@inproceedings{Katsamanis2011MultipleInstanceLearningfor,
 abstract = {Analysis of audiovisual human behavior observations is a
common practice in behavioral sciences. It is generally carried through
by expert annotators who are asked to evaluate several aspects of the
observations along various dimensions. This can be a tedious task. We
propose that automatic classification of behavioral patterns in this context
can be viewed as a multiple instance learning problem. In this paper, we analyze a corpus of married couples interacting about a problem
in their relationship. We extract features from both the audio and the
transcriptions and apply the Diverse Density-Support Vector Machine
framework. Apart from attaining classification on the expert annotations, this framework also allows us to estimate salient regions of the
complex interaction.},
 author = {Katsamanis, Athanasios and Gibson, James and Black, Matthew P. and Narayanan, Shrikanth S.},
 bib2html_rescat = {},
 booktitle = {Proceedings of Affective Computing and Intelligent Interaction (ACII), Lecture Notes in Computer Science},
 doi = {10.1007/978-3-642-24600-5_18},
 link = {http://sail.usc.edu/publications/files/KatsamanisGibsonBlackNarayanan_MIL_HumanBehavior_ACII2011.pdf},
 location = {Memphis, TN},
 month = {Oct},
 title = {Multiple Instance Learning for Classification of Human Behavior Observations},
 year = {2011}
}

{"_id":"8d2asEQ8cT9SJXwYT","bibbaseid":"katsamanis-gibson-black-narayanan-multipleinstancelearningforclassificationofhumanbehaviorobservations-2011","downloads":0,"creationDate":"2017-05-08T08:45:46.179Z","title":"Multiple Instance Learning for Classification of Human Behavior Observations","author_short":["Katsamanis, A.","Gibson, J.","Black, M. P.","Narayanan, S. S."],"year":2011,"bibtype":"inproceedings","biburl":"https://bibbase.org/f/nWhKb4SffvhfreEmj/shri-isi-edu.bib","bibdata":{"bibtype":"inproceedings","type":"inproceedings","abstract":"Analysis of audiovisual human behavior observations is a common practice in behavioral sciences. It is generally carried through by expert annotators who are asked to evaluate several aspects of the observations along various dimensions. This can be a tedious task. We propose that automatic classification of behavioral patterns in this context can be viewed as a multiple instance learning problem. In this paper, we analyze a corpus of married couples interacting about a problem in their relationship. We extract features from both the audio and the transcriptions and apply the Diverse Density-Support Vector Machine framework. Apart from attaining classification on the expert annotations, this framework also allows us to estimate salient regions of the complex interaction.","author":[{"propositions":[],"lastnames":["Katsamanis"],"firstnames":["Athanasios"],"suffixes":[]},{"propositions":[],"lastnames":["Gibson"],"firstnames":["James"],"suffixes":[]},{"propositions":[],"lastnames":["Black"],"firstnames":["Matthew","P."],"suffixes":[]},{"propositions":[],"lastnames":["Narayanan"],"firstnames":["Shrikanth","S."],"suffixes":[]}],"bib2html_rescat":"","booktitle":"Proceedings of Affective Computing and Intelligent Interaction (ACII), Lecture Notes in Computer Science","doi":"10.1007/978-3-642-24600-5_18","link":"http://sail.usc.edu/publications/files/KatsamanisGibsonBlackNarayanan_MIL_HumanBehavior_ACII2011.pdf","location":"Memphis, TN","month":"Oct","title":"Multiple Instance Learning for Classification of Human Behavior Observations","year":"2011","bibtex":"@inproceedings{Katsamanis2011MultipleInstanceLearningfor,\n abstract = {Analysis of audiovisual human behavior observations is a\ncommon practice in behavioral sciences. It is generally carried through\nby expert annotators who are asked to evaluate several aspects of the\nobservations along various dimensions. This can be a tedious task. We\npropose that automatic classification of behavioral patterns in this context\ncan be viewed as a multiple instance learning problem. In this paper, we analyze a corpus of married couples interacting about a problem\nin their relationship. We extract features from both the audio and the\ntranscriptions and apply the Diverse Density-Support Vector Machine\nframework. Apart from attaining classification on the expert annotations, this framework also allows us to estimate salient regions of the\ncomplex interaction.},\n author = {Katsamanis, Athanasios and Gibson, James and Black, Matthew P. and Narayanan, Shrikanth S.},\n bib2html_rescat = {},\n booktitle = {Proceedings of Affective Computing and Intelligent Interaction (ACII), Lecture Notes in Computer Science},\n doi = {10.1007/978-3-642-24600-5_18},\n link = {http://sail.usc.edu/publications/files/KatsamanisGibsonBlackNarayanan_MIL_HumanBehavior_ACII2011.pdf},\n location = {Memphis, TN},\n month = {Oct},\n title = {Multiple Instance Learning for Classification of Human Behavior Observations},\n year = {2011}\n}\n\n","author_short":["Katsamanis, A.","Gibson, J.","Black, M. P.","Narayanan, S. S."],"bibbaseid":"katsamanis-gibson-black-narayanan-multipleinstancelearningforclassificationofhumanbehaviorobservations-2011","role":"author","urls":{},"metadata":{"authorlinks":{}}},"search_terms":["multiple","instance","learning","classification","human","behavior","observations","katsamanis","gibson","black","narayanan"],"keywords":[],"authorIDs":[],"dataSources":["z5xLfHHoMYwhn8vbA","P3nQrSLkFzGGSmKJQ","Reikhy6EiDXFTcuR9"]}