{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T10:22:48Z","timestamp":1771064568855,"version":"3.50.1"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001475","name":"Nanyang Technological University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001475","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NTU Internal Funding - Accelerating Creativity and Excellence","award":["NTU--ACE2020-03"],"award-info":[{"award-number":["NTU--ACE2020-03"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3142448","type":"journal-article","created":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T20:31:00Z","timestamp":1642105860000},"page":"2085-2096","source":"Crossref","is-referenced-by-count":18,"title":["Deep Multimodal Sequence Fusion by Regularized Expressive Representation Distillation"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3427-8540","authenticated-orcid":false,"given":"Xiaobao","family":"Guo","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University Singapore, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9728-9511","authenticated-orcid":false,"given":"Adams Wai-Kin","family":"Kong","sequence":"additional","affiliation":[{"name":"Rapid-Rich Object Search (ROSE) Laboratory, Interdisciplinary Graduate Programme, Nanyang Technological University, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6262-8125","authenticated-orcid":false,"given":"Alex","family":"Kot","sequence":"additional","affiliation":[{"name":"Rapid-Rich Object Search (ROSE) Laboratory, Interdisciplinary Graduate Programme, Nanyang Technological University, Singapore, Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"ref3","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chap. Assoc. Comput. Linguistics: Human Language Technol.","author":"Devlin"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2860246"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682154"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-018-0548-3"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2020.2981446"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.2005.1571679"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101236"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2012.6248032"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1001"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2925966"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.challengehml-1.3"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5347"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3107990.3107993"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2916887"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref27","first-page":"473","article-title":"LSTM can solve hard long time lag problems","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"1","author":"Hochreiter","year":"1997"},{"key":"ref28","first-page":"1","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","volume-title":"Proc. Neural Inf. Process. Syst. Workshop Deep Learn.","author":"Chung","year":"2014"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_21"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1046"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1566"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2070481.2070509"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019301"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0055"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24571-8_47"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3143011"},{"key":"ref38","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"ref40","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representat.","author":"Dosovitskiy"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref43","first-page":"668--675","article-title":"The earth movers distance, multi-dimensional scaling, and color-based image retrieval","volume-title":"Proc. ARPA Image Understanding Workshop","volume":"661","author":"Rubner","year":"1997"},{"key":"ref44","first-page":"2292","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"26","author":"Cuturi","year":"2013"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1090\/gsm\/058"},{"key":"ref46","first-page":"82","article-title":"Mosi: Multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos","volume-title":"CoRR","volume":"abs\/1606.06259","author":"Zadeh","year":"2016"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.343"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6431"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.jretconser.2017.01.001"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1081"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017216"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09681296.pdf?arnumber=9681296","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:08:54Z","timestamp":1703030934000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9681296\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3142448","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}