22 Aug 2010},
conferencelocation = {New Brunswick, NJ },
year         = {2010},
month        = {August},
publisher    = {MSFT research},
refereed     = {y},
group        = {INS2},
language     = {en},
abstract     = {There is a wide agreement that a user centred approach to IR applications design outperforms system centred
 ones.
A classic understanding of this design approach, and specifically of its underlying notion of context, appeared however
 insufficient to explain the results of a pilot experiment.
We recognise the importance of context, but we define context
 differently by means of a domain theory: a conceptualisation of the domain at hand, preferably developed within the same
 community which users belong to.},
url          = {http://research.microsoft.com/en-us/um/people/ryenw/hcir2010/docs/HCIR2010Proceedings.pdf},
}

There is a wide agreement that a user centred approach to IR applications design outperforms system centred ones. A classic understanding of this design approach, and specifically of its underlying notion of context, appeared however insufficient to explain the results of a pilot experiment. We recognise the importance of context, but we define context differently by means of a domain theory: a conceptualisation of the domain at hand, preferably developed within the same community which users belong to.

@inproceedings{17076,
author       = {Tordai, A. and van Ossenbruggen, J. R. and Schreiber, G. and Wielinga, B.},
title        = {Aligning {Large} {S{KOS}-}{Like} {Vocabularies}},
booktitle    = {Proceedings of European Semantic Web Conference 2010 (7)},
conferencetitle    = {European Semantic Web Conference},
conferencedate     = {2010, May 30 - June 3},
conferencelocation = {Heraklion, Crete, Greece},
series       = {Lecture Notes in Computer Science},
pages        = {198 - 212},
year         = {2010},
month        = {May},
volume       = {6088},
publisher    = {Springer},
isbn         = {978-3-642-13485-2},
issn         = {0302-9743},
refereed     = {y},
size         = {15p.},
group        = {INS2},
language     = {en},
project      = {Non-NWO Project 1},
abstract     = {In this paper we build on our methodology for combining and selecting alignment techniques for vocabularies,
 with two alignment case studies of large vocabularies in two languages. Firstly, we analyze the vocabularies and based on
 that analysis choose our alignment techniques. Secondly, we test our hypothesis based on earlier work that first generating
 alignments using simple lexical alignment techniques, followed by a separate disambiguation of alignments performs best
 in terms of precision and recall. The experimental results show, for example, that this combination of techniques provides
 an estimated precision of 0.7 for a sample of the 12,725 concepts for which alignments were generated (of the total 27,992
 concepts). Thirdly, we explain our results in light of the characteristics of the vocabularies and discuss their impact
 on the alignments techniques.},
url          = {http://dx.doi.org/10.1007/978-3-642-13486-9_14},
}

In this paper we build on our methodology for combining and selecting alignment techniques for vocabularies, with two alignment case studies of large vocabularies in two languages. Firstly, we analyze the vocabularies and based on that analysis choose our alignment techniques. Secondly, we test our hypothesis based on earlier work that first generating alignments using simple lexical alignment techniques, followed by a separate disambiguation of alignments performs best in terms of precision and recall. The experimental results show, for example, that this combination of techniques provides an estimated precision of 0.7 for a sample of the 12,725 concepts for which alignments were generated (of the total 27,992 concepts). Thirdly, we explain our results in light of the characteristics of the vocabularies and discuss their impact on the alignments techniques.

@inproceedings{17079,
author       = {Tordai, A. and van Ossenbruggen, J. R. and Ghazvinian, A. and Musen, M. A. and Noy, N. F.},
title        = {Lost {In} {Translation}? {Empirical} {Analysis} {Of} {Mapping} {Compositions} {For} {Large} {Ontologies}},
booktitle    = {Proceedings of International Workshop on Ontology Matching  2010 (5)},
conferencetitle    = {International Workshop on Ontology Matching },
conferencedate     = {2010, November 7},
conferencelocation = {Shanghai},
year         = {2010},
month        = {November},
publisher    = {Stichting Mathematisch Centrum},
refereed     = {y},
group        = {INS2},
language     = {en},
project      = {Non-NWO Project 1},
abstract     = {When three or more ontologies have been aligned, longer chains of mapped concepts start to appear. In this
 paper, we empirically study the nature of these composite mappings, focusing on chains of (near) equivalence links
of length
 two. We ask human experts to evaluate samples of composite mappings, taken from large real life data sets. Based on these
 evaluations, we analyze the features of mappings produced by composition in three different domains
(bio-medicine, cultural
 heritage, and library subject headings), among ontologies in multiple languages (English, Dutch, German, and French), and
 using existing
mappings that were created by different methods (lexical and instance-based methods).We examine the quality
 of the composite mappings relative to the quality
of the input mappings and analyze how characteristics of the input mappings
 and the ontologies influence the composition.},
url          = {http://www.dit.unitn.it/~p2p/OM-2010/om2010_Tpaper2.pdf},
}

When three or more ontologies have been aligned, longer chains of mapped concepts start to appear. In this paper, we empirically study the nature of these composite mappings, focusing on chains of (near) equivalence links of length two. We ask human experts to evaluate samples of composite mappings, taken from large real life data sets. Based on these evaluations, we analyze the features of mappings produced by composition in three different domains (bio-medicine, cultural heritage, and library subject headings), among ontologies in multiple languages (English, Dutch, German, and French), and using existing mappings that were created by different methods (lexical and instance-based methods).We examine the quality of the composite mappings relative to the quality of the input mappings and analyze how characteristics of the input mappings and the ontologies influence the composition.

@inproceedings{17080,
author       = {Gligarov, R. and Baltussen, L. B. and van Ossenbruggen, J. R. and Aroyo, L. and Brinkerink, M. and Oomen, J. and van Ees, A.},
title        = {Towards {Integration} {Of} {End-{User}} {Tags} {With} {Professional} {Annotations}},
booktitle    = {Proceedings of Web Science 2010: Extending the Frontiers of Society On-Line},
conferencetitle    = {Web Science},
conferencedate     = {2010, April 26-27},
conferencelocation = {Raleigh, North Carolina, US},
year         = {2010},
month        = {April},
publisher    = {The Web Science Trust},
refereed     = {y},
group        = {INS2},
language     = {en},
abstract     = {The goal of the paper is assessing the quality of end-user tags from a video labeling game as a first step
 in the process of integrating them with the annotations made by professionals. Tags lack precise meaning, whereas the terms
 and concepts the professionals are used to have a clearly defined semantics given by structured vocabularies. Hence, we
 explore the possibility of mapping user tags to their semantic counterparts from domain and lexical vocabularies. Furthermore,
 we report on an analysis performed by a senior cataloguer regarding the general usefulness of the user tags in terms of
 video and fragment retrieval. Finally, we investigate the distribution of tags with respect to audio and visual portion
 of the video content.},
url          = {http://journal.webscience.org/363/2/websci10_submission_65.pdf},
}

The goal of the paper is assessing the quality of end-user tags from a video labeling game as a first step in the process of integrating them with the annotations made by professionals. Tags lack precise meaning, whereas the terms and concepts the professionals are used to have a clearly defined semantics given by structured vocabularies. Hence, we explore the possibility of mapping user tags to their semantic counterparts from domain and lexical vocabularies. Furthermore, we report on an analysis performed by a senior cataloguer regarding the general usefulness of the user tags in terms of video and fragment retrieval. Finally, we investigate the distribution of tags with respect to audio and visual portion of the video content.

@techreport{13282,
author       = {Amin, A. K. and Hildebrand, M. and van Ossenbruggen, J. R. and Evers, V. and Hardman, L.},
title        = {List, {Group} {Or} {Menu}: {Organizing} {Suggestions} {In} {Autocompletion} {Interfaces}},
type         = {CWI Technical Report},
origin       = {other},
series       = {Information Systems [INS]},
year         = {2009},
month        = {January},
number       = {INS-E0901},
publisher    = {CWI},
issn         = {1386-3681},
institution  = {CWI},
keywords     = {autocompletion },
group        = {INS2},
language     = {en},
project      = {Non-NWO Project 1},
abstract     = {We describe two user studies that investigate organization strategies
of autocompletion in a known-item
 search task: searching for terms taken from
a thesaurus. In Study 1, we explored ways of grouping term suggestions from
two
 different thesauri (TGN and WordNet) and found that different thesauri may
require different organization strategies. Users
 found Group organization more
appropriate to organize location names from TGN, while Alphabetical works better
for WordNet.
 In Study 2, we compared three different organization strategies
(Alphabetical, Group and Composite) for location name search
 tasks. The results
indicate that for TGN autocompletion interfaces help improve the quality
of keywords, Group and Composite
 organization help users search faster, and is
perceived easier to understand and to use than Alphabetical.},
url          = {http://oai.cwi.nl/oai/asset/13282/13282A.pdf},
}

We describe two user studies that investigate organization strategies of autocompletion in a known-item search task: searching for terms taken from a thesaurus. In Study 1, we explored ways of grouping term suggestions from two different thesauri (TGN and WordNet) and found that different thesauri may require different organization strategies. Users found Group organization more appropriate to organize location names from TGN, while Alphabetical works better for WordNet. In Study 2, we compared three different organization strategies (Alphabetical, Group and Composite) for location name search tasks. The results indicate that for TGN autocompletion interfaces help improve the quality of keywords, Group and Composite organization help users search faster, and is perceived easier to understand and to use than Alphabetical.

@inproceedings{13425,
author       = {Hildebrand, M. and van Ossenbruggen, J. R.},
title        = {Configuring {Semantic} {Web} {Interfaces} {By} {Data} {Mapping}},
booktitle    = {Proceedings of the VISSW 2009 Workshop: Visual Interfaces to the Social and the Semantic Web},
conferencetitle    = {Visual Interfaces to the Social and the Semantic Web},
conferencedate     = {2009, February 8},
conferencelocation = {Sanibel Island, Florida},
series       = {Proceedings of the VISSW Workshop: Visual Interfaces to the Social and the Semantic Web},
year         = {2009},
month        = {February},
refereed     = {y},
keywords     = {Interface design, heterogeneous data, ClioPatria, YUI},
group        = {INS2},
language     = {en},
project      = {Non-NWO Project 1},
abstract     = {We demonstrate how to develop Web-based user interfaces
for Semantic Web applications using commonly available,
 off-the-shelf
Web widget libraries. By formally defining the underlying data model
that is assumed by these widgets, Semantic
 Web application developers
can use familiar RDF constructs to map their own data to the model
implemented by the Widgets.
  As an example, we briefly describe the
interface model underlying our own framework, and provide concrete
examples showing
 how it has been used to create Semantic Web
applications in two different domains.  We conclude by discussing the
advantages
 and limitations of our approach.},
url          = {http://oai.cwi.nl/oai/asset/13425/13425B.pdf},
url          = {http://smart-ui.org/events/vissw2009/papers/VISSW2009-Hildebrand.pdf},
}

We demonstrate how to develop Web-based user interfaces for Semantic Web applications using commonly available, off-the-shelf Web widget libraries. By formally defining the underlying data model that is assumed by these widgets, Semantic Web application developers can use familiar RDF constructs to map their own data to the model implemented by the Widgets. As an example, we briefly describe the interface model underlying our own framework, and provide concrete examples showing how it has been used to create Semantic Web applications in two different domains. We conclude by discussing the advantages and limitations of our approach.

@inproceedings{13988,
author       = {Tordai, A. and van Ossenbruggen, J. R. and Schreiber, G.},
title        = {Combining {Vocabulary} {Alignment} {Techniques}},
booktitle    = {Proceedings of The Fifth International Conference on Knowledge Capture},
conferencetitle    = {International Conference on Knowledge Capture},
conferencedate     = {2009, 1 – 4 September},
conferencelocation = {Redondo Beach, California},
year         = {2009},
month        = {September},
publisher    = {Stichting Mathematisch Centrum},
refereed     = {y},
class        = { I.2.4},
keywords     = {vocabulary alignment, case study, cultural heritage},
group        = {INS2},
language     = {en},
project      = {Non-NWO Project 1},
abstract     = {Identifying alignments between vocabularies has become a central knowledge engineering activity. A plethora
 of alignment techniques has been developed over the 
past years. In this paper we present a case study in which we examine
 and evaluate the practical use of three typical alignment techniques.  The study involves 
the alignment of two vocabularies
 used in a semantic-search engine for cultural-heritage objects. We show that a sequence can be beneficial. The case study
 give
s insight into evaluation issues, such as techniques for identification of false positives. We see this work as a
 step to a badly-needed methodology for alignment. 
},
url          = {http://www.cs.vu.nl/%7Eguus/papers/Tordai09a.pdf},
}

Identifying alignments between vocabularies has become a central knowledge engineering activity. A plethora of alignment techniques has been developed over the past years. In this paper we present a case study in which we examine and evaluate the practical use of three typical alignment techniques. The study involves the alignment of two vocabularies used in a semantic-search engine for cultural-heritage objects. We show that a sequence can be beneficial. The case study give s insight into evaluation issues, such as techniques for identification of false positives. We see this work as a step to a badly-needed methodology for alignment.

@article{13989,
author       = {Hildebrand, M. and van Ossenbruggen, J. R. and Hardman, L. and Jacobs, G.},
title        = {Supporting {Subject} {Matter} {Annotation} {Using} {Heterogeneous} {Thesauri}, {A} {User} {Study} {In} {Web} {Data} {Reuse}},
journal      = {International Journal of Human-Computer Studies},
pages        = {888 - 903},
year         = {2009},
month        = {October},
number       = {10},
volume       = {67},
publisher    = {Academic Press},
issn         = {1071-5819},
refereed     = {y},
size         = {16p.},
class        = { H.5.2; H.3.3},
keywords     = {Heterogeneous data, data integration and reuse, semantic annotation, cultural heritage},
group        = {INS2},
language     = {en},
project      = {Non-NWO Project 1},
abstract     = {We performed a user experiment in which museum professionals used vocabularies from the Web for annotating
 the subject matter of museum objects. We study the requirements on the underlying RDF dataset, search algorithms and user
 interface design in a real world setting. We identify the advantages of reusing vocabularies from the Web and discuss how
 and to what extent the disadvantages can be overcome. The study is performed at the Print Room of the Rijksmuseum Amsterdam,
 where currently a large collection of prints, photographs and 
drawings is being catalogued. We report on the analysis
 of the current practice of professional cataloguers, the iterative design of an annotation tool and a qualitative evaluation
 of this tool with a user experiment in a realistic annotation environment. We discuss our findings in terms of their impact
 on the RDF data, the semantic search functionality and the user interface.},
url          = {http://oai.cwi.nl/oai/asset/13989/13989D.pdf},
url          = {http://dx.doi.org/10.1016/j.ijhcs.2009.07.008},
}

We performed a user experiment in which museum professionals used vocabularies from the Web for annotating the subject matter of museum objects. We study the requirements on the underlying RDF dataset, search algorithms and user interface design in a real world setting. We identify the advantages of reusing vocabularies from the Web and discuss how and to what extent the disadvantages can be overcome. The study is performed at the Print Room of the Rijksmuseum Amsterdam, where currently a large collection of prints, photographs and drawings is being catalogued. We report on the analysis of the current practice of professional cataloguers, the iterative design of an annotation tool and a qualitative evaluation of this tool with a user experiment in a realistic annotation environment. We discuss our findings in terms of their impact on the RDF data, the semantic search functionality and the user interface.

