{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T18:13:09Z","timestamp":1791310389845,"version":"4.3.1"},"reference-count":17,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,7]]},"DOI":"10.1109\/wiamis.2013.6616129","type":"proceedings-article","created":{"date-parts":[[2013,10,10]],"date-time":"2013-10-10T19:28:22Z","timestamp":1381433302000},"page":"1-4","source":"Crossref","is-referenced-by-count":7,"title":["Fusion methods for multi-modal indexing of web data"],"prefix":"10.1109","author":[{"given":"Usman","family":"Niaz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bernard","family":"Merialdo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33885-4_43"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30542-2_123"},{"key":"16","article-title":"Fusion of speech, faces and text for person identification in tv broadcast","author":"bredin","year":"2012","journal-title":"ECCV"},{"key":"13","article-title":"A comparison of score, rank and probability-based fusion methods for video shot retrieval","author":"mcdonald","year":"2005","journal-title":"CIVR"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1145\/1027527.1027661"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874062"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33885-4_40"},{"key":"3","author":"snoek","year":"2005","journal-title":"Early Versus Late Fusion in Semantic Video Analysis"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1023\/B:MTAP.0000046380.27575.a5"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-010-0182-0"},{"key":"10","first-page":"170","article-title":"Semantic indexing of multimedia content using visual, audio and text cues","volume":"2","author":"adams","year":"2003","journal-title":"EURASIP"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.879876"},{"key":"6","author":"law","year":"2012","journal-title":"Hybrid Pooling Fusion in the Bow Pipeline"},{"key":"5","article-title":"Multimodal semisupervised learning for image classification","author":"guillaumin","year":"2010","journal-title":"CVPR"},{"key":"4","author":"strat","year":"2012","journal-title":"Hierarchical Late Fusion for Concept Detection in Videos"},{"key":"9","article-title":"Tracking humans using multi-modal fusion","author":"zou","year":"2005","journal-title":"CVPR"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1145\/1991996.1992025"}],"event":{"name":"2013 14th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS)","location":"Paris, France","start":{"date-parts":[[2013,7,3]]},"end":{"date-parts":[[2013,7,5]]}},"container-title":["2013 14th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6589214\/6616118\/06616129.pdf?arnumber=6616129","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,22]],"date-time":"2017-03-22T13:48:49Z","timestamp":1490190529000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6616129\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,7]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/wiamis.2013.6616129","relation":{},"subject":[],"published":{"date-parts":[[2013,7]]}}}