{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T01:17:45Z","timestamp":1768871865953,"version":"3.49.0"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2010,10,1]],"date-time":"2010-10-01T00:00:00Z","timestamp":1285891200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2010,10]]},"DOI":"10.1109\/tmm.2010.2051871","type":"journal-article","created":{"date-parts":[[2010,9,15]],"date-time":"2010-09-15T21:13:45Z","timestamp":1284585225000},"page":"523-535","source":"Crossref","is-referenced-by-count":63,"title":["Affective Audio-Visual Words and Latent Topic Driving Model for Realizing Movie Affective Scene Classification"],"prefix":"10.1109","volume":"12","author":[{"given":"Go","family":"Irie","sequence":"first","affiliation":[]},{"given":"Takashi","family":"Satou","sequence":"additional","affiliation":[]},{"given":"Akira","family":"Kojima","sequence":"additional","affiliation":[]},{"given":"Toshihiko","family":"Yamasaki","sequence":"additional","affiliation":[]},{"given":"Kiyoharu","family":"Aizawa","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","first-page":"2167","DOI":"10.21437\/Eurospeech.1999-546","article-title":"topic-based language models using em","author":"gildea","year":"1999","journal-title":"Proc EUROSPEECH"},{"key":"ref38","first-page":"591","article-title":"maximum entropy markov models for information extraction and segmentation","author":"mccallum","year":"2000","journal-title":"Proc Int Conf Machine Learning (ICML)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071"},{"key":"ref32","first-page":"289","article-title":"probabilistic latent semantic analysis","author":"hofmann","year":"1999","journal-title":"Proc Conf Uncertainty in Artificial Intelligence (UAI)"},{"key":"ref31","first-page":"17","article-title":"hierarchical topic models and the nested chinese restaurant process","author":"blei","year":"2003","journal-title":"Proc Neural Information Processing Systems (NIPS)"},{"key":"ref30","first-page":"682","article-title":"the cluster-abstraction model: unsupervised learning of topic hierarchies from text data","author":"hofmann","year":"1999","journal-title":"Proc Int Joint Conf Artificial Intelligence (IJCAI)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1026711.1026751"},{"key":"ref36","first-page":"495","author":"talkin","year":"1995","journal-title":"Speech Coding and Synthesis"},{"key":"ref35","first-page":"1","article-title":"visual categorization with bags of keypoints","author":"csurka","year":"2004","journal-title":"Proc Eur Conf Computer Vision (ECCV)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.1994.318984"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1080\/08838159509364309"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.23.1.473"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"1971","DOI":"10.21437\/Eurospeech.1997-523","article-title":"language model adaptation using dynamic marginals","author":"kneser","year":"1997","journal-title":"Proc EUROSPEECH"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/nn733"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1631272.1631357"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1080\/026999398379574"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780195169157.001.0001","author":"coan","year":"2007","journal-title":"Handbook of Emotion Elicitation and Assessment"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF02686918"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"ref18","first-page":"207","article-title":"universals and cultural differences in facial expressions of emotion","volume":"19","author":"ekman","year":"1972","journal-title":"Proc Nebraska Symp Motivation"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1511\/2001.4.344"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007469218079"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2003.1246884"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/jmlr.2003.3.4-5.993"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1198302.1198305"},{"key":"ref6","first-page":"105","article-title":"automatically extracting highlights for tv baseball programs","author":"rui","year":"2000","journal-title":"Proc ACM Int Conf Multimedia (ACM MM)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2004.02.004"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/500178.500181"},{"key":"ref8","first-page":"456","article-title":"video summarization using greedy method in a constraint satisfaction framework","author":"lu","year":"2003","journal-title":"Proc Int Conf Distributed Multimedia Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2006.262855"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2004.840618"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1126004.1126005"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1076034.1076097"},{"key":"ref20","first-page":"259","article-title":"affective content detection using hmms","author":"kang","year":"2003","journal-title":"Proc ACM Int Conf Multimedia (ACM MM)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2009.5202548"},{"key":"ref21","first-page":"622","article-title":"affective content analysis in comedy and horror videos by audio emotional event detection","author":"xu","year":"2005","journal-title":"Proc IEEE Int Conf Multimedia & Expo (ICME)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291251"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.4018\/jdwm.2007070101"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.2004911"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1080\/02699939508408966"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1007\/978-3-540-74889-2_52","article-title":"video affective content representation and recognition using video affective tree and hidden markov models","author":"sun","year":"2007","journal-title":"Proc 1st Int Conf Affective Comput Intell Interaction"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1459359.1459457"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/S0306-4573(02)00021-3"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6046\/5571813\/05571819.pdf?arnumber=5571819","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,25]],"date-time":"2025-02-25T21:26:52Z","timestamp":1740518812000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5571819\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,10]]},"references-count":43,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2010.2051871","relation":{},"ISSN":["1520-9210"],"issn-type":[{"value":"1520-9210","type":"print"}],"subject":[],"published":{"date-parts":[[2010,10]]}}}