@inproceedings{14046,
author       = {Amin, A. K. and Townsend, S. and van Ossenbruggen, J. R. and Hardman, L.},
editor       = {Gross, T. and Gulliksen, J. and Kotzé, P. and Oestreicher, L. and Palanque, P. A. and Winckler, M. and Oliveira Prates, R.},
title        = {Fancy {A} {Drink} {In} {Canary} {Wharf}? {A} {User} {Study} {On} {Location-{Based}}  {Mobile} {Search}},
booktitle    = {Proceedings of IFIP TC13 International Conference on Human-Computer Interaction 2009 (12)},
conferencetitle    = {IFIP TC13 International Conference on Human-Computer Interaction},
conferencedate     = {2009, August 24-28},
conferencelocation = {Uppsala, Sweden},
series       = {Lecture Notes in Computer Science},
pages        = {736 - 749},
year         = {2009},
month        = {August},
volume       = {5726},
publisher    = {Springer},
isbn         = {978-3-642-03654},
issn         = {0302-9743},
refereed     = {y},
size         = {14p.},
group        = {INS2},
language     = {en},
project      = {Non-NWO Project 1},
url          = {http://oai.cwi.nl/oai/asset/14046/14046A.pdf},
url          = {http://dx.doi.org/10.1007/978-3-642-03655-2_80},
}

@inproceedings{14047,
author       = {Amin, A. K. and Hildebrand, M. and van Ossenbruggen, J. R. and Evers, V. and Hardman, L.},
editor       = {Boughanem, M. and Berrut, C. and Mothe, M. and Soulé-Dupuy, C.},
title        = {Organizing {Suggestions} {In} {Autocompletion} {Interfaces}},
booktitle    = {Proceedings of the European Conference on Information Retrieval},
conferencetitle    = {European Conference on Information Retrieval},
conferencedate     = {2009, April 6-9},
conferencelocation = {Toulouse, France},
series       = {Lecture Notes in Computer Science},
pages        = {521 - 529},
year         = {2009},
month        = {April},
volume       = {5478},
publisher    = {Springer},
isbn         = {978-3-642-00957},
issn         = {0302-9743},
refereed     = {y},
size         = {9p.},
group        = {INS2},
language     = {en},
project      = {Non-NWO Project 1},
url          = {http://dx.doi.org/10.1007/978-3-642-00958-7_46},
}

@inproceedings{14746,
author       = {Hardman, L. and van Ossenbruggen, J. R. and Troncy, R. and Amin, A. K. and Hildebrand, M.},
title        = {Interactive {Information} {Access} {On} {The} {Web} {Of} {Data}},
booktitle    = {Proceedings of WebSci 2009},
conferencetitle    = {WebSci: Society On-Line},
conferencedate     = {2009, March 18 - March 20},
conferencelocation = {Athens},
year         = {2009},
month        = {March},
publisher    = {Web Science Research Initiative},
note         = {Unclear whether this is an electronic journal or conference proceedings.  (The event was a conference.)},
refereed     = {y},
keywords     = {Information access, Linked Data, User interface},
group        = {INS2},
language     = {en},
project      = {Non-NWO Project 1; Non-NWO Project 2},
abstract     = {The Web of data enables fragments of information to be identified, described and connected together in a
 rich information environment. Users requiring information are faced with the problem of finding out what information is
 available, and obtaining sufficient fragments to successfully carry out their task. Systems supporting these tasks can use
 the fragments, descriptions of them and relationships among them, to improve both the selection and presentation of the
 information. Questions to be answered are: which information needs can be better supported, and how can the Web of data
 help. While the construction of the linked data cloud'' is necessary to even start thinking about providing this type of
 support for users, our claim is that we first need to establish the user's information needs before establishing the potential
 roles the linked data can play in information selection and presentation. In this paper, we discuss potential uses of linked
 data to support users' information needs, give examples of using linked data to support user information seeking tasks and
 highlight future research directions.},
url          = {http://oai.cwi.nl/oai/asset/14746/14746A.pdf},
url          = {http://journal.webscience.org/212/},
}

The Web of data enables fragments of information to be identified, described and connected together in a rich information environment. Users requiring information are faced with the problem of finding out what information is available, and obtaining sufficient fragments to successfully carry out their task. Systems supporting these tasks can use the fragments, descriptions of them and relationships among them, to improve both the selection and presentation of the information. Questions to be answered are: which information needs can be better supported, and how can the Web of data help. While the construction of the linked data cloud'' is necessary to even start thinking about providing this type of support for users, our claim is that we first need to establish the user's information needs before establishing the potential roles the linked data can play in information selection and presentation. In this paper, we discuss potential uses of linked data to support users' information needs, give examples of using linked data to support user information seeking tasks and highlight future research directions.

@article{15607,
author       = {Hardman, L. and Aroyo, L. and van Ossenbruggen, J. R. and Hyvönen, E.},
title        = {Using {A{I}} {To} {Access} {And} {Experience} {Cultural} {Heritage}},
journal      = {IEEE Intelligent systems},
pages        = {23 - 25},
year         = {2009},
number       = {2},
volume       = {24},
publisher    = {IEEE},
issn         = {1541-1672},
refereed     = {y},
size         = {3p.},
keywords     = {Cultural Heritage, Artificial Intelligence, Semantic Web},
group        = {INS2},
language     = {en},
abstract     = {Cultural heritage involves rich and highly heterogeneous collections of different people, organizations and
 collections. Preserved mainly by professionals it is challenging to convey this diversity of perspectives and information
 to the general public. Professionals also experience a great deal of obstacles archiving digital collections. This special
 issue presents current trends in employing AI and Web technologies to overcome such problems.
},
url          = {http://oai.cwi.nl/oai/asset/15607/15607D.pdf},
url          = {http://doi.ieeecomputersociety.org/10.1109/MIS.2009.37 },
}

Cultural heritage involves rich and highly heterogeneous collections of different people, organizations and collections. Preserved mainly by professionals it is challenging to convey this diversity of perspectives and information to the general public. Professionals also experience a great deal of obstacles archiving digital collections. This special issue presents current trends in employing AI and Web technologies to overcome such problems.

@inproceedings{12381,
author       = {Amin, A. K. and van Ossenbruggen, J. R. and Hardman, L. and van Nispen, A.},
title        = {Understanding {Cultural} {Heritage} {Experts}’ {Information} {Seeking} {Needs}},
booktitle    = {Proceedings of the 8th ACM/IEEE joint conference on Digital libraries},
year         = {2008},
month        = {June},
publisher    = {ACM},
refereed     = {y},
keywords     = {cultural heritage experts, information seeking},
group        = {INS2},
language     = {en},
project      = {Non-NWO Project 1},
abstract     = {We report on our user study on the information seeking behavior of
cultural heritage experts and the sources
 they use to carry out search
tasks. Seventeen experts from nine cultural heritage institutes in the
Netherlands were interviewed
 and asked to answer questionnaires
about their daily search activities. The interviews helped us to better
understand
 their search motivations, types, sources and tools. A
key finding of our study is that the majority of search tasks involve
relatively
 complex information gathering. This is in contrast to the
relatively simple fact-finding oriented support provided by current
tools.
 We describe a number of strategies that experts have developed
to overcome the inadequacies of their tools. Finally, based
 on
the analysis, we derive general trends of cultural heritage experts’
information seeking needs and discuss our preliminary
 experiences
with potential solutions.},
url          = {http://oai.cwi.nl/oai/asset/12381/12381A.pdf},
url          = {http://doi.acm.org/10.1145/1378889.1378897},
}

We report on our user study on the information seeking behavior of cultural heritage experts and the sources they use to carry out search tasks. Seventeen experts from nine cultural heritage institutes in the Netherlands were interviewed and asked to answer questionnaires about their daily search activities. The interviews helped us to better understand their search motivations, types, sources and tools. A key finding of our study is that the majority of search tasks involve relatively complex information gathering. This is in contrast to the relatively simple fact-finding oriented support provided by current tools. We describe a number of strategies that experts have developed to overcome the inadequacies of their tools. Finally, based on the analysis, we derive general trends of cultural heritage experts’ information seeking needs and discuss our preliminary experiences with potential solutions.

@techreport{12425,
author       = {van Ossenbruggen, J. R. and Amin, A. K. and Hildebrand, M.},
title        = {Why {Evaluating} {Semantic} {Web} {Applications} {Is} {Difficult}},
series       = {Semantic Web User Interface Workshop CHI},
pages        = {1 - 4},
year         = {2008},
month        = {April},
number       = {SWUI-},
institution  = {CWI},
size         = {4p.},
class        = { H.5},
group        = {INS2},
language     = {en},
project      = {Non-NWO Project 1},
abstract     = {This position paper discusses our experience in evaluating
our cultural search and annotation engine. We
 identify three
aspects that determine the quality of a semantic web application
as a whole, namely: the quality of data
 set, the quality
of underlying search and inference software and the quality
of the user interface. We argue that evaluation
 of semantic
web applications is particularly difficult because of the
strong interdependency between the three aspects.},
url          = {http://oai.cwi.nl/oai/asset/12425/12425A.pdf},
url          = {http://swui.webscience.org/SWUI2008CHI/vanOssenbruggen.pdf},
}

This position paper discusses our experience in evaluating our cultural search and annotation engine. We identify three aspects that determine the quality of a semantic web application as a whole, namely: the quality of data set, the quality of underlying search and inference software and the quality of the user interface. We argue that evaluation of semantic web applications is particularly difficult because of the strong interdependency between the three aspects.

@article{13260,
author       = {Schreiber, G. and Amin, A. K. and Aroyo, L. and van Assem, M. and de Boer, V. and Hardman, L. and Hildebrand, M. and van Ossenbruggen, J. R. and Omelayenko, B. and Tordai, A. and Wielemaker, J. and Wielinga, B.},
title        = {Semantic {Annotation} {And} {Search} {Of} {Cultural-{Heritage}} {Collections}: {The} {M{ultimediaN}} {E-{Culture}} {Demonstrator}},
journal      = {Journal of Web Semantics},
pages        = {243 - 249},
year         = {2008},
month        = {November},
number       = {4},
volume       = {6},
publisher    = {ScienceDirect},
issn         = {1570-8268},
refereed     = {y},
size         = {7p.},
keywords     = {Semantic search, Digital heritage, Semantic annotation, Virtual collections},
group        = {INS2},
language     = {en},
project      = {Non-NWO Project 1},
abstract     = {In this article we describe a Semantic Web application for semantic annotation and search in large virtual
 collections of cultural-heritage objects, indexed with multiple vocabularies. During the annotation phase we harvest, enrich
 and align collection metadata and vocabularies. The semantic-search facilities support keyword-based queries of the graph
 (currently 20 M triples), resulting in semantically grouped result clusters, all representing potential semantic matches
 of the original query. We show two sample search scenario’s. The annotation and search software is open source and is
 already being used by third parties. All software is based on established Web standards, in particular HTML/XML, CSS, RDF/OWL,
 SPARQL and JavaScript.},
url          = {http://oai.cwi.nl/oai/asset/13260/13260A.pdf},
url          = {http://dx.doi.org/10.1016/j.websem.2008.08.001},
}

In this article we describe a Semantic Web application for semantic annotation and search in large virtual collections of cultural-heritage objects, indexed with multiple vocabularies. During the annotation phase we harvest, enrich and align collection metadata and vocabularies. The semantic-search facilities support keyword-based queries of the graph (currently 20 M triples), resulting in semantically grouped result clusters, all representing potential semantic matches of the original query. We show two sample search scenario’s. The annotation and search software is open source and is already being used by third parties. All software is based on established Web standards, in particular HTML/XML, CSS, RDF/OWL, SPARQL and JavaScript.

@inproceedings{13275,
author       = {Wielemaker, J. and Hildebrand, M. and van Ossenbruggen, J. R. and Schreiber, G.},
editor       = {Sheth, A. and et al},
title        = {Thesaurus-{Based} {Search} {In} {Large} {Heterogeneous} {Collections}},
booktitle    = {The Semantic Web - ISWC 2008},
conferencetitle    = {International Semantic Web Conference },
conferencelocation = {Karlsruhe, Germany},
series       = {Lecture Notes in Computer Science},
pages        = {483 - 498},
year         = {2008},
month        = {October},
volume       = {5318},
publisher    = {Springer},
isbn         = {978-3-540-88563},
issn         = {0302-9743},
refereed     = {y},
size         = {16p.},
group        = {INS2},
project      = {Non-NWO Project 1},
abstract     = {In cultural heritage, large virtual collections are coming into 
existence. Such collections contain heterogeneous
 sets of metadata and 
vocabulary concepts, originating from multiple sources. In the context 
of the E-Culture demonstrator
 we have shown earlier that such virtual 
collections can be effectively explored with keyword search and semantic 
clustering.
 In this paper we describe the design rationale of ClioPatria, 
an open-source system which provides APIs for scalable semantic
 graph 
search. The use of ClioPatria’s search strategies is illustrated with a 
realistic use case: searching for ”Picasso”.
 We discuss details of scalable 
graph search, the required OWL reasoning functionalities and show why 
SPARQL queries
 are insufficient for solving the search problem. 
},
url          = {http://oai.cwi.nl/oai/asset/13275/13275B.pdf},
url          = {http://dx.doi.org/10.1007/978-3-540-88564-1_44},
}

In cultural heritage, large virtual collections are coming into existence. Such collections contain heterogeneous sets of metadata and vocabulary concepts, originating from multiple sources. In the context of the E-Culture demonstrator we have shown earlier that such virtual collections can be effectively explored with keyword search and semantic clustering. In this paper we describe the design rationale of ClioPatria, an open-source system which provides APIs for scalable semantic graph search. The use of ClioPatria’s search strategies is illustrated with a realistic use case: searching for ”Picasso”. We discuss details of scalable graph search, the required OWL reasoning functionalities and show why SPARQL queries are insufficient for solving the search problem.

