Multivariate density-based 3D shape Descriptors. Akguel, C. B., Sankur, B., Schmitt, F., & Yemez, Y. In IEEE INTERNATIONAL CONFERENCE ON SHAPE MODELING AND APPLICATIONS 2007, PROCEEDINGS, pages 3-12, 2007. ACM SIGRAPT; CNRS; Groupement Rech Informat Mathemat; Reg Rhone Alpes; Univ Claude Bernard Lyon 1. 9th International Conference on Shape Modeling and Applications, Lyon, FRANCE, JUN 13-15, 2007doi abstract bibtex We address the 3D object retrieval problem using multivariate density-based shape descriptors. Considering the fusion of first and second order local surface information, we construct multivariate features up to five dimensions and process them by the kernel density estimation methodology to obtain descriptor vectors. We can compute these descriptors very efficiently using the fast Gauss transform algorithm. We also make use of descriptor level information fusion by concatenating descriptor vectors to increase their discrimination power further To render the resulting descriptors storage-wise efficient, we develop two analytical tools, marginalization and probability density suppression, for descriptor dimensionality reduction. The experiments on two different databases, Princeton Shape Benchmark and Sculpteur show that, boosted with both feature level and descriptor level information fusion, and powered with fast computational schemes, the density-based shape description firamework enables effective and efficient 3D object retrieval.
@inproceedings{ ISI:000248622300001,
Author = {Akguel, Ceyhun Burak and Sankur, Buelent and Schmitt, Francis and Yemez,
Yuecel},
Book-Group-Author = {{IEEE Computer Society}},
Title = {{Multivariate density-based 3D shape Descriptors}},
Booktitle = {{IEEE INTERNATIONAL CONFERENCE ON SHAPE MODELING AND APPLICATIONS 2007,
PROCEEDINGS}},
Year = {{2007}},
Pages = {{3-12}},
Note = {{9th International Conference on Shape Modeling and Applications, Lyon,
FRANCE, JUN 13-15, 2007}},
Organization = {{ACM SIGRAPT; CNRS; Groupement Rech Informat Mathemat; Reg Rhone Alpes;
Univ Claude Bernard Lyon 1}},
Abstract = {{We address the 3D object retrieval problem using multivariate
density-based shape descriptors. Considering the fusion of first and
second order local surface information, we construct multivariate
features up to five dimensions and process them by the kernel density
estimation methodology to obtain descriptor vectors. We can compute
these descriptors very efficiently using the fast Gauss transform
algorithm. We also make use of descriptor level information fusion by
concatenating descriptor vectors to increase their discrimination power
further To render the resulting descriptors storage-wise efficient, we
develop two analytical tools, marginalization and probability density
suppression, for descriptor dimensionality reduction. The experiments on
two different databases, Princeton Shape Benchmark and Sculpteur show
that, boosted with both feature level and descriptor level information
fusion, and powered with fast computational schemes, the density-based
shape description firamework enables effective and efficient 3D object
retrieval.}},
DOI = {{10.1109/SMI.2007.27}},
ISBN = {{978-0-7695-2815-1}},
Unique-ID = {{ISI:000248622300001}},
}
Downloads: 0
{"_id":"ngNBgGWbTCY5dzewu","bibbaseid":"akguel-sankur-schmitt-yemez-multivariatedensitybased3dshapedescriptors-2007","downloads":0,"creationDate":"2016-12-09T13:41:59.910Z","title":"Multivariate density-based 3D shape Descriptors","author_short":["Akguel, C. B.","Sankur, B.","Schmitt, F.","Yemez, Y."],"year":2007,"bibtype":"inproceedings","biburl":"http://home.ku.edu.tr/~eerzin/pubs/mvgl.bib","bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Akguel"],"firstnames":["Ceyhun","Burak"],"suffixes":[]},{"propositions":[],"lastnames":["Sankur"],"firstnames":["Buelent"],"suffixes":[]},{"propositions":[],"lastnames":["Schmitt"],"firstnames":["Francis"],"suffixes":[]},{"propositions":[],"lastnames":["Yemez"],"firstnames":["Yuecel"],"suffixes":[]}],"book-group-author":"IEEE