{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T07:07:09Z","timestamp":1742800029090,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009,6]]},"DOI":"10.1109\/cvprw.2009.5204264","type":"proceedings-article","created":{"date-parts":[[2010,3,1]],"date-time":"2010-03-01T18:36:32Z","timestamp":1267468592000},"page":"81-88","source":"Crossref","is-referenced-by-count":5,"title":["Audiovisual event detection towards scene understanding"],"prefix":"10.1109","author":[{"given":"C.","family":"Canton-Ferrer","sequence":"first","affiliation":[]},{"given":"T.","family":"Butko","sequence":"additional","affiliation":[]},{"given":"C.","family":"Segura","sequence":"additional","affiliation":[]},{"given":"X.","family":"Giro","sequence":"additional","affiliation":[]},{"given":"C.","family":"Nadeu","sequence":"additional","affiliation":[]},{"given":"J.","family":"Hernando","sequence":"additional","affiliation":[]},{"given":"J.R.","family":"Casas","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1999.784637"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990517"},{"key":"17","first-page":"3","article-title":"Multi-speaker DOA tracking using interactive multiple models and probabilistic data association","author":"potamitis","year":"2003","journal-title":"Proc European Conference on Speech Communication and Technology"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1109\/83.841934"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1121\/1.4778220"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1109\/89.568735"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.804546"},{"key":"14","first-page":"1381","article-title":"On the decollation of filter-bank energies in speech recognition","volume":"2","author":"nadeu","year":"1995","journal-title":"Proc European Speech Processing Conference"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013200319198"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1002\/0471660264"},{"key":"21","first-page":"354","article-title":"Acoustic event detection: SVM-based system and evaluation setup in CLEAR'07","volume":"4625","author":"temko","year":"2007","journal-title":"Classification of Events Activities and Relationships (CLEAR) Evaluation and Workshop"},{"key":"3","first-page":"3","author":"brandstein","year":"1995","journal-title":"A framework for speech source localization using sensor arrays"},{"journal-title":"Acoustic Event Detection and Classification","year":"2007","author":"temko","key":"20"},{"key":"2","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/34.910878","article-title":"The recognition of human movement using temporal templates","volume":"23","author":"bobick","year":"1999","journal-title":"IEEE Trans on Pattern Analysis and Machine Intelligence"},{"year":"2004","key":"1","first-page":"1"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/WIAMIS.2007.31"},{"key":"7","first-page":"5","article-title":"Real-time lip tracking and bi-modal continuous speech recognition","author":"chan","year":"1998","journal-title":"Proc IEEE Workshop on Multimedia Signal Processing"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2008.4712337"},{"key":"5","first-page":"1","article-title":"Fusion of audio and video modalities for detection of acoustic events","author":"butko","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"4","first-page":"1","author":"bregman","year":"1990","journal-title":"Auditory Scene Analysis"},{"key":"9","first-page":"3","author":"dibiase","year":"2001","journal-title":"Microphone Arrays Robust Localization in Reverberant Rooms"},{"key":"8","first-page":"53","article-title":"An adaptive blind SIMO identification approach to joint multichannel time delay estimation","volume":"4","author":"chen","year":"2004","journal-title":"Proc IEEE Int Conf on Acoustics Speech and Signal Processing"}],"event":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","start":{"date-parts":[[2009,6,20]]},"location":"Miami, FL","end":{"date-parts":[[2009,6,25]]}},"container-title":["2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5191364\/5204041\/05204264.pdf?arnumber=5204264","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,17]],"date-time":"2019-09-17T02:24:21Z","timestamp":1568687061000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/5204264\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,6]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/cvprw.2009.5204264","relation":{},"subject":[],"published":{"date-parts":[[2009,6]]}}}