@techreport{12283,
author       = {Amin, A. K. and van Ossenbruggen, J. R. and Hardman, L. and van Nispen, A.},
title        = {Understanding {Experts}' {Information} {Seeking} {Needs}: {A} {User} {Study} {In} {The} {Cultural} {Heritage} {Domain}},
series       = {Information Systems [INS]},
year         = {2007},
number       = {INS-E0707},
publisher    = {CWI},
issn         = {1386-3681},
class        = { H.3.3; H.5.2},
keywords     = {cultural heritage experts, user study, search behavior, task analysis"},
group        = {INS2},
language     = {en},
project      = {Non-NWO Project 1},
abstract     = { },
url          = {http://oai.cwi.nl/oai/asset/12283/12283D.pdf},
}

@techreport{12297,
author       = {Hildebrand, M. and van Ossenbruggen, J. R. and Amin, A. K. and Aroyo, L. and Wielemaker, J. and Hardman, L.},
title        = {The {Design} {Space} {Of} {A} {Configurable} {Autocompletion} {Component}},
series       = {Information Systems [INS]},
year         = {2007},
number       = {INS-E0708},
publisher    = {CWI},
issn         = {1386-3681},
class        = { H.5.2; H.3.3},
keywords     = {Semantic autocompletion, configurable interface component, sorting, clustering, presentation, RDF"},
group        = {INS2},
language     = {en},
abstract     = {Autocompletion is a commonly used interface feature in diverse applications. Semantic Web data has, on the
 one hand, the potential to provide new functionality by exploiting the semantics in the data used for generating autocompletion
 suggestions. Semantic Web applications, on the other hand, typically pose extra requirements on the semantic properties
 of the suggestions given. When the number of syntactic matches becomes too large, some means of selecting a semantically
 meaningful subset of suggestions to be presented to the user is needed. In this paper we identify a number of key design
 dimensions of autocompletion interface components. Our hypothesis is that a one-size-fits-all solution to autocompletion
 interface components does not exist, because different tasks and different data sets require interfaces corresponding to
 different points in our design space. We present a fully configurable architecture, which can be used to configure autocompletion
 components to the desired point in this design space. The architecture has been implemented as an open source software component
 that can be plugged into a variety of applications. We report on the results of a user evaluation that confirms this hypothesis,
 and describe the need to evaluate semantic autocompletion in a task and application-specific context.
},
url          = {http://oai.cwi.nl/oai/asset/12297/12297D.pdf},
}

Autocompletion is a commonly used interface feature in diverse applications. Semantic Web data has, on the one hand, the potential to provide new functionality by exploiting the semantics in the data used for generating autocompletion suggestions. Semantic Web applications, on the other hand, typically pose extra requirements on the semantic properties of the suggestions given. When the number of syntactic matches becomes too large, some means of selecting a semantically meaningful subset of suggestions to be presented to the user is needed. In this paper we identify a number of key design dimensions of autocompletion interface components. Our hypothesis is that a one-size-fits-all solution to autocompletion interface components does not exist, because different tasks and different data sets require interfaces corresponding to different points in our design space. We present a fully configurable architecture, which can be used to configure autocompletion components to the desired point in this design space. The architecture has been implemented as an open source software component that can be plugged into a variety of applications. We report on the results of a user evaluation that confirms this hypothesis, and describe the need to evaluate semantic autocompletion in a task and application-specific context.

@techreport{12302,
author       = {Hildebrand, M. and van Ossenbruggen, J. R. and Hardman, L.},
title        = {An {Analysis} {Of} {Search-{Based}} {User} {Interaction} {On} {The} {Semantic} {Web}},
series       = {Information Systems [INS]},
year         = {2007},
number       = {INS-E0706},
publisher    = {CWI},
issn         = {1386-3681},
class        = { H.3.3; H.5.2; H.5.4},
keywords     = {Semantic search, user interaction, analysis, evaluation"},
group        = {INS2},
language     = {en},
abstract     = {Many Semantic Web applications provide access to their resources through text-based search queries, using
 explicit semantics to improve the search results. This paper provides an analysis of the current state of the art in semantic
 search, based on 35 existing systems. We identify different types of semantic search features that are used during query
 construction, the core search process, the presentation of the search results and user feedback on query and results. For
 each of these, we consider the functionality that the system provides and how this is made available through the user interface.
},
url          = {http://oai.cwi.nl/oai/asset/12302/12302D.pdf},
}

Many Semantic Web applications provide access to their resources through text-based search queries, using explicit semantics to improve the search results. This paper provides an analysis of the current state of the art in semantic search, based on 35 existing systems. We identify different types of semantic search features that are used during query construction, the core search process, the presentation of the search results and user feedback on query and results. For each of these, we consider the functionality that the system provides and how this is made available through the user interface.

@techreport{12314,
author       = {Obrenovic, Z. and van Ossenbruggen, J. R.},
title        = {Integrating {Heterogeneous} {Open-}{Source} {Software} {Into} {Web} {Browsers} {Using} {A{MICO}}:{W{EB}}},
series       = {Information Systems [INS]},
year         = {2007},
number       = {INS-E0703},
publisher    = {CWI},
issn         = {1386-3681},
class        = { K.4.2; H.5.2; D.2; K.4.2},
keywords     = {Web Accessibility, User Interfaces, Open Source Software, Software Platform, Middleware"},
group        = {INS2},
language     = {en},
abstract     = {A web browser provides a uniform user interface to different types of information. Making this interface
 universally accessible and more interactive is a long term goal still far from being achieved. Universally accessible browsers
 require novel interaction modalities and additional functionalities, for which existing browsers tend to provide only partial
 solutions. Although functionality for web accessibility can be found as open-source and free software components, their
 reuse and integration is complex because they were developed in diverse implementation environments, following standards
 and conventions incompatible with the web. To enable the integration of existing partial solutions within a mainstream web
 browser environment, we have developed a middleware infrastructure, AMICO:WEB. This enables browser access to a wide variety
 of open source and free software components. The main contribution of AMICO:WEB is in enabling the syntactic interoperability
 between web extension mechanisms and a variety of integration mechanisms used by open-source and free software components.
 It also bridges the semantic differences between the high-level world of web XML-based APIs and the low-level APIs of the
 device-oriented world. We discuss the design decisions made during the development of AMICO:WEB in the context of web accessibility,
 using two typical usage scenarios: one describing a disabled user using a mainstream web browser with additional interaction
 modalities; another describing a non-disabled user browsing in a suboptimal interaction situation.},
url          = {http://oai.cwi.nl/oai/asset/12314/12314D.pdf},
}

A web browser provides a uniform user interface to different types of information. Making this interface universally accessible and more interactive is a long term goal still far from being achieved. Universally accessible browsers require novel interaction modalities and additional functionalities, for which existing browsers tend to provide only partial solutions. Although functionality for web accessibility can be found as open-source and free software components, their reuse and integration is complex because they were developed in diverse implementation environments, following standards and conventions incompatible with the web. To enable the integration of existing partial solutions within a mainstream web browser environment, we have developed a middleware infrastructure, AMICO:WEB. This enables browser access to a wide variety of open source and free software components. The main contribution of AMICO:WEB is in enabling the syntactic interoperability between web extension mechanisms and a variety of integration mechanisms used by open-source and free software components. It also bridges the semantic differences between the high-level world of web XML-based APIs and the low-level APIs of the device-oriented world. We discuss the design decisions made during the development of AMICO:WEB in the context of web accessibility, using two typical usage scenarios: one describing a disabled user using a mainstream web browser with additional interaction modalities; another describing a non-disabled user browsing in a suboptimal interaction situation.

@techreport{12324,
author       = {Amin, A. K. and Hardman, L. and van Ossenbruggen, J. R.},
title        = {Searching {In} {The} {Cultural} {Heritage} {Domain}: {Capturing} {Cultural} {Heritage} {Expert} {Information} {Seeking} {Needs}},
series       = {Information Systems [INS]},
year         = {2007},
number       = {INS-R0701},
publisher    = {CWI},
issn         = {1386-3681},
class        = { H.3.7; H.1.2},
keywords     = {cultural heritage, expert, interview, user study, knowledge acquisition, information seeking task"},
group        = {INS2},
language     = {en},
abstract     = {We report the results of a user study that captures knowledge on how cultural heritage experts search for
 information. We use a qualitative study technique with participants from four cultural heritage institutions in the Netherlands
 who were interviewed and asked to answer questionnaires about their daily work. Our goal is to acquire knowledge of their
 information seeking needs and the information sources they use. The paper provides an analysis and discussion of the issues
 that experts frequently face when searching for information.},
url          = {http://oai.cwi.nl/oai/asset/12324/12324D.pdf},
}

We report the results of a user study that captures knowledge on how cultural heritage experts search for information. We use a qualitative study technique with participants from four cultural heritage institutions in the Netherlands who were interviewed and asked to answer questionnaires about their daily work. Our goal is to acquire knowledge of their information seeking needs and the information sources they use. The paper provides an analysis and discussion of the issues that experts frequently face when searching for information.

@inproceedings{12353,
author       = {Wielemaker, J. and Hildebrand, M. and van Ossenbruggen, J. R.},
editor       = {Polleres, A. and Pearce, D. and Heymans, S. and Ruckhaus, E.},
title        = {Prolog {As} {The} {Fundament} {For} {Applications} {On} {The} {Semantic} {Web}},
booktitle    = {Proceedings of the ICLP2007 Workshop on Applications of Logic Programming to the Web, Semantic Web and Semantic Web Services (ALPSWS2007)},
conferencetitle    = {International Workshop on Applications of Logic Programming to the Web, Semantic Web and Semantic Web Services},
conferencedate     = {2007, September 13},
conferencelocation = {Porto, Portugal},
series       = {CEUR Workshop Proceedings},
pages        = {1 - 16},
year         = {2007},
volume       = {287},
publisher    = {RWTH Aachen},
issn         = {1613-0073},
note         = {Workshop co-located with the International Conference on Logic Programming ICLP 2007},
refereed     = {y},
size         = {16p.},
group        = {INS2},
language     = {en},
project      = {Non-NWO Project 1},
url          = {http://sunsite.informatik.rwth-aachen.de/Publications/CEUR-WS/Vol-287/paper_1.pdf},
}

@inproceedings{12357,
author       = {van Ossenbruggen, J. R. and Amin, A. K. and Hardman, L. and Hildebrand, M. and van Assem, M. and Omelayenko, B. and Tordai, A. and Schreiber, G. and de Boer, V. and Wielinga, B. and Wielemaker, J. and de Niet, M. and Taekema, J. and van Orsouw, M.-C. and Teesing, A.},
title        = {Searching {And} {Annotating} {Virtual} {Heritage} {Collections} {With}  {Semantic-{Web}} {Techniques}},
booktitle    = {Museums and the Web 2007 },
conferencetitle    = {International Conference for Culture and Heritage On-line-Museums and the Web},
conferencedate     = {2007, April 11-14},
conferencelocation = {San Francicsco, CA, USA},
pages        = {1 - 11},
year         = {2007},
publisher    = {Archives $1 Museum Informatics },
refereed     = {y},
size         = {11p.},
keywords     = {Semantic Web, multiple thesauri, semantic search, search paradigms, large virtual collections, scalability},
group        = {INS2},
language     = {en},
project      = {Non-NWO Project 1},
abstract     = {This paper describes ongoing work of a project aimed at exploiting Semantic Web techniques to support searching
 and annotating large cross-institutional digital-heritage collections. The project demonstrator contains multiple collections
 and multiple vocabularies. The architecture is fully based on Web standards. We show novel search and presentation techniques
 which make use of interoperability between the collections and between the vocabularies. 

},
url          = {http://www.archimuse.com/mw2007/papers/ossenbruggen/ossenbruggen.html},
}

This paper describes ongoing work of a project aimed at exploiting Semantic Web techniques to support searching and annotating large cross-institutional digital-heritage collections. The project demonstrator contains multiple collections and multiple vocabularies. The architecture is fully based on Web standards. We show novel search and presentation techniques which make use of interoperability between the collections and between the vocabularies.

@inproceedings{12377,
author       = {Obrenovic, Z. and van Ossenbruggen, J. R.},
title        = {Web {Browser} {Accessibility} {Using} {Open} {Source} {Software}},
booktitle    = {Proceedings of the 2007 international cross disciplinary conference on Web accessibility (W4A)},
conferencetitle    = {International Cross Disciplinary Conference on Web Accessibility },
conferencedate     = {2007, May, 7-8},
conferencelocation = {Banff, Canada},
series       = {ACM International Conference Proceeding Series},
pages        = {15 - 24},
year         = {2007},
volume       = {225  },
publisher    = {ACM},
isbn         = {1-59593-590-X},
refereed     = {y},
size         = {10p.},
group        = {INS2},
language     = {en},
project      = {Non-NWO Project 1},
abstract     = {A Web browser provides a uniform user interface to
different types of information. Making this interface
 universally
accessible and more interactive is a long term goal still far from being
achieved. Universally accessible
 browsers require novel interaction
modalities and additional functionalities, for which existing browsers
tend to provide
 only partial solutions. Although functionality for Web
accessibility can be found as open source and free software components,
their
 reuse and integration is complex because they were developed in
diverse implementation environments, following standards
 and conventions
incompatible with the Web.  To enable the integration of existing partial
solutions within a mainstream
 Web browser environment, we have developed a
middleware infrastructure, AMICO:WEB. This enables browser access to a
wide
 variety of open source and free software components. The main
contribution of AMICO:WEB is in enabling the syntactic interoperability
between
 Web extension mechanisms and a variety of integration mechanisms
used by open source and free software components. It also
 bridges the
semantic differences between the high-level world of Web XML-based APIs
and the low-level APIs of the device-oriented
 world.  We discuss the
design decisions made during the development of AMICO:WEB in the context
of Web accessibility,
 using two typical usage scenarios: one describing a
disabled user using a mainstream Web browser with additional interaction
modalities;
 another describing a non-disabled user browsing in a
suboptimal interaction situation.
},
url          = {http://doi.acm.org/10.1145/1243441.1243451},
}

A Web browser provides a uniform user interface to different types of information. Making this interface universally accessible and more interactive is a long term goal still far from being achieved. Universally accessible browsers require novel interaction modalities and additional functionalities, for which existing browsers tend to provide only partial solutions. Although functionality for Web accessibility can be found as open source and free software components, their reuse and integration is complex because they were developed in diverse implementation environments, following standards and conventions incompatible with the Web. To enable the integration of existing partial solutions within a mainstream Web browser environment, we have developed a middleware infrastructure, AMICO:WEB. This enables browser access to a wide variety of open source and free software components. The main contribution of AMICO:WEB is in enabling the syntactic interoperability between Web extension mechanisms and a variety of integration mechanisms used by open source and free software components. It also bridges the semantic differences between the high-level world of Web XML-based APIs and the low-level APIs of the device-oriented world. We discuss the design decisions made during the development of AMICO:WEB in the context of Web accessibility, using two typical usage scenarios: one describing a disabled user using a mainstream Web browser with additional interaction modalities; another describing a non-disabled user browsing in a suboptimal interaction situation.

