{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T23:07:05Z","timestamp":1756076825251},"reference-count":17,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,5]]},"DOI":"10.1109\/icassp.2011.5946412","type":"proceedings-article","created":{"date-parts":[[2011,7,13]],"date-time":"2011-07-13T15:50:30Z","timestamp":1310572230000},"page":"349-352","source":"Crossref","is-referenced-by-count":5,"title":["Improving acoustic event detection using generalizable visual features and multi-modality modeling"],"prefix":"10.1109","author":[{"given":"Po-Sen","family":"Huang","sequence":"first","affiliation":[]},{"given":"Xiaodan","family":"Zhuang","sequence":"additional","affiliation":[]},{"given":"Mark","family":"Hasegawa-Johnson","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"214","article-title":"A duality based approach for realtime tv-11 optical flow","author":"zach","year":"0","journal-title":"Pattern Recognition (Proc DAGM)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2008.4761434"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-13015-5_35"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/89.799688"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553391"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2002.1021886"},{"key":"ref17","article-title":"Feature analysis and selection for acoustic event detection","author":"zhuang","year":"0","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"journal-title":"CLEAR 2007 AED evaluation plan","year":"2007","author":"temko","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198808"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2001.1237704"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2010.02.005"},{"key":"ref8","article-title":"Audio-visual speech modeling using coupled hidden Markov models","author":"chu","year":"0","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-32367-8_7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521669"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2009.5204264"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2004.05.001"}],"event":{"name":"ICASSP 2011 - 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2011,5,22]]},"location":"Prague, Czech Republic","end":{"date-parts":[[2011,5,27]]}},"container-title":["2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5916934\/5946226\/05946412.pdf?arnumber=5946412","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,21]],"date-time":"2017-03-21T09:45:55Z","timestamp":1490089555000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5946412\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,5]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/icassp.2011.5946412","relation":{},"subject":[],"published":{"date-parts":[[2011,5]]}}}