{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:56:03Z","timestamp":1771613763457,"version":"3.50.1"},"reference-count":18,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2018,4,1]],"date-time":"2018-04-01T00:00:00Z","timestamp":1522540800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2018,4,1]],"date-time":"2018-04-01T00:00:00Z","timestamp":1522540800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2018,4,1]],"date-time":"2018-04-01T00:00:00Z","timestamp":1522540800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE MultiMedia"],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/mmul.2018.023121161","type":"journal-article","created":{"date-parts":[[2018,8,3]],"date-time":"2018-08-03T19:59:50Z","timestamp":1533326390000},"page":"11-23","source":"Crossref","is-referenced-by-count":11,"title":["A Crossmodal Approach to Multimodal Fusion in Video Hyperlinking"],"prefix":"10.1109","volume":"25","author":[{"given":"Vedran","family":"Vukotic","sequence":"first","affiliation":[{"name":"INRIA\/IRISA Rennes and INSA Rennes"}]},{"given":"Christian","family":"Raymond","sequence":"additional","affiliation":[{"name":"INRIA\/IRISA Rennes and INSA Rennes"}]},{"given":"Guillaume","family":"Gravier","sequence":"additional","affiliation":[{"name":"INRIA\/IRISA Rennes and CNRS"}]}],"member":"263","reference":[{"key":"ref10","article-title":"HITS and IRISA at MediaEval 2013: Search and Hyperlinking Task","author":"guinaudeau","year":"2013","journal-title":"Working Notes Proc of the MediaEval 2013 Workshop"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912064"},{"key":"ref12","article-title":"The Search and Hyperlinking Task at MediaEval2014","author":"eskevich","year":"0","journal-title":"Working Notes Proceedings of the Mediaeval 2014 Workshop"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-37444-9_34"},{"key":"ref14","article-title":"TRECVID 2014—An Overview of the Goals, Tasks, Data, Evaluation Mechanisms, and Metrics","author":"over","year":"0","journal-title":"Proceedings of TRECVID 2014"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-85287-2_2"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2983563.2983567"},{"key":"ref17","first-page":"249","article-title":"Understanding the Difficulty of Training Deep Feedforward Neural Networks","author":"glorot","year":"0","journal-title":"Proc 13th Intl Conf Artificial Intelligence and Statistics (AISTATS 10)"},{"key":"ref18","article-title":"TRECVID 2016: Evaluating Video Search, Video Event Detection, Localization, and Hyperlinking","author":"awad","year":"0","journal-title":"Proceedings of TRECVID 2016"},{"key":"ref4","article-title":"IRISA at TRECVid 2017: Beyond Crossmodal and Multimodal Models for Video Hyperlinking","author":"demirdelen","year":"0","journal-title":"Working Notes of the TRECVid 2017 Workshop"},{"key":"ref3","article-title":"Trecvid 2017: Evaluating Ad-hoc and Instance Video Search, Events Detection, Video Captioning, and Hyperlinking","author":"awad","year":"0","journal-title":"Proceedings of TRECVID 2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24033-6_29"},{"key":"ref8","article-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","author":"simonyan","year":"0","journal-title":"Proc Int'l Conf Learning Representations (ICLR 15)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654902"},{"key":"ref1","first-page":"689","article-title":"Multimodal Deep Learning","author":"ngiam","year":"0","journal-title":"Proc 28th Int Conf Mach Learn (ICML-11)"},{"key":"ref9","article-title":"Audio-visual Integration in Multimodal Communication","volume":"86","author":"chen","year":"0","journal-title":"Proc IEEE"}],"container-title":["IEEE MultiMedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/93\/8424760\/08424826.pdf?arnumber=8424826","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,3]],"date-time":"2022-05-03T20:03:25Z","timestamp":1651608205000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8424826\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":18,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/mmul.2018.023121161","relation":{},"ISSN":["1070-986X","1941-0166"],"issn-type":[{"value":"1070-986X","type":"print"},{"value":"1941-0166","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,4]]}}}