@techreport{10806,
author       = {Hardman, L. and van Ossenbruggen, J. R.},
title        = {Creating {Meaningful} {Multimedia} {Presentations}},
type         = {CWI Technical Report},
origin       = {other},
series       = {Information Systems [INS]},
pages        = {1 - 8},
year         = {2006},
number       = {INS-E0602},
publisher    = {CWI},
issn         = {1386-3681},
size         = {8p.},
group        = {INS2},
language     = {en},
project      = {Non-NWO Project 1},
abstract     = {Finding relevant information is one step in the chain of understanding information. Presenting material to
 a user in a suitable way is a further step. Our research focuses on using semantic annotations of multimedia elements to
 increase the },
url          = {http://oai.cwi.nl/oai/asset/10806/10806D.pdf},
}

Finding relevant information is one step in the chain of understanding information. Presenting material to a user in a suitable way is a further step. Our research focuses on using semantic annotations of multimedia elements to increase the

@article{11322,
author       = {Stamou, G. and van Ossenbruggen, J. R. and Pan, J. Z. and Schreiber, G.},
title        = {Multimedia {Annotations} {On} {The} {Semantic} {Web}},
journal      = {IEEE MultiMedia},
pages        = {86 - 90},
year         = {2006},
number       = {1},
volume       = {13},
publisher    = {I.E.E.E. Computer Society Press},
issn         = {1070-986X},
refereed     = {y},
size         = {5p.},
group        = {INS2},
language     = {en},
project      = {Non-NWO Project 1},
abstract     = {Multimedia in all forms (images, video, graphics, music, speech) is exploding on the Web. The content needs
 to be annotated and indexed to enable effective search and retrieval. However, recent standards and best practices for multimedia
 metadata don't provide semantically rich descriptions of multimedia content. On the other hand, the World Wide Web Consortium's
 (W3C's) Semantic Web effort has been making great progress in advancing techniques for annotating semantics of Web resources.
 To bridge this gap, a new W3C task force has been created to investigate multimedia annotations on the Semantic Web. This
 article examines the problems of semantically annotating multimedia and describes the integration of multimedia metadata
 with the Semantic Web. (Editor's note by John R. Smith). },
url          = {http://doi.ieeecomputersociety.org/10.1109/MMUL.2006.15},
}

Multimedia in all forms (images, video, graphics, music, speech) is exploding on the Web. The content needs to be annotated and indexed to enable effective search and retrieval. However, recent standards and best practices for multimedia metadata don't provide semantically rich descriptions of multimedia content. On the other hand, the World Wide Web Consortium's (W3C's) Semantic Web effort has been making great progress in advancing techniques for annotating semantics of Web resources. To bridge this gap, a new W3C task force has been created to investigate multimedia annotations on the Semantic Web. This article examines the problems of semantically annotating multimedia and describes the integration of multimedia metadata with the Semantic Web. (Editor's note by John R. Smith).

@incollection{11409,
author       = {Schreiber, G. and Amin, A. K. and van Assem, M. and de Boer, V. and Hardman, L. and Hildebrand, M. and Hollink, L. and Huang, Z. and van Kersen, J. and de Niet, M. and Omelayenko, B. and van Ossenbruggen, J. R. and Siebes, R. and Taekema, J. and Wielemaker, J. and Wielinga, B.},
title        = {M{ultimediaN} {E-{Culture}} {Demonstrator}},
booktitle    = {Lecture Notes in Computer Science},
series       = {Lecture Notes in Computer Science},
pages        = {951 - 958},
year         = {2006},
month        = {November},
volume       = {4273},
publisher    = {Springer},
issn         = {0302-9743},
size         = {8p.},
group        = {INS2},
language     = {en},
project      = {Non-NWO Project 1},
abstract     = {The main objective of the MultimediaN E-Culture project is to demonstrate how novel semantic-web and presentation
 technologies can be deployed to provide better indexing and search support within large virtual collections of cultural-heritage
 resources. The architecture is fully based on open web standards, in particular XML, SVG, RDF/OWL and SPARQL. One basic
 hypothesis underlying this work is that the use of explicit background knowledge in the form of ontologies/vocabularies/thesauri
 is in particular useful in information retrieval in knowledge-rich domains. },
url          = {http://dx.doi.org/10.1007/11926078_70},
}

The main objective of the MultimediaN E-Culture project is to demonstrate how novel semantic-web and presentation technologies can be deployed to provide better indexing and search support within large virtual collections of cultural-heritage resources. The architecture is fully based on open web standards, in particular XML, SVG, RDF/OWL and SPARQL. One basic hypothesis underlying this work is that the use of explicit background knowledge in the form of ontologies/vocabularies/thesauri is in particular useful in information retrieval in knowledge-rich domains.

@incollection{11421,
author       = {Hildebrand, M. and van Ossenbruggen, J. R. and Hardman, L.},
title        = {/facet: {A} {Browser} {For} {Heterogeneous} {Semantic} {Web} {Repositories}},
booktitle    = {The Semantic Web - ISWC 2006},
pages        = {272 - 285},
year         = {2006},
month        = {November},
publisher    = {Springer-Verlag},
size         = {14p.},
keywords     = {facet browsing, heterogeneous querying, cross relations},
group        = {INS2},
language     = {en},
project      = {Non-NWO Project 1},
abstract     = {Facet browsing has become popular as a user friendly interface to data repositories. The Semantic Web raises
 new challenges due to the heterogeneous character of the data. First, users should be able to select and navigate through
 facets of resources of any type and to make selections based on properties of other, semantically related, types. Second,
 where traditional facet browsers require manual configuration of the software, a semantic web browser should be able to
 handle any RDFS dataset without any additional configuration. Third, hierarchical data on the semantic web is not designed
 for browsing: complementary techniques, such as search, should be available to overcome this problem. We address these requirements
 in our browser, /facet. Additionally, the interface allows the inclusion of facet-specific display options that go beyond
 the hierarchical navigation that characterizes current facet browsing. /facet is a tool for Semantic Web developers as an
 instant interface to their complete dataset. The automatic facet configuration generated by the system can then be further
 refined to configure it as a tool for end users. The implementation is based on current Web standards and open source software.
 The new functionality is motivated using a scenario from the cultural heritage domain. },
url          = {http://oai.cwi.nl/oai/asset/11421/11421A.pdf},
url          = {http://dx.doi.org/10.1007/11926078_20},
}

Facet browsing has become popular as a user friendly interface to data repositories. The Semantic Web raises new challenges due to the heterogeneous character of the data. First, users should be able to select and navigate through facets of resources of any type and to make selections based on properties of other, semantically related, types. Second, where traditional facet browsers require manual configuration of the software, a semantic web browser should be able to handle any RDFS dataset without any additional configuration. Third, hierarchical data on the semantic web is not designed for browsing: complementary techniques, such as search, should be available to overcome this problem. We address these requirements in our browser, /facet. Additionally, the interface allows the inclusion of facet-specific display options that go beyond the hierarchical navigation that characterizes current facet browsing. /facet is a tool for Semantic Web developers as an instant interface to their complete dataset. The automatic facet configuration generated by the system can then be further refined to configure it as a tool for end users. The implementation is based on current Web standards and open source software. The new functionality is motivated using a scenario from the cultural heritage domain.

@media{15585,
author       = {Troncy, R. and van Ossenbruggen, J. R. and Halaschek-Wiener, C. and Stamou, G. and Tzouvaras, V.},
title        = {Multi-{Perspective} {Requirements} {For} {A} {Common} {Multimedia} {Ontology} {Framework}},
year         = {2006},
group        = {INS2},
language     = {en},
}

@techreport{15597,
author       = {Hildebrand, M. and van Ossenbruggen, J. R. and Obrenovic, Z. and Hardman, L. and Troncy, R. and et al},
title        = {Report {Specification} {Of} {Semantics-{Based}} {Interaction} {With} {Multimedia}},
type         = {delivrable},
origin       = {other},
series       = {CWI Deliverables},
year         = {2006},
number       = {CWI Deliverables-D5.3},
publisher    = {CWI},
group        = {INS2},
language     = {en},
}

@inproceedings{16475,
author       = {Hardman, L. and van Ossenbruggen, J. R.},
title        = {Creating {Meaningful} {Multimedia} {Presentations}},
booktitle    = {International Symposium on Circuits and Systems (ISCAS 2006)},
conferencetitle    = {International Symposium on Circuits and Systems},
conferencedate     = {2006, May},
year         = {2006},
month        = {May},
publisher    = {IEEE},
refereed     = {y},
group        = {INS2},
url          = {http://oai.cwi.nl/oai/asset/16475/16475B.pdf},
url          = {http://dx.doi.org/10.1109/ISCAS.2006.1693031},
}

@techreport{10982,
author       = {Rutledge, L. and van Ossenbruggen, J. R. and Hardman, L.},
title        = {Making {R{DF}} {Presentable}: {Integrated} {Global} {And} {Local} {Semantic} {Web} {Browsing}},
type         = {CWI Technical Report},
origin       = {other},
series       = {Information Systems [INS]},
pages        = {5 - 12},
year         = {2005},
number       = {INS-E0505},
publisher    = {CWI},
issn         = {1386-3681},
size         = {8p.},
group        = {INS2},
language     = {en},
abstract     = {This paper discusses generating document structure from annotated media repositories in a domain-independent
 manner. This approaches the vision of a universal RDF browser. We start by applying the search-and-browse paradigm established
 for the WWW to RDF presentation. Furthermore, this paper adds to this paradigm the clustering-based derivation of document
 structure from search returns, providing simple but domain-independent hypermedia generation from RDF stores. While such
 generated presentations hardly meet the standards of those written by humans, they provide quick access to media repositories
 when the required document has not yet been written. The resulting system allows a user to specify a topic for which it
 generates a hypermedia document providing guided navigation through virtually any RDF repository. The impact for content
 providers is that as soon as one adds new media items and their annotations to a repository, they become immediately available
 for automatic integration into subsequently requested presentations},
url          = {http://oai.cwi.nl/oai/asset/10982/10982D.pdf},
}

This paper discusses generating document structure from annotated media repositories in a domain-independent manner. This approaches the vision of a universal RDF browser. We start by applying the search-and-browse paradigm established for the WWW to RDF presentation. Furthermore, this paper adds to this paradigm the clustering-based derivation of document structure from search returns, providing simple but domain-independent hypermedia generation from RDF stores. While such generated presentations hardly meet the standards of those written by humans, they provide quick access to media repositories when the required document has not yet been written. The resulting system allows a user to specify a topic for which it generates a hypermedia document providing guided navigation through virtually any RDF repository. The impact for content providers is that as soon as one adds new media items and their annotations to a repository, they become immediately available for automatic integration into subsequently requested presentations

@article{11313,
author       = {van Ossenbruggen, J. R. and Hardman, L. and Rutledge, L.},
title        = {Combining {R{DF}} {Semantics} {With} {X{ML}} {Document} {Transformations}},
journal      = {International Journal of Web Engineering and Technology},
pages        = {248 - 263},
year         = {2005},
number       = {2/3},
volume       = {2},
note         = {	IJWET Special Issue on SemanticWeb Technologies for Data Integration and Multimedia Presentation. Flavius Frasincar, Geert- Jan Houben and Jacco van Ossenbruggen (guest editors)},
refereed     = {y},
size         = {16p.},
group        = {INS2},
language     = {en},
}

@article{11319,
author       = {Nack, F.-M. and van Ossenbruggen, J. R. and Hardman, L.},
title        = {That {Obscure} {Object} {Of} {Desire}: {Multimedia} {Metadata} {On} {The} {Web} ({Part} {I{I}})},
journal      = {IEEE MultiMedia},
pages        = {54 - 63},
year         = {2005},
number       = {1},
volume       = {12},
publisher    = {I.E.E.E. Computer Society Press},
issn         = {1070-986X},
refereed     = {y},
size         = {10p.},
keywords     = {Semantic Web, metadata production, multimedia production process, XML, XML Schema, RDF, RDF Schema, MPEG-4, MPEG-7, MPEG-21},
group        = {INS2},
language     = {en},
abstract     = {This article discusses the state of the art in metadata for audio-visual media in large semantic networks,
 such as the Semantic Web. Our discussion is predominantly motivated by the two most widely known approaches towards machine-processable
 and semantic-based content description, namely the Semantic Web activity of the W3C and ISO's efforts in the direction of
 complex media content modeling, in particular the Multimedia Content Description Interface (MPEG-7). We explain that the
 conceptual ideas and technologies discussed in both approaches are essential for the next step in multimedia development.
 Unfortunately, there are still many practical obstacles that block their widespread use for providing multimedia metadata
 on the Web. Based on a scenario to explain our vision of a media-aware Semantic Web, we derive in Part I a number of problems
 regarding the semantic content description of media units. We then discuss the multimedia production chain, in particular
 emphasizing the role of progressive metadata production. As a result we distill a set of media-based metadata production
 requirements and show how current media production environments fail to address these. We then introduce those parts of
 the W3C and ISO standardization works that are relevant to our discussion. In Part II of this article, we analyze their
 abilities to define structures for describing media semantics, discuss syntactic and semantic problems, ontological problems
 for media semantics, and the problems of applying the theoretical concepts to real world problems. Part II concludes with
 implications of the findings for future action with respect to the actions the community should take. },
url          = {http://www.computer.org/csdl/mags/mu/2005/01/u1054.pdf},
}

This article discusses the state of the art in metadata for audio-visual media in large semantic networks, such as the Semantic Web. Our discussion is predominantly motivated by the two most widely known approaches towards machine-processable and semantic-based content description, namely the Semantic Web activity of the W3C and ISO's efforts in the direction of complex media content modeling, in particular the Multimedia Content Description Interface (MPEG-7). We explain that the conceptual ideas and technologies discussed in both approaches are essential for the next step in multimedia development. Unfortunately, there are still many practical obstacles that block their widespread use for providing multimedia metadata on the Web. Based on a scenario to explain our vision of a media-aware Semantic Web, we derive in Part I a number of problems regarding the semantic content description of media units. We then discuss the multimedia production chain, in particular emphasizing the role of progressive metadata production. As a result we distill a set of media-based metadata production requirements and show how current media production environments fail to address these. We then introduce those parts of the W3C and ISO standardization works that are relevant to our discussion. In Part II of this article, we analyze their abilities to define structures for describing media semantics, discuss syntactic and semantic problems, ontological problems for media semantics, and the problems of applying the theoretical concepts to real world problems. Part II concludes with implications of the findings for future action with respect to the actions the community should take.

@incollection{11348,
author       = {Rutledge, L. and van Ossenbruggen, J. R. and Hardman, L.},
title        = {Making {R{DF}} {Presentable} - {Integrated} {Global} {And} {Local} {Semantic} {Web} {Browsing}},
pages        = {199 - 206},
year         = {2005},
size         = {8p.},
group        = {INS2},
language     = {en},
abstract     = {This paper discusses generating document structure from annotated media repositories in a domain-independent
 manner. This approaches the vision of a universal RDF browser. We start by applying the search-and-browse paradigm established
 for the WWW to RDF presentation. Furthermore, this paper adds to this paradigm the clustering-based derivation of document
 structure from search returns, providing simple but domain-independent hypermedia generation from RDF stores. While such
 generated presentations hardly meet the standards of those written by humans, they provide quick access to media repositories
 when the needed document has not yet been written. The resulting system allows a user to specify a topic for which it generates
 a hypermedia document providing guided navigation through virtually any RDF repository. The impact for content providers
 is that as soon as new media items and their annotations are added to a repository, they become immediately available for
 automatic integration into subsequently requested presentations. },
url          = {http://www2005.org/cdrom/docs/p199.pdf},
}

This paper discusses generating document structure from annotated media repositories in a domain-independent manner. This approaches the vision of a universal RDF browser. We start by applying the search-and-browse paradigm established for the WWW to RDF presentation. Furthermore, this paper adds to this paradigm the clustering-based derivation of document structure from search returns, providing simple but domain-independent hypermedia generation from RDF stores. While such generated presentations hardly meet the standards of those written by humans, they provide quick access to media repositories when the needed document has not yet been written. The resulting system allows a user to specify a topic for which it generates a hypermedia document providing guided navigation through virtually any RDF repository. The impact for content providers is that as soon as new media items and their annotations are added to a repository, they become immediately available for automatic integration into subsequently requested presentations.

