{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:49:09Z","timestamp":1777654149409,"version":"3.51.4"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[],"published-print":{"date-parts":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683898","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"3941-3945","source":"Crossref","is-referenced-by-count":33,"title":["Dense Multimodal Fusion for Hierarchically Joint Representation"],"prefix":"10.1109","author":[{"given":"Di","family":"Hu","sequence":"first","affiliation":[{"name":"School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi’an, Shaanxi, 710072, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengze","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi’an, Shaanxi, 710072, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feiping","family":"Nie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi’an, Shaanxi, 710072, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi’an, Shaanxi, 710072, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654902"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993176"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2738401"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref14","first-page":"190","article-title":"Speaker-independent machine lip-reading with speaker-dependent viseme classifiers","author":"bear","year":"2015","journal-title":"AVSPN"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639140"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2014.6836053"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.538"},{"key":"ref18","first-page":"179","article-title":"The challenge of multispeaker lipreading","author":"cox","year":"2008","journal-title":"AVSPN"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"ref4","first-page":"2222","article-title":"Multi-modal learning with deep boltzmann machines","author":"srivastava","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref3","first-page":"23","article-title":"Audio-visual automatic speech recognition: An overview","volume":"22","author":"potamianos","year":"2004","journal-title":"Issues in Audio-visual Speech Processing"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijar.2008.11.006"},{"key":"ref5","article-title":"A comprehensive survey on cross-modal retrieval","author":"wang","year":"2016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101236"},{"key":"ref7","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.389"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2057231"},{"key":"ref1","first-page":"2141","article-title":"Improved multimodal deep learning with variation of information","author":"sohn","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2607421"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.261"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, UK","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683898.pdf?arnumber=8683898","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:18:54Z","timestamp":1755800334000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683898\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683898","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}