Computer Society","title":"Multivariate density-based 3D shape Descriptors","booktitle":"IEEE INTERNATIONAL CONFERENCE ON SHAPE MODELING AND APPLICATIONS 2007, PROCEEDINGS","year":"2007","pages":"3-12","note":"9th International Conference on Shape Modeling and Applications, Lyon, FRANCE, JUN 13-15, 2007","organization":"ACM SIGRAPT; CNRS; Groupement Rech Informat Mathemat; Reg Rhone Alpes; Univ Claude Bernard Lyon 1","abstract":"We address the 3D object retrieval problem using multivariate density-based shape descriptors. Considering the fusion of first and second order local surface information, we construct multivariate features up to five dimensions and process them by the kernel density estimation methodology to obtain descriptor vectors. We can compute these descriptors very efficiently using the fast Gauss transform algorithm. We also make use of descriptor level information fusion by concatenating descriptor vectors to increase their discrimination power further To render the resulting descriptors storage-wise efficient, we develop two analytical tools, marginalization and probability density suppression, for descriptor dimensionality reduction. The experiments on two different databases, Princeton Shape Benchmark and Sculpteur show that, boosted with both feature level and descriptor level information fusion, and powered with fast computational schemes, the density-based shape description firamework enables effective and efficient 3D object retrieval.","doi":"10.1109/SMI.2007.27","isbn":"978-0-7695-2815-1","unique-id":"ISI:000248622300001","bibtex":"@inproceedings{ ISI:000248622300001,\nAuthor = {Akguel, Ceyhun Burak and Sankur, Buelent and Schmitt, Francis and Yemez,\n Yuecel},\nBook-Group-Author = {{IEEE Computer Society}},\nTitle = {{Multivariate density-based 3D shape Descriptors}},\nBooktitle = {{IEEE INTERNATIONAL CONFERENCE ON SHAPE MODELING AND APPLICATIONS 2007,\n PROCEEDINGS}},\nYear = {{2007}},\nPages = {{3-12}},\nNote = {{9th International Conference on Shape Modeling and Applications, Lyon,\n FRANCE, JUN 13-15, 2007}},\nOrganization = {{ACM SIGRAPT; CNRS; Groupement Rech Informat Mathemat; Reg Rhone Alpes;\n Univ Claude Bernard Lyon 1}},\nAbstract = {{We address the 3D object retrieval problem using multivariate\n density-based shape descriptors. Considering the fusion of first and\n second order local surface information, we construct multivariate\n features up to five dimensions and process them by the kernel density\n estimation methodology to obtain descriptor vectors. We can compute\n these descriptors very efficiently using the fast Gauss transform\n algorithm. We also make use of descriptor level information fusion by\n concatenating descriptor vectors to increase their discrimination power\n further To render the resulting descriptors storage-wise efficient, we\n develop two analytical tools, marginalization and probability density\n suppression, for descriptor dimensionality reduction. The experiments on\n two different databases, Princeton Shape Benchmark and Sculpteur show\n that, boosted with both feature level and descriptor level information\n fusion, and powered with fast computational schemes, the density-based\n shape description firamework enables effective and efficient 3D object\n retrieval.}},\nDOI = {{10.1109/SMI.2007.27}},\nISBN = {{978-0-7695-2815-1}},\nUnique-ID = {{ISI:000248622300001}},\n}\n\n","author_short":["Akguel, C. B.","Sankur, B.","Schmitt, F.","Yemez, Y."],"key":"ISI:000248622300001","id":"ISI:000248622300001","bibbaseid":"akguel-sankur-schmitt-yemez-multivariatedensitybased3dshapedescriptors-2007","role":"author","urls":{},"metadata":{"authorlinks":{}},"downloads":0,"html":""},"search_terms":["multivariate","density","based","shape","descriptors","akguel","sankur","schmitt","yemez"],"keywords":[],"authorIDs":[],"dataSources":["P7SB4qiBxZPhjXYRW"]}