@incollection{11388,
author       = {van Ossenbruggen, J. R. and Stamou, G. and Pan, J. Z.},
title        = {Multimedia {Annotations} {And} {The} {Semantic} {Web}},
booktitle    = {Semantic Web Case Studies and Best Practices for eBusiness},
year         = {2005},
group        = {INS2},
language     = {en},
url          = {http://oai.cwi.nl/oai/asset/11388/11388B.pdf},
}

@incollection{11434,
author       = {van Ossenbruggen, J. R. and Hardman, L.},
title        = {From {Syntactic} {Towards} {Semantic-{Driven}} {Document} {Transformations}},
booktitle    = {Creation, Use and Deployment of Digital Information},
pages        = {55 - 72},
year         = {2005},
publisher    = {Erlbaum},
size         = {18p.},
group        = {INS2},
language     = {en},
}

@inproceedings{16349,
author       = {Rutledge, L. and van Ossenbruggen, J. R. and Hardman, L.},
title        = {Making {R{DF}} {Presentable}. {Integrated} {Global} {And} {Local} {Semantic} {Web} {Browsing}},
booktitle    = {Proceedings of International World Wide Web Conference  2005},
conferencetitle    = {International World Wide Web Conference },
conferencedate     = {2005},
pages        = {199 - 206},
year         = {2005},
publisher    = {W3C},
refereed     = {y},
size         = {8p.},
group        = {INS2},
language     = {en},
}

@inproceedings{16350,
author       = {Schwarz, K. and Kouwenhoven, T. and Dignum, V. and van Ossenbruggen, J. R.},
title        = {Supporting {The} {Decision} {Process} {For} {The} {Choice} {Of} {A} {Domain} {Modeling} {Scheme}},
booktitle    = {Proceedings of Formal Ontologies Meet Industry 2005},
conferencetitle    = {Formal Ontologies Meet Industry},
conferencedate     = {2005},
pages        = {1 - 6},
year         = {2005},
refereed     = {y},
size         = {6p.},
group        = {INS2},
language     = {en},
abstract     = {Enterprises are experiencing the need to model their domain in order to improve the communication and control
 over their intellectual assets. There are several different approaches to modeling a domain, some old-fashioned, some trendy;
 practitioners are at a loss when having to decide which approach best suits their situation. In this research we compare
 different domain modeling schemes to find out which problem each of them is best suited to solve. The modeling schemes we
 consider are taxonomy, thesaurus and ontology. We draw relevant information from evaluating case studies and interviewing
 practitioners in the field of domain modeling. We restrict the scope to those projects that aim at improving the retrieval
 of information. The aim of this research is to support practitioners when they want to model their domain to choose the
 right scheme, considering the trade-offs being made between requirements and effort. },
}

Enterprises are experiencing the need to model their domain in order to improve the communication and control over their intellectual assets. There are several different approaches to modeling a domain, some old-fashioned, some trendy; practitioners are at a loss when having to decide which approach best suits their situation. In this research we compare different domain modeling schemes to find out which problem each of them is best suited to solve. The modeling schemes we consider are taxonomy, thesaurus and ontology. We draw relevant information from evaluating case studies and interviewing practitioners in the field of domain modeling. We restrict the scope to those projects that aim at improving the retrieval of information. The aim of this research is to support practitioners when they want to model their domain to choose the right scheme, considering the trade-offs being made between requirements and effort.

@inproceedings{16362,
author       = {van Ossenbruggen, J. R. and Stamou, G. and Pan, J. Z.},
title        = {Multimedia {Annotations} {And} {The} {Semantic} {Web}. {S{emanticWeb}} {Case} {Studies} {And} {Best} {Practices} {For} {E{Business}}},
booktitle    = {Proceedings of Industrial Track of the International Semantic Web Conference 2005},
conferencetitle    = {Industrial Track of the International Semantic Web Conference},
conferencedate     = {2005},
pages        = {1 - 4},
year         = {2005},
note         = {Workshop in collocation with ISWC},
refereed     = {n},
size         = {4p.},
group        = {INS2},
language     = {en},
}

@software{16363,
author       = {van Ossenbruggen, J. R.},
title        = {Eculture {M{ultimediaN}} {Demonstrator}},
year         = {2005},
note         = {first version},
group        = {INS2},
project      = {Non-NWO Project 1},
}

@inproceedings{16471,
author       = {Geurts, J. P. T. M. and van Ossenbruggen, J. R. and Hardman, L.},
title        = {Requirements {For} {Practical} {Multimedia} {Annotation}},
booktitle    = {Proceedings of Workshop on Multimedia and the Semantic Web 2005},
conferencetitle    = {Workshop on Multimedia and the Semantic Web},
conferencedate     = {2005, November 4},
pages        = {4 - 11},
year         = {2005},
refereed     = {y},
size         = {8p.},
group        = {INS2},
language     = {en},
abstract     = {Applications that use annotated multimedia assets need to be able to process all the annotations about a
 specific media asset. At first sight, this seems almost trivial, but annotations are needed for different levels of description,
 these need to be related to each other in the appropriate way and, in particular on the Semantic Web, annotations may not
 all be stored in the same place. We distinguish between technical descriptions of a media asset from content-level descriptions.
 At both levels, the annotations needed in a single application may come from different vocabularies. In addition, the instantiated
 values for a term used from an ontology also need to be specified. We present a number of existing vocabularies related
 to multimedia, discuss the above problems then discuss requirements for and the desirability of a lightweight multimedia
 ontology. },
url          = {http://oai.cwi.nl/oai/asset/16471/16471B.pdf},
}

Applications that use annotated multimedia assets need to be able to process all the annotations about a specific media asset. At first sight, this seems almost trivial, but annotations are needed for different levels of description, these need to be related to each other in the appropriate way and, in particular on the Semantic Web, annotations may not all be stored in the same place. We distinguish between technical descriptions of a media asset from content-level descriptions. At both levels, the annotations needed in a single application may come from different vocabularies. In addition, the instantiated values for a term used from an ontology also need to be specified. We present a number of existing vocabularies related to multimedia, discuss the above problems then discuss requirements for and the desirability of a lightweight multimedia ontology.

@inproceedings{16474,
author       = {van Ossenbruggen, J. R. and Hardman, L.},
title        = {Semantic {Timeline} {Interfaces} {For} {Annotated} {Multimedia} {Assets}},
booktitle    = {Proceedings of the European Workshop on the Integration of Knowledge, Semantics and Digital Media Technology. (EWIMT , 2005)},
conferencetitle    = {European Workshop on the Integration of Knowledge, Semantics and Digital Media Technology.},
conferencedate     = {2005},
year         = {2005},
refereed     = {y},
group        = {INS2},
language     = {en},
url          = {http://oai.cwi.nl/oai/asset/16474/16474B.pdf},
}

@inproceedings{16487,
author       = {Rutledge, L. and van Ossenbruggen, J. R.},
title        = {Cruising {The} {Semantic} {Web} {With} {Noadster} (poster)},
booktitle    = {Proceedings of ACM Conference on Hypertext and Hypermedia  2005},
conferencetitle    = {ACM Conference on Hypertext and Hypermedia },
conferencedate     = {2005},
pages        = {290 - 291},
year         = {2005},
publisher    = {ACM},
refereed     = {y},
size         = {2p.},
group        = {INS2},
language     = {en},
url          = {http://oai.cwi.nl/oai/asset/16487/16487B.pdf},
}

@media{16501,
author       = {Rutledge, L. and van Ossenbruggen, J. R.},
title        = {Cruising {The} {Semantic} {Web} {With} {Noadster}},
year         = {2005},
note         = {Slides broadcast at the ACM Hypoertext Conference},
group        = {INS2},
language     = {en},
url          = {http://oai.cwi.nl/oai/asset/16501/16501B.ppt},
}

@inproceedings{16502,
author       = {Rutledge, L. and van Ossenbruggen, J. R.},
title        = {Cruising {The} {Semantic} {Web} {With} {Noadster} (poster {Description} {In} {Conference} {Proceedings})},
booktitle    = {Proceedings of ACM Conference on Hypertext and Hypermedia  2005},
conferencetitle    = {ACM Conference on Hypertext and Hypermedia },
conferencedate     = {2005},
pages        = {290 - 291},
year         = {2005},
publisher    = {ACM},
refereed     = {y},
size         = {2p.},
group        = {INS2},
language     = {en},
}

@techreport{4028,
author       = {Geurts, J. P. T. M. and van Ossenbruggen, J. R.},
title        = {Video {On} {The} {Semantic} {Web}: {Experiences} {With} {Media} {Streams}},
type         = {CWI Technical Report},
origin       = {other},
series       = {Information Systems [INS]},
pages        = {1 - 18},
year         = {2004},
number       = {INS-E0404},
publisher    = {CWI},
issn         = {1386-3681},
size         = {18p.},
class        = {H.5.1;H.3.3},
group        = {INS2},
language     = {en},
abstract     = {In this paper, we report our experiences with the use of SemanticWeb technology for annotating digital video
 material.Web technology is used to transform a large, existing video ontology embedded in an annotation tool into a commonly
 accessible format. The recombination of existing video material is then used as an example application, in which the video
 metadata enables the retrieval of video footage based on both content descriptions and cinematographic concepts, such as
 establishing and reaction shots. The paper focuses on the practical issues of porting ontological information to the Semantic
 Web, the multimedia-specific issues of video annotation, and requirements for Semantic Web query and access patterns. It
 thereby explicitly aims at providing input to the two new W3C Semantic Web Working Groups (Best Practices and Deployment;
 Data Access).},
url          = {http://oai.cwi.nl/oai/asset/4028/04028D.pdf},
}

In this paper, we report our experiences with the use of SemanticWeb technology for annotating digital video material.Web technology is used to transform a large, existing video ontology embedded in an annotation tool into a commonly accessible format. The recombination of existing video material is then used as an example application, in which the video metadata enables the retrieval of video footage based on both content descriptions and cinematographic concepts, such as establishing and reaction shots. The paper focuses on the practical issues of porting ontological information to the Semantic Web, the multimedia-specific issues of video annotation, and requirements for Semantic Web query and access patterns. It thereby explicitly aims at providing input to the two new W3C Semantic Web Working Groups (Best Practices and Deployment; Data Access).

@techreport{4030,
author       = {Rutledge, L. and van Ossenbruggen, J. R. and Hardman, L.},
title        = {Structuring {And} {Presenting} {Annotated} {Media} {Repositories}},
type         = {CWI Technical Report},
origin       = {other},
series       = {Information Systems [INS]},
pages        = {1 - 12},
year         = {2004},
number       = {INS-E0402},
publisher    = {CWI},
issn         = {1386-3681},
size         = {12p.},
group        = {INS2},
language     = {en},
abstract     = {The Semantic Web envisions a Web that is both human readable and machine processible. In practice, however,
 there is still a large conceptual gap between annotated content repositories on the one hand, and coherent, human readable
 Web pages on the other. To bridge this conceptual gap, one needs to select the appropriate content from the repository,
 structure and order the material, and design a Web page that effectively conveys the selected content and the chosen structure.
 In addition to this conceptual gap, there is also a technological gap. On one side of this gap, we find the semantic-oriented
 technology deployed to build annotated content repositories. This includes RDF, RDF Schema and OWL. On the other side of
 the gap is the syntax-oriented technology deployed to build Websites. This includes XML, XSLT, CSS, XHTML and SMIL. In this
 paper, we discuss the conceptual relationships between the world of explicit metadata semantics and the world of Web presentations
 and their underlying syntactic formats. We also explore to what extent this gap can be bridged automatically, and how current
 Web technologies can be used to support this process.},
url          = {http://oai.cwi.nl/oai/asset/4030/04030D.pdf},
}

The Semantic Web envisions a Web that is both human readable and machine processible. In practice, however, there is still a large conceptual gap between annotated content repositories on the one hand, and coherent, human readable Web pages on the other. To bridge this conceptual gap, one needs to select the appropriate content from the repository, structure and order the material, and design a Web page that effectively conveys the selected content and the chosen structure. In addition to this conceptual gap, there is also a technological gap. On one side of this gap, we find the semantic-oriented technology deployed to build annotated content repositories. This includes RDF, RDF Schema and OWL. On the other side of the gap is the syntax-oriented technology deployed to build Websites. This includes XML, XSLT, CSS, XHTML and SMIL. In this paper, we discuss the conceptual relationships between the world of explicit metadata semantics and the world of Web presentations and their underlying syntactic formats. We also explore to what extent this gap can be bridged automatically, and how current Web technologies can be used to support this process.

@article{11333,
author       = {van Ossenbruggen, J. R. and Nack, F.-M. and Hardman, L.},
title        = {That {Obscure} {Object} {Of} {Desire}: {Multimedia} {Metadata} {On} {The} {Web} ({Part} {I})},
journal      = {IEEE MultiMedia},
pages        = {38 - 48},
year         = {2004},
number       = {4},
volume       = {11},
publisher    = {I.E.E.E. Computer Society Press},
issn         = {1070-986X},
refereed     = {y},
size         = {11p.},
keywords     = {Semantic Web, metadata production, multimedia production process, XML, XML Schema, RDF, RDF Schema, MPEG-4, MPEG-7, MPEG-21},
group        = {INS2},
language     = {en},
url          = {http://www.computer.org/csdl/mags/mu/2004/04/u4038.pdf},
}

@incollection{11383,
author       = {Geurts, J. P. T. M. and van Ossenbruggen, J. R. and Hardman, L.},
title        = {Discourse {Knowledge} {In} {Device} {Independent} {Document} {Formatting}},
year         = {2004},
note         = {bibliographical data to be processed -- Proceedings of W3C Workshop on Metadata for Content Adaptation, 2004 --  -- },
group        = {INS2},
language     = {en},
abstract     = {Most document structures define layout structures which implicitly define semantic relationships between
 content elements. While document structures for text are well established (books, reports, papers etc.), models for time
 based documents such as multimedia and hypermedia are relatively new and lack established document structures. Traditional
 document description languages convey domain-dependent semantic relationships implicitly, using domain-independent mark-up
 for expressing layout. This works well for textual documents a,s for example, CSS and HTML demonstrate. True device independence,
 however, sometimes requires a change of document model to maintain the content semantics. To achieve this we need explicit
 information about the discourse role of the content element. We propose a model in which content is marked-up with the discourse
 role it plays in the document. This way the formatter has knowledge about the function of a content element so it can make
 appropriate lay out choices. },
url          = {http://oai.cwi.nl/oai/asset/11383/11383B.pdf},
}

Most document structures define layout structures which implicitly define semantic relationships between content elements. While document structures for text are well established (books, reports, papers etc.), models for time based documents such as multimedia and hypermedia are relatively new and lack established document structures. Traditional document description languages convey domain-dependent semantic relationships implicitly, using domain-independent mark-up for expressing layout. This works well for textual documents a,s for example, CSS and HTML demonstrate. True device independence, however, sometimes requires a change of document model to maintain the content semantics. To achieve this we need explicit information about the discourse role of the content element. We propose a model in which content is marked-up with the discourse role it plays in the document. This way the formatter has knowledge about the function of a content element so it can make appropriate lay out choices.

