{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T17:13:55Z","timestamp":1729617235083,"version":"3.28.0"},"reference-count":12,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1109\/icassp.2004.1326728","type":"proceedings-article","created":{"date-parts":[[2004,9,28]],"date-time":"2004-09-28T09:50:22Z","timestamp":1096365022000},"page":"iii-1048-51","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal video search techniques: late fusion of speech-based retrieval and visual content-based retrieval"],"prefix":"10.1109","volume":"3","author":[{"given":"A.","family":"Amir","sequence":"first","affiliation":[]},{"given":"G.","family":"Iyengar","sequence":"additional","affiliation":[]},{"given":"C.-Y.","family":"Lin","sequence":"additional","affiliation":[]},{"given":"M.","family":"Naphade","sequence":"additional","affiliation":[]},{"given":"A.","family":"Natsev","sequence":"additional","affiliation":[]},{"given":"C.","family":"Neti","sequence":"additional","affiliation":[]},{"given":"H.J.","family":"Nock","sequence":"additional","affiliation":[]},{"given":"J.R.","family":"Smith","sequence":"additional","affiliation":[]},{"given":"B.","family":"Tseng","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"3","article-title":"The TREC-2001 video track: Information retrieval on digital video information","author":"smeaton","year":"2002","journal-title":"Proc of ECDL 2002"},{"key":"2","article-title":"The TREC-2002 video track report","author":"smeaton","year":"2002","journal-title":"Proc of TREC 2002"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(01)00061-9"},{"key":"1","article-title":"Automatic recognition of audio-visual speech: Recent progress and challenges","volume":"91","author":"potamianos","year":"2003","journal-title":"Proc IEEE"},{"key":"7","article-title":"Videoal: A novel end-to-end mpeg-7 video automatic labeling system","author":"lin","year":"2003","journal-title":"Proc Int Conf Image Processing"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2003.1220948"},{"key":"5","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1155\/S1110865703211173","article-title":"Semantic indexing of multimedia content using visual, audio and text cues","volume":"2","author":"adams","year":"2003","journal-title":"EURASIP Journal on Applied Signal Processing"},{"key":"4","article-title":"IBM Research TREC-2002 video retrieval system","volume":"sp500 251","author":"adams","year":"2003","journal-title":"Proc The Eleventh Text Retrieval Conference"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2003.1220950"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2003.1221649"},{"key":"11","first-page":"109","article-title":"Okapi at trec-3","author":"robertson","year":"1995","journal-title":"Proceedings of the third Text Retrieval Conference (TREC-3)"},{"journal-title":"TRECVID Workshop Notebook Papers","year":"2003","key":"12"}],"event":{"name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","acronym":"ICASSP-04","location":"Montreal, Que., Canada"},"container-title":["2004 IEEE International Conference on Acoustics, Speech, and Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/9248\/29345\/01326728.pdf?arnumber=1326728","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,16]],"date-time":"2017-06-16T06:26:07Z","timestamp":1497594367000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/1326728\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":12,"URL":"https:\/\/doi.org\/10.1109\/icassp.2004.1326728","relation":{},"subject":[]}}