@inproceedings{11424,
author       = {Falkovych, K. and Nack, F.-M. and van Ossenbruggen, J. R. and Rutledge, L.},
title        = {S{ampLe}: {Towards} {A} {Framework} {For} {System-{Supported}} {Multimedia} {Authoring}},
booktitle    = {Proceedings of the tenth International Multimedia Modelling Conference 2004},
conferencetitle    = {International Multimedia Modelling Conference},
conferencedate     = {2004},
year         = {2004},
refereed     = {y},
group        = {INS2},
language     = {en},
url          = {http://csdl.computer.org/comp/proceedings/mmm/2004/2084/00/20840362.pdf},
}

@techreport{4084,
author       = {Nack, F.-M. and van Ossenbruggen, J. R. and Hardman, L.},
title        = {That {Obscure} {Object} {Of} {Desire}: {Multimedia} {Metadata} {On} {The} {Web}, {Part} 1},
type         = {CWI Technical Report},
origin       = {other},
series       = {Information Systems [INS]},
pages        = {1 - 15},
year         = {2003},
number       = {INS-E0308},
publisher    = {CWI},
issn         = {1386-3681},
size         = {15p.},
class        = {H.3.1;H.3.7;H.5.1;H.5.4;I.7.2},
group        = {INS2},
language     = {en},
abstract     = {This article discusses the state of the art in metadata for audio-visual media in large semantic networks,
 such as the Semantic Web. Our discussion is predominantly motivated by the two most widely known approaches towards machine-processable
 and semantic-based content description, namely the Semantic Web activity of the W3C and ISO's efforts in the direction of
 complex media content modeling, in particular the Multimedia Content Description Interface (MPEG-7). We explain that the
 conceptual ideas and technologies discussed in both approaches are essential for the next step in multimedia development.
 Unfortunately, there are still many practical obstacles that block their widespread use for providing multimedia metadata
 on the Web. Based on a scenario to explain our vision of a media-aware Semantic Web, we derive in Part I a number of problems
 regarding the semantic content description of media units. We then discuss the multimedia production chain, in particular
 emphasizing the role of progressive metadata production. As a result we distill a set of media-based metadata production
 requirements and show how current media production environments fail to address these. We then introduce those parts of
 the W3C and ISO standardization works that are relevant to our discussion. In Part II of this article, we analyze their
 abilities to define structures for describing media semantics, discuss syntactic and semantic problems, ontological problems
 for media semantics, and the problems of applying the theoretical concepts to real world problems. Part II concludes with
 implications of the findings for future action with respect to the actions the community should take.},
url          = {http://oai.cwi.nl/oai/asset/4084/04084D.pdf},
}

This article discusses the state of the art in metadata for audio-visual media in large semantic networks, such as the Semantic Web. Our discussion is predominantly motivated by the two most widely known approaches towards machine-processable and semantic-based content description, namely the Semantic Web activity of the W3C and ISO's efforts in the direction of complex media content modeling, in particular the Multimedia Content Description Interface (MPEG-7). We explain that the conceptual ideas and technologies discussed in both approaches are essential for the next step in multimedia development. Unfortunately, there are still many practical obstacles that block their widespread use for providing multimedia metadata on the Web. Based on a scenario to explain our vision of a media-aware Semantic Web, we derive in Part I a number of problems regarding the semantic content description of media units. We then discuss the multimedia production chain, in particular emphasizing the role of progressive metadata production. As a result we distill a set of media-based metadata production requirements and show how current media production environments fail to address these. We then introduce those parts of the W3C and ISO standardization works that are relevant to our discussion. In Part II of this article, we analyze their abilities to define structures for describing media semantics, discuss syntactic and semantic problems, ontological problems for media semantics, and the problems of applying the theoretical concepts to real world problems. Part II concludes with implications of the findings for future action with respect to the actions the community should take.

@techreport{4085,
author       = {Falkovych, K. and Nack, F.-M. and van Ossenbruggen, J. R. and Rutledge, L.},
title        = {Semantics {In} {Multi-}{Facet} {Hypermedia} {Authoring}},
type         = {CWI Technical Report},
origin       = {other},
series       = {Information Systems [INS]},
pages        = {1 - 7},
year         = {2003},
number       = {INS-E0307},
publisher    = {CWI},
issn         = {1386-3681},
size         = {7p.},
class        = {H.5.4;H.5.1},
group        = {INS2},
language     = {en},
abstract     = {The presentation generation area of hypermedia authoring contains different approaches to address the challenge
 of the presentation creation process. This paper presents the approach in which the author creates a presentation following
 the five stages process. These five stages reflect various facets in hypermedia authoring.},
url          = {http://oai.cwi.nl/oai/asset/4085/04085D.pdf},
}

The presentation generation area of hypermedia authoring contains different approaches to address the challenge of the presentation creation process. This paper presents the approach in which the author creates a presentation following the five stages process. These five stages reflect various facets in hypermedia authoring.

@techreport{4089,
author       = {van Ossenbruggen, J. R. and Hardman, L. and Rutledge, L.},
title        = {Towards {Smart} {Style}: {Combining} {R{DF}} {Semantics} {With} {X{ML}} {Document} {Transformations}},
type         = {CWI Technical Report},
origin       = {other},
series       = {Information Systems [INS]},
pages        = {1 - 16},
year         = {2003},
number       = {INS-E0303},
publisher    = {CWI},
issn         = {1386-3681},
size         = {16p.},
class        = {H.5.4},
group        = {INS2},
language     = {en},
abstract     = {The 'Document Web' has established itself through the creation of an impressive family of XML and related
 languages. In addition to this, the 'Semantic Web' is developing its own family of languages based primarily on RDF. Although
 these families were both developed specifically for 'the Web', each language family has been developed from different premises
 with specific goals in mind. The result is that combining both families in a single application is surprisingly difficult.
 This is unfortunate, since the combination of semantic processing with document processing provides advantages in both directions
 --- namely using semantic inferencing for more intelligent document processing and using document processing tools for presenting
 semantic representations to an end-user. In this paper, we investigate this integration problem, focusing on the role of
 (RDF) semantics in selecting, structuring and styling (XML) content. We analyze the approaches taken by two example architectures
 and use our analysis to derive a more integrated alternative.},
url          = {http://oai.cwi.nl/oai/asset/4089/04089D.pdf},
}

The 'Document Web' has established itself through the creation of an impressive family of XML and related languages. In addition to this, the 'Semantic Web' is developing its own family of languages based primarily on RDF. Although these families were both developed specifically for 'the Web', each language family has been developed from different premises with specific goals in mind. The result is that combining both families in a single application is surprisingly difficult. This is unfortunate, since the combination of semantic processing with document processing provides advantages in both directions — namely using semantic inferencing for more intelligent document processing and using document processing tools for presenting semantic representations to an end-user. In this paper, we investigate this integration problem, focusing on the role of (RDF) semantics in selecting, structuring and styling (XML) content. We analyze the approaches taken by two example architectures and use our analysis to derive a more integrated alternative.

@techreport{4127,
author       = {Falkovych, K. and Nack, F.-M. and van Ossenbruggen, J. R. and Rutledge, L.},
title        = {S{ampLe}: {Towards} {A} {Framework} {For} {System-{Supported}} {Multimedia} {Authoring}},
type         = {CWI Technical Report},
origin       = {other},
series       = {Information Systems [INS]},
pages        = {1 - 11},
year         = {2003},
number       = {INS-E0302},
publisher    = {CWI},
issn         = {1386-3681},
size         = {11p.},
group        = {INS2},
language     = {en},
abstract     = {Much current research on hypermedia generation accepts user input only at the start of an otherwise fully-automated
 process. However, since multimedia presentation creation is often a complex and creative process, it has multiple phases
 which would each benefit from human intervention. This paper presents a hypermedia generation model that lets the user influence
 all phases of this computer-assisted human-guided process. The main focus is on providing extra support for helping the
 user find relevant media items and combine them meaningfully into a rich and coherent multimedia presentation. Like fully-automated
 systems, our approach uses explicit knowledge about the presentation's topic domain, narrative structures, hypermedia presentation
 and distinctions between media modalities. This paper presents a motivating scenario that is used to derive a number of
 system requirements and to discuss the pros and cons of the presented approach.},
url          = {http://oai.cwi.nl/oai/asset/4127/04127D.pdf},
}

Much current research on hypermedia generation accepts user input only at the start of an otherwise fully-automated process. However, since multimedia presentation creation is often a complex and creative process, it has multiple phases which would each benefit from human intervention. This paper presents a hypermedia generation model that lets the user influence all phases of this computer-assisted human-guided process. The main focus is on providing extra support for helping the user find relevant media items and combine them meaningfully into a rich and coherent multimedia presentation. Like fully-automated systems, our approach uses explicit knowledge about the presentation's topic domain, narrative structures, hypermedia presentation and distinctions between media modalities. This paper presents a motivating scenario that is used to derive a number of system requirements and to discuss the pros and cons of the presented approach.

@techreport{4128,
author       = {van Ossenbruggen, J. R. and Hardman, L. and Geurts, J. P. T. M. and Rutledge, L.},
title        = {Towards {A} {Multimedia} {Formatting} {Vocabulary}},
type         = {CWI Technical Report},
origin       = {other},
series       = {Information Systems [INS]},
pages        = {1 - 12},
year         = {2003},
number       = {INS-E0301},
publisher    = {CWI},
issn         = {1386-3681},
size         = {12p.},
class        = {H.5.1;I.7.2;H.5.4},
group        = {INS2},
language     = {en},
abstract     = {Time-based, media-centric Web presentations can be described declaratively in the XML world through the development
 of languages such as SMIL. It is difficult, however, to fully integrate them in a complete document transformation processing
 chain. In order to achieve the desired processing of data-driven, time-based, media-centric presentations, the text-flow
 based formatting vocabularies used by style languages such as XSL, CSS and DSSSL need to be extended. The paper presents
 a selection of use cases which are used to derive a list of requirements for a multimedia style and transformation formatting
 vocabulary. The boundaries of applicability of existing text-based formatting models for media-centric transformations are
 analyzed. The paper then discusses the advantages and disadvantages of a fully-fledged time-based multimedia formatting
 model. Finally, the discussion is illustrated by describing the key properties of the example multimedia formatting vocabulary
 currently implemented in the back-end of our Cuypers multimedia transformation engine.},
url          = {http://oai.cwi.nl/oai/asset/4128/04128D.pdf},
}

Time-based, media-centric Web presentations can be described declaratively in the XML world through the development of languages such as SMIL. It is difficult, however, to fully integrate them in a complete document transformation processing chain. In order to achieve the desired processing of data-driven, time-based, media-centric presentations, the text-flow based formatting vocabularies used by style languages such as XSL, CSS and DSSSL need to be extended. The paper presents a selection of use cases which are used to derive a list of requirements for a multimedia style and transformation formatting vocabulary. The boundaries of applicability of existing text-based formatting models for media-centric transformations are analyzed. The paper then discusses the advantages and disadvantages of a fully-fledged time-based multimedia formatting model. Finally, the discussion is illustrated by describing the key properties of the example multimedia formatting vocabulary currently implemented in the back-end of our Cuypers multimedia transformation engine.

@techreport{4156,
author       = {Geurts, J. P. T. M. and Bocconi, S. and van Ossenbruggen, J. R. and Hardman, L.},
title        = {Towards {Ontology-{Driven}} {Discourse}: {From} {Semantic} {Graphs} {To} {Multimedia} {Presentations}},
type         = {CWI Technical Report},
origin       = {other},
series       = {Information Systems [INS]},
pages        = {1 - 14},
year         = {2003},
number       = {INS-R-0305},
publisher    = {CWI},
issn         = {1386-3681},
size         = {14p.},
class        = {H.5.4;H.5.1;I.7.2},
group        = {INS2},
language     = {en},
abstract     = {Traditionally, research in applying Semantic Web technology to multimedia information systems has focused
 on using annotations and ontologies to improve the retrieval process. This paper concentrates on improving the presentation
 of the retrieval results. First, our approach uses ontological domain knowledge to select and organize the content relevant
 to the topic the user is interested in. Domain ontologies are valuable in the presentation generation process, because effective
 presentations are those that succeed in conveying the relevant domain semantics to the user. Explicit discourse and narrative
 knowledge allows selection of appropriate presentation genres and creation of narrative structures, which are used for conveying
 these domain relations. In addition, knowledge of graphic design and media characteristics is essential to transform abstract
 presentation structures in real multimedia presentations. Design knowledge determines how the semantics and presentation
 structure are expressed in the multimedia presentation. In traditional Web environments, this type of design knowledge remains
 implicit, hidden in style sheets and other document transformation code. Our second use of Semantic Web technology is to
 model design knowledge explicitly, and to let it drive the transformations needed to turn annotated media items into structured
 presentations.},
url          = {http://oai.cwi.nl/oai/asset/4156/04156D.pdf},
}

Traditionally, research in applying Semantic Web technology to multimedia information systems has focused on using annotations and ontologies to improve the retrieval process. This paper concentrates on improving the presentation of the retrieval results. First, our approach uses ontological domain knowledge to select and organize the content relevant to the topic the user is interested in. Domain ontologies are valuable in the presentation generation process, because effective presentations are those that succeed in conveying the relevant domain semantics to the user. Explicit discourse and narrative knowledge allows selection of appropriate presentation genres and creation of narrative structures, which are used for conveying these domain relations. In addition, knowledge of graphic design and media characteristics is essential to transform abstract presentation structures in real multimedia presentations. Design knowledge determines how the semantics and presentation structure are expressed in the multimedia presentation. In traditional Web environments, this type of design knowledge remains implicit, hidden in style sheets and other document transformation code. Our second use of Semantic Web technology is to model design knowledge explicitly, and to let it drive the transformations needed to turn annotated media items into structured presentations.

@inproceedings{11346,
author       = {Geurts, J. P. T. M. and Bocconi, S. and van Ossenbruggen, J. R. and Hardman, L.},
title        = {Towards {Ontology-{Driven}} {Discourse}: {From} {Semantic} {Graphs} {To} {Multimedia} {Presentations}},
booktitle    = { Second International Semantic Web Conference (ISWC2003) },
conferencetitle    = {International Semantic Web Conference },
conferencedate     = {2011},
pages        = {597 - 612},
year         = {2003},
month        = {October},
publisher    = {Springer-Verlag},
refereed     = {y},
size         = {16p.},
group        = {INS2},
language     = {en},
abstract     = {Traditionally, research in applying Semantic Web technology to multimedia information systems has focused
 on using annotations and ontologies to improve the retrieval process. This paper concentrates on improving the presentation
 of the retrieval results. First, our approach uses ontological domain knowledge to select and organize the content relevant
 to the topic the user is interested in. Domain ontologies are valuable in the presentation generation process, because effective
 presentations are those that succeed in conveying the relevant domain semantics to the user. Explicit discourse and narrative
 knowledge allows selection of appropriate presentation genres and creation of narrative structures, which are used for conveying
 these domain relations. In addition, knowledge of graphic design and media characteristics is essential to transform abstract
 presentation structures into real multimedia presentations. Design knowledge determines how the semantics and presentation
 structure are expressed in the multimedia presentation. In traditional Web environments, this type of design knowledge remains
 implicit, hidden in style sheets and other document transformation code. Our second use of Semantic Web technology is to
 model design knowledge explicitly, and to enable it to drive the transformations needed to turn annotated media items into
 structured presentations },
url          = {http://oai.cwi.nl/oai/asset/11346/11346B.pdf},
}

Traditionally, research in applying Semantic Web technology to multimedia information systems has focused on using annotations and ontologies to improve the retrieval process. This paper concentrates on improving the presentation of the retrieval results. First, our approach uses ontological domain knowledge to select and organize the content relevant to the topic the user is interested in. Domain ontologies are valuable in the presentation generation process, because effective presentations are those that succeed in conveying the relevant domain semantics to the user. Explicit discourse and narrative knowledge allows selection of appropriate presentation genres and creation of narrative structures, which are used for conveying these domain relations. In addition, knowledge of graphic design and media characteristics is essential to transform abstract presentation structures into real multimedia presentations. Design knowledge determines how the semantics and presentation structure are expressed in the multimedia presentation. In traditional Web environments, this type of design knowledge remains implicit, hidden in style sheets and other document transformation code. Our second use of Semantic Web technology is to model design knowledge explicitly, and to enable it to drive the transformations needed to turn annotated media items into structured presentations

@incollection{11349,
author       = {van Ossenbruggen, J. R. and Geurts, J. P. T. M. and Hardman, L. and Rutledge, L.},
title        = {Towards {A} {Multimedia} {Formatting} {Vocabulary}},
booktitle    = {The Twelfth International World Wide Web Conference (WWW2003)},
pages        = {384 - 393},
year         = {2003},
month        = {May},
publisher    = {ACM Press},
note         = {bibliographical data to be processed -- pages 384-393 --  -- 9},
size         = {10p.},
group        = {INS2},
language     = {en},
abstract     = {Time-based, media-centric Web presentations can be described declaratively in the XML world through the development
 of languages such as SMIL. It is difficult, however, to fully integrate them in a complete document transformation processing
 chain. In order to achieve the desired processing of data-driven, time-based, media-centric presentations, the text-flow
 based formatting vocabularies used by style languages such as XSL, CSS and DSSSL need to be extended. The paper presents
 a selection of use cases which are used to derive a list of requirements for a multimedia style and transformation formatting
 vocabulary. The boundaries of applicability of existing text-based formatting models for media-centric transformations are
 analyzed. The paper then discusses the advantages and disadvantages of a fully-fledged time-based multimedia formatting
 model. Finally, the discussion is illustrated by describing the key properties of the example multimedia formatting vocabulary
 currently implemented in the back-end of our Cuypers multimedia transformation engine. },
url          = {http://oai.cwi.nl/oai/asset/11349/11349C.pdf},
url          = {http://www2003.org/cdrom/papers/refereed/p383/p383-ossenbruggen.html},
}

Time-based, media-centric Web presentations can be described declaratively in the XML world through the development of languages such as SMIL. It is difficult, however, to fully integrate them in a complete document transformation processing chain. In order to achieve the desired processing of data-driven, time-based, media-centric presentations, the text-flow based formatting vocabularies used by style languages such as XSL, CSS and DSSSL need to be extended. The paper presents a selection of use cases which are used to derive a list of requirements for a multimedia style and transformation formatting vocabulary. The boundaries of applicability of existing text-based formatting models for media-centric transformations are analyzed. The paper then discusses the advantages and disadvantages of a fully-fledged time-based multimedia formatting model. Finally, the discussion is illustrated by describing the key properties of the example multimedia formatting vocabulary currently implemented in the back-end of our Cuypers multimedia transformation engine.

@techreport{21735,
author       = {Nack, F.-M. and van Ossenbruggen, J. R. and Hardman, L.},
title        = {That {Obscure} {Object} {Of} {Desire}: {Multimedia} {Metadata} {On} {The} {Web}, {Part} 2},
type         = {CWI Technical Report},
origin       = {other},
series       = {Information Systems [INS]},
pages        = { - },
year         = {2003},
number       = {INS-E0309},
publisher    = {CWI},
issn         = {1386-3681},
size         = {1p.},
class        = {H.3.1;H.3.7;H.5.1;H.5.4;I.7.2},
group        = {INS2},
language     = {en},
abstract     = {This article discusses the state of the art in metadata for audio-visual media in large semantic networks,
 such as the Semantic Web. Our discussion is predominantly motivated by the two most widely known approaches towards machine-processable
 and semantic-based content description, namely the Semantic Web activity of the W3C and ISO's efforts in the direction of
 complex media content modeling, in particular the Multimedia Content Description Interface (MPEG-7). We explain that the
 conceptual ideas and technologies discussed in both approaches are essential for the next step in multimedia development.
 Unfortunately, there are still many practical obstacles that block their widespread use for providing multimedia metadata
 on the Web. Based on a scenario to explain our vision of a media-aware Semantic Web, we derive in Part I a number of problems
 regarding the semantic content description of media units. We then discuss the multimedia production chain, in particular
 emphasizing the role of progressive metadata production. As a result we distill a set of media-based metadata production
 requirements and show how current media production environments fail to address these. We then introduce those parts of
 the W3C and ISO standardization works that are relevant to our discussion. In Part II of this article, we analyze their
 abilities to define structures for describing media semantics, discuss syntactic and semantic problems, ontological problems
 for media semantics, and the problems of applying the theoretical concepts to real world problems. Part II concludes with
 implications of the findings for future action with respect to the actions the community should take.},
url          = {http://oai.cwi.nl/oai/asset/21735/21735D.pdf},
}

This article discusses the state of the art in metadata for audio-visual media in large semantic networks, such as the Semantic Web. Our discussion is predominantly motivated by the two most widely known approaches towards machine-processable and semantic-based content description, namely the Semantic Web activity of the W3C and ISO's efforts in the direction of complex media content modeling, in particular the Multimedia Content Description Interface (MPEG-7). We explain that the conceptual ideas and technologies discussed in both approaches are essential for the next step in multimedia development. Unfortunately, there are still many practical obstacles that block their widespread use for providing multimedia metadata on the Web. Based on a scenario to explain our vision of a media-aware Semantic Web, we derive in Part I a number of problems regarding the semantic content description of media units. We then discuss the multimedia production chain, in particular emphasizing the role of progressive metadata production. As a result we distill a set of media-based metadata production requirements and show how current media production environments fail to address these. We then introduce those parts of the W3C and ISO standardization works that are relevant to our discussion. In Part II of this article, we analyze their abilities to define structures for describing media semantics, discuss syntactic and semantic problems, ontological problems for media semantics, and the problems of applying the theoretical concepts to real world problems. Part II concludes with implications of the findings for future action with respect to the actions the community should take.

@techreport{21736,
author       = {Nack, F.-M. and van Ossenbruggen, J. R. and Hardman, L.},
title        = {That {Obscure} {Object} {Of} {Desire}: {Multimedia} {Metadata} {On} {The} {Web}},
type         = {CWI Technical Report},
origin       = {other},
series       = {preprint (not CWI, to be used with submitted papers)},
pages        = { - },
year         = {2003},
number       = {preprint (not CWI, to be used with submitted papers)-},
note         = {Submission of a paper published in two articles in IEEE MultiMedia 11(2004)4, pp. 38-48, and IEEE MultiMedia (12(2005)1, pp. 54-63},
size         = {1p.},
group        = {INS2},
language     = {en},
url          = {http://oai.cwi.nl/oai/asset/21736/21736B.pdf},
}

@techreport{4264,
author       = {van Ossenbruggen, J. R. and Hardman, L.},
title        = {Smart {Style} {On} {The} {Semantic} {Web}},
type         = {CWI Technical Report},
origin       = {other},
series       = {Information Systems [INS]},
pages        = {1 - 16},
year         = {2002},
number       = {INS-R 0201},
publisher    = {CWI},
issn         = {1386-3681},
size         = {16p.},
class        = {H.5.4;H.5.1;I.2.4},
group        = {INS2},
language     = {en},
abstract     = {Web publishing systems have to take into account a plethora of Web-enableddevices, user preferences and abilities.
 Technologies generating thesepresentations will need to be explicitly aware of the context in which theinformation is being
 presented. Semantic Web technology can be a fundamentalpart of the solution to this problem by explicitly modeling the knowledge
 needed to adapt presentations to a specific delivery context. We propose the development of a $1lt;em$1gt;Smart Style$1lt;/em$1gt;
 layer which is able to process metadata that describes content and use this metadata to improve the presentation of thecontent
 to human users. In the paper, we derive the requirements of such aSmart Style layer by considering Web design from both
 the document engineeringand graphic design perspectives. In addition, design trade-offs made by humandesigners have to be
 taken into account for the automated process.After stating the requirements for a Smart Style layer, we discuss to whatextent
 the currently available Web technology can be used and what itslimitations are.  The limitations are illustrated with examples
 of potentialfuture extensions.},
url          = {http://oai.cwi.nl/oai/asset/4264/04264D.pdf},
}

Web publishing systems have to take into account a plethora of Web-enableddevices, user preferences and abilities. Technologies generating thesepresentations will need to be explicitly aware of the context in which theinformation is being presented. Semantic Web technology can be a fundamentalpart of the solution to this problem by explicitly modeling the knowledge needed to adapt presentations to a specific delivery context. We propose the development of a $1lt;em$1gt;Smart Style$1lt;/em$1gt; layer which is able to process metadata that describes content and use this metadata to improve the presentation of thecontent to human users. In the paper, we derive the requirements of such aSmart Style layer by considering Web design from both the document engineeringand graphic design perspectives. In addition, design trade-offs made by humandesigners have to be taken into account for the automated process.After stating the requirements for a Smart Style layer, we discuss to whatextent the currently available Web technology can be used and what itslimitations are. The limitations are illustrated with examples of potentialfuture extensions.

@article{11300,
author       = {van Ossenbruggen, J. R. and Hardman, L.},
title        = {Hypermedia {Presentation} {Generation} {On} {The} {Semantic} {Web}},
journal      = {ERCIM News},
pages        = {36 - 36},
year         = {2002},
volume       = {51},
publisher    = {ERCIM},
issn         = {0926-4981},
refereed     = {n},
size         = {1p.},
group        = {INS2},
language     = {en},
abstract     = {The research goal of the Multimedia and Human-Computer Interaction group at CWI is to investigate the automated
 generation of Web-based hypermedia presentations tailored to the abilities, preferences and platform of the user. This requires
 the description and processing of different types of information in order to assemble semantically annotated media items
 into a coherent presentation, i.e. a presentation that communicates the intended semantic relations to the user. },
url          = {http://oai.cwi.nl/oai/asset/11300/11300D.pdf},
}

The research goal of the Multimedia and Human-Computer Interaction group at CWI is to investigate the automated generation of Web-based hypermedia presentations tailored to the abilities, preferences and platform of the user. This requires the description and processing of different types of information in order to assemble semantically annotated media items into a coherent presentation, i.e. a presentation that communicates the intended semantic relations to the user.

@article{11312,
author       = {van Ossenbruggen, J. R. and Hardman, L. and Rutledge, L.},
title        = {Hypermedia {And} {The} {Semantic} {Web}: {A} {Research} {Agenda}},
journal      = {Journal of Digital Information},
year         = {2002},
number       = {1},
volume       = {3},
refereed     = {y},
group        = {INS2},
language     = {en},
abstract     = {Until recently, the Semantic Web was little more than a name for the next generation Web infrastructure as
 envisioned by its inventor, Tim Berners-Lee. Now, with the introduction of XML and RDF, and new developments such as RDF
 Schema and DAML+OIL, the Semantic Web is rapidly taking shape. In this paper, we first give an overview of the state-of-the-art
 in Semantic Web technology, the key relationships with traditional hypermedia research, and a comprehensive reference list
 to various sets of literature (Hypertext, Web and Semantic Web). We then present a research agenda by describing the open
 research issues in the development of the Semantic Web from the perspective of hypermedia research. },
url          = {http://jodi.ecs.soton.ac.uk/Articles/v03/i01/VanOssenbruggen/},
}

Until recently, the Semantic Web was little more than a name for the next generation Web infrastructure as envisioned by its inventor, Tim Berners-Lee. Now, with the introduction of XML and RDF, and new developments such as RDF Schema and DAML+OIL, the Semantic Web is rapidly taking shape. In this paper, we first give an overview of the state-of-the-art in Semantic Web technology, the key relationships with traditional hypermedia research, and a comprehensive reference list to various sets of literature (Hypertext, Web and Semantic Web). We then present a research agenda by describing the open research issues in the development of the Semantic Web from the perspective of hypermedia research.

@incollection{11410,
author       = {van Ossenbruggen, J. R. and Hardman, L.},
title        = {Smart {Style} {On} {The} {Semantic} {Web}},
year         = {2002},
note         = {bibliographical data to be processed -- Semantic Web Workshop, WWW2002, 2002 --  -- },
keywords     = {Semantic Web, Device Independent Authoring, Document Engineering, Graphic Design},
group        = {INS2},
language     = {en},
abstract     = {Web publishing systems have to take into account a plethora of Web-enabled devices, user preferences and
 abilities. Technologies generating these presentations will need to be explicitly aware of the context in which the information
 is being presented. Semantic Web technology can be a fundamental part of the solution to this problem by explicitly modeling
 the knowledge needed to adapt presentations to a specific delivery context. We propose the development of a emphSmart Stylelayer
 which is able to process metadata that describes content and use this metadata to improve the presentation of the content
 to human users. In the paper, we derive the requirements of such a Smart Style layer by considering Web design from both
 the document engineering and graphic design perspectives. In addition, design trade-offs made by human designers have to
 be taken into account for the automated process. After stating the requirements for a Smart Style layer, we discuss to what
 extent the currently available Web technology can be used and what its limitations are. The limitations are illustrated
 with examples of potential future extensions. },
url          = {http://oai.cwi.nl/oai/asset/11410/11410B.pdf},
}

Web publishing systems have to take into account a plethora of Web-enabled devices, user preferences and abilities. Technologies generating these presentations will need to be explicitly aware of the context in which the information is being presented. Semantic Web technology can be a fundamental part of the solution to this problem by explicitly modeling the knowledge needed to adapt presentations to a specific delivery context. We propose the development of a emphSmart Stylelayer which is able to process metadata that describes content and use this metadata to improve the presentation of the content to human users. In the paper, we derive the requirements of such a Smart Style layer by considering Web design from both the document engineering and graphic design perspectives. In addition, design trade-offs made by human designers have to be taken into account for the automated process. After stating the requirements for a Smart Style layer, we discuss to what extent the currently available Web technology can be used and what its limitations are. The limitations are illustrated with examples of potential future extensions.

@techreport{4340,
author       = {Geurts, J. P. T. M. and van Ossenbruggen, J. R. and Hardman, L.},
title        = {Application-{Specific} {Constraints} {For} {Multimedia} {Presentation} {Generation}},
type         = {CWI Technical Report},
origin       = {other},
series       = {Information Systems [INS]},
pages        = {1 - 16},
year         = {2001},
number       = {INS-R 0107},
publisher    = {CWI},
issn         = {1386-3681},
size         = {16p.},
class        = {H.5.4;H.5.1;I.7},
group        = {INS2},
language     = {en},
abstract     = {A multimedia presentation can be viewed as a collection of multimedia items (such as image, text, video and
 audio), along with detailed information that describes the spatial and temporal placement of the items as part of the presentation.
  Manual multimedia authoring involves explicitly stating the placement of each media item in the spatial and temporal dimensions.
  The drawback of this approach is that resulting presentations are hard to adapt to different target platforms, network
 resources, and user preferences.  An approach to solving this problem is to abstract from the low-level presentation details,
 for example by specifying the high-level semantic relations between the media items.  The presentation itself can then be
 generated from the semantic relations along with a generic set of transformation rules, specifying how each semantic relation
 can be conveyed using multimedia constructs.  These constructs may differ depending on the target platform, current network
 conditions or user preferences. We are thus able to automatically adapt the presentation to a wide variety of different
 circumstances while ensuring that the underlying message of the presentation remains the same.  This approach requires an
 execution environment in which transformation rules, resulting in a set of constraints, are derived from a given semantic
 description.  The resulting set of constraints can then be solved to create a final multimedia presentation.  The paper
 describes the design and implementation of such a system.  It explains the advantages of using constraint logic programming
 to realize the implementation of both the transformation rules and the constraints system.  It also demonstrates the need
 for two different types of constraints.  Quantitative constraints are needed to verify whether the final form presentation
 meets all the numeric constraints that are required by the environment.  Qualitative constraints are needed to facilitate
 high-level reasoning and presentation encoding. While the quantitative constraints can be handled by off-the-shelf constraint
 solvers, the qualitative constraints needed are specific to the multimedia domain and need to be defined explicitly.},
url          = {http://oai.cwi.nl/oai/asset/4340/04340D.pdf},
}

A multimedia presentation can be viewed as a collection of multimedia items (such as image, text, video and audio), along with detailed information that describes the spatial and temporal placement of the items as part of the presentation. Manual multimedia authoring involves explicitly stating the placement of each media item in the spatial and temporal dimensions. The drawback of this approach is that resulting presentations are hard to adapt to different target platforms, network resources, and user preferences. An approach to solving this problem is to abstract from the low-level presentation details, for example by specifying the high-level semantic relations between the media items. The presentation itself can then be generated from the semantic relations along with a generic set of transformation rules, specifying how each semantic relation can be conveyed using multimedia constructs. These constructs may differ depending on the target platform, current network conditions or user preferences. We are thus able to automatically adapt the presentation to a wide variety of different circumstances while ensuring that the underlying message of the presentation remains the same. This approach requires an execution environment in which transformation rules, resulting in a set of constraints, are derived from a given semantic description. The resulting set of constraints can then be solved to create a final multimedia presentation. The paper describes the design and implementation of such a system. It explains the advantages of using constraint logic programming to realize the implementation of both the transformation rules and the constraints system. It also demonstrates the need for two different types of constraints. Quantitative constraints are needed to verify whether the final form presentation meets all the numeric constraints that are required by the environment. Qualitative constraints are needed to facilitate high-level reasoning and presentation encoding. While the quantitative constraints can be handled by off-the-shelf constraint solvers, the qualitative constraints needed are specific to the multimedia domain and need to be defined explicitly.

@techreport{4342,
author       = {van Ossenbruggen, J. R. and Hardman, L. and Rutledge, L.},
title        = {Hypermedia {And} {The} {Semantic} {Web}: {A} {Research} {Agenda}},
type         = {CWI Technical Report},
origin       = {other},
series       = {Information Systems [INS]},
pages        = {1 - 14},
year         = {2001},
number       = {INS-R 0105},
publisher    = {CWI},
issn         = {1386-3681},
size         = {14p.},
class        = {H.5.4;H.5.1;I.2.4},
group        = {INS2},
language     = {en},
abstract     = {Until recently, the Semantic Web was little more than a name for the next generation Web infrastructure as
 envisioned by its inventor, Tim Berners-Lee.  Now, with the introduction of XML and RDF, and new developments such as RDF
 Schema and DAML+OIL, the Semantic Web is rapidly taking shape.  In this paper, we first give an overview of the state-of-the-art
 in Semantic Web technology, the key relationships with traditional hypermedia research, and a comprehensive reference list
 to various sets of literature (Hypertext, Web and Semantic Web). The core of the paper presents a research agenda by describing
 the open research issues in the development of the Semantic Web from the perspective of hypermedia research.},
url          = {http://oai.cwi.nl/oai/asset/4342/04342D.pdf},
}

Until recently, the Semantic Web was little more than a name for the next generation Web infrastructure as envisioned by its inventor, Tim Berners-Lee. Now, with the introduction of XML and RDF, and new developments such as RDF Schema and DAML+OIL, the Semantic Web is rapidly taking shape. In this paper, we first give an overview of the state-of-the-art in Semantic Web technology, the key relationships with traditional hypermedia research, and a comprehensive reference list to various sets of literature (Hypertext, Web and Semantic Web). The core of the paper presents a research agenda by describing the open research issues in the development of the Semantic Web from the perspective of hypermedia research.

@incollection{11351,
author       = {van Ossenbruggen, J. R. and Geurts, J. P. T. M. and Cornelissen, F. J. and Rutledge, L. and Hardman, L.},
title        = {Towards {Second} {And} {Third} {Generation} {Web-{Based}} {Multimedia}},
booktitle    = {International World Wide Web Conference (WWW2001)},
pages        = {479 - 488},
year         = {2001},
month        = {May},
publisher    = {ACM Press},
size         = {10p.},
group        = {INS2},
language     = {en},
abstract     = {First generation Web-content encodes information in handwritten (HTML) Web pages. Second generation Web content
 generates HTML pages on demand, e.g. by filling in templates with content retrieved dynamically from a database or transformation
 of structured documents using style sheets (e.g. XSLT). Third generation Web pages will make use of rich markup (e.g. XML)
 along with metadata (e.g. RDF) schemes to make the content not only machine readable but also machine processable - a necessary
 pre-requisite to the emphSemantic Web. While text-based content on the Web is already rapidly approaching the third generation,
 multimedia content is still trying to catch up with second generation techniques. Multimedia document processing has a number
 of fundamentally different requirements from text which make it more difficult to incorporate within the document processing
 chain. In particular, multimedia transformation uses different document and presentation abstractions, its formatting rules
 cannot be based on text-flow, it requires feedback from the formatting back-end and is hard to describe in the functional
 style of current style languages. We state the requirements for second generation processing of multimedia and describe
 how these have been incorporated in our prototype multimedia document transformation environment, emphCuypers. The system
 overcomes a number of the restrictions of the text-flow based tool sets by integrating a number of conceptually distinct
 processing steps in a single runtime execution environment. We describe the need for these different processing steps and
 describe them in turn (semantic structure, communicative device, qualitative constraints, quantitative constraints, final
 form presentation), and illustrate our approach by means of an example. We conclude by discussing the models and techniques
 required for the creation of third generation multimedia content. },
url          = {http://oai.cwi.nl/oai/asset/11351/11351C.pdf},
url          = {http://doi.acm.org/10.1145/371920.372143},
}

First generation Web-content encodes information in handwritten (HTML) Web pages. Second generation Web content generates HTML pages on demand, e.g. by filling in templates with content retrieved dynamically from a database or transformation of structured documents using style sheets (e.g. XSLT). Third generation Web pages will make use of rich markup (e.g. XML) along with metadata (e.g. RDF) schemes to make the content not only machine readable but also machine processable - a necessary pre-requisite to the emphSemantic Web. While text-based content on the Web is already rapidly approaching the third generation, multimedia content is still trying to catch up with second generation techniques. Multimedia document processing has a number of fundamentally different requirements from text which make it more difficult to incorporate within the document processing chain. In particular, multimedia transformation uses different document and presentation abstractions, its formatting rules cannot be based on text-flow, it requires feedback from the formatting back-end and is hard to describe in the functional style of current style languages. We state the requirements for second generation processing of multimedia and describe how these have been incorporated in our prototype multimedia document transformation environment, emphCuypers. The system overcomes a number of the restrictions of the text-flow based tool sets by integrating a number of conceptually distinct processing steps in a single runtime execution environment. We describe the need for these different processing steps and describe them in turn (semantic structure, communicative device, qualitative constraints, quantitative constraints, final form presentation), and illustrate our approach by means of an example. We conclude by discussing the models and techniques required for the creation of third generation multimedia content.

@incollection{11370,
author       = {Geurts, J. P. T. M. and van Ossenbruggen, J. R. and Hardman, L.},
title        = {Application-{Specific} {Constraints} {For} {Multimedia} {Presentation} {Generation}},
year         = {2001},
note         = {bibliographical data to be processed -- Proceedings of the International Conference on Multimedia Modeling 2001 (MMM01), 247-266, 2001 --  -- 19},
keywords     = {Multimedia, Constraints, CLP, CHR, Cuypers},
group        = {INS2},
language     = {en},
abstract     = {The paper describes the advantages of the use of constraint logic programming to articulate transformation
 rules for multimedia presentation in combination with efficient constraint solving techniques. It demonstrates the need
 for two different types of constraints. Quantitative constraints are needed to verify whether the final form presentation
 meets all the numeric constraints that are required by the environment. Qualitative constraints are needed to facilitate
 high-level reasoning and presentation encoding. While the quantitative constraints can be handled by off-the-shelf constraint
 solvers, the qualitative constraints needed are specific to the multimedia domain and need to be defined explicitly. },
url          = {http://oai.cwi.nl/oai/asset/11370/11370B.pdf},
}

The paper describes the advantages of the use of constraint logic programming to articulate transformation rules for multimedia presentation in combination with efficient constraint solving techniques. It demonstrates the need for two different types of constraints. Quantitative constraints are needed to verify whether the final form presentation meets all the numeric constraints that are required by the environment. Qualitative constraints are needed to facilitate high-level reasoning and presentation encoding. While the quantitative constraints can be handled by off-the-shelf constraint solvers, the qualitative constraints needed are specific to the multimedia domain and need to be defined explicitly.

@phdthesis{11438,
author       = {van Ossenbruggen, J. R.},
editor       = {van Vliet, J. C. and Eliëns, A.},
title        = {Processing {Structured} {Hypermedia} - {A} {Matter} {Of} {Style}},
school       = {Vrije Universiteit Amsterdam},
year         = {2001},
date         = {2001-04-10},
advisor      = {van Vliet, J.C.},
coadvisor    = {Eliëns, A.},
group        = {INS2},
language     = {en},
abstract     = {With the introduction of the World Wide Web in the early nineties, hypermedia has become the uniform interface
 to the wide variety of information sources available over the Internet. The full potential of the Web, however, can only
 be realized by building on the strengths of its underlying research fields. This book describes the areas of hypertext,
 multimedia, electronic publishing and the World Wide Web and points out fundamental similarities and differences in approaches
 towards the processing of information. It gives an overview of the dominant models and tools developed in these fields and
 describes the key interrelationships and mutual incompatibilities. In addition to a formal specification of a selection
 of these models, the book discusses the impact of the models described on the software architectures that have been developed
 for processing hypermedia documents. Two example hypermedia architectures are described in more detail: the DejaVu object-oriented
 hypermedia framework, developed at the VU, and CWI's Berlage environment for time-based hypermedia document transformations.
 },
url          = {http://oai.cwi.nl/oai/asset/11438/11438B.pdf},
}

With the introduction of the World Wide Web in the early nineties, hypermedia has become the uniform interface to the wide variety of information sources available over the Internet. The full potential of the Web, however, can only be realized by building on the strengths of its underlying research fields. This book describes the areas of hypertext, multimedia, electronic publishing and the World Wide Web and points out fundamental similarities and differences in approaches towards the processing of information. It gives an overview of the dominant models and tools developed in these fields and describes the key interrelationships and mutual incompatibilities. In addition to a formal specification of a selection of these models, the book discusses the impact of the models described on the software architectures that have been developed for processing hypermedia documents. Two example hypermedia architectures are described in more detail: the DejaVu object-oriented hypermedia framework, developed at the VU, and CWI's Berlage environment for time-based hypermedia document transformations.

@inproceedings{16577,
author       = {Geurts, J. P. T. M. and van Ossenbruggen, J. R. and Hardman, L.},
title        = {Application-{Specific} {Constraints} {For} {Multimedia} {Presentation} {Generation}},
booktitle    = {Proceedings of International Conference on Multimedia Modeling  2001},
conferencetitle    = {International Conference on Multimedia Modeling },
conferencedate     = {2001},
pages        = {247 - 266},
year         = {2001},
refereed     = {y},
size         = {20p.},
keywords     = {Multimedia, Constraints, CLP, CHR, Cuypers},
group        = {INS2},
language     = {en},
abstract     = {The paper describes the advantages of the use of constraint logic programming to articulate transformation
 rules for multimedia presentation in combination with efficient constraint solving techniques. It demonstrates the need
 for two different types of constraints. Quantitative constraints are needed to verify whether the final form presentation
 meets all the numeric constraints that are required by the environment. Qualitative constraints are needed to facilitate
 high-level reasoning and presentation encoding. While the quantitative constraints can be handled by off-the-shelf constraint
 solvers, the qualitative constraints needed are specific to the multimedia domain and need to be defined explicitly. },
}

The paper describes the advantages of the use of constraint logic programming to articulate transformation rules for multimedia presentation in combination with efficient constraint solving techniques. It demonstrates the need for two different types of constraints. Quantitative constraints are needed to verify whether the final form presentation meets all the numeric constraints that are required by the environment. Qualitative constraints are needed to facilitate high-level reasoning and presentation encoding. While the quantitative constraints can be handled by off-the-shelf constraint solvers, the qualitative constraints needed are specific to the multimedia domain and need to be defined explicitly.

@techreport{4384,
author       = {van Ossenbruggen, J. R. and Hardman, L. and Rutledge, L.},
title        = {Integrating {Multimedia} {Characteristics} {In} {Web-}{Based} {Document} {Languages}},
type         = {CWI Technical Report},
origin       = {other},
series       = {Information Systems [INS]},
pages        = {1 - 15},
year         = {2000},
number       = {INS-R 0024},
publisher    = {CWI},
issn         = {1386-3681},
size         = {15p.},
class        = {H.5.4;H.5.1;I.7},
group        = {INS2},
language     = {en},
abstract     = {A single multimedia document model needs to include a wide range of different types of information. In particular,
 information about space and time is essential for determining the spatial and temporal placement of elements within a presentation.
 Each information type included in a document model requires its own structuring mechanisms. The language used to express
 the document model has to be able to encapsulate the plurality of required structures. While this is a process that can
 be carried out relatively easily during the initial design of a language, it is more difficult in the case that a particular
 document language already exists and extra multimedia characteristics are required. For example, one could consider adding
 temporal information to an existing 'static' document language. We investigate the underlying problems of superimposing
 a new document feature on an existing language and discuss possible strategies for integrating the required extra information
 in a modified document description language.},
url          = {http://oai.cwi.nl/oai/asset/4384/04384D.pdf},
}

A single multimedia document model needs to include a wide range of different types of information. In particular, information about space and time is essential for determining the spatial and temporal placement of elements within a presentation. Each information type included in a document model requires its own structuring mechanisms. The language used to express the document model has to be able to encapsulate the plurality of required structures. While this is a process that can be carried out relatively easily during the initial design of a language, it is more difficult in the case that a particular document language already exists and extra multimedia characteristics are required. For example, one could consider adding temporal information to an existing 'static' document language. We investigate the underlying problems of superimposing a new document feature on an existing language and discuss possible strategies for integrating the required extra information in a modified document description language.