{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T15:10:55Z","timestamp":1781622655175,"version":"3.54.5"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62236003"],"award-info":[{"award-number":["62236003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376137"],"award-info":[{"award-number":["62376137"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3385180","type":"journal-article","created":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T19:38:56Z","timestamp":1712691536000},"page":"9036-9046","source":"Crossref","is-referenced-by-count":23,"title":["Muti-Modal Emotion Recognition via Hierarchical Knowledge Distillation"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0932-8910","authenticated-orcid":false,"given":"Teng","family":"Sun","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Shandong University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1791-3159","authenticated-orcid":false,"given":"Yinwei","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7070-8137","authenticated-orcid":false,"given":"Juntong","family":"Ni","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Shandong University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4258-6775","authenticated-orcid":false,"given":"Zixin","family":"Liu","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5274-4197","authenticated-orcid":false,"given":"Xuemeng","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Shandong University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2197-9038","authenticated-orcid":false,"given":"Yaowei","family":"Wang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Multi-modal emotion recognition on IEMOCAP dataset using deep learning","author":"Tripathi","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3475872"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.417"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3032037"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2934824"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548211"},{"key":"ref9","first-page":"10944","article-title":"What makes multi-modal learning better than single (provably)","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Huang","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3035277"},{"key":"ref11","first-page":"1","article-title":"Albert: A lite BERT for self-supervised learning of language representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lan","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413690"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.02.003"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11280"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"ref16","first-page":"1","article-title":"Learning factorized multimodal representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tsai","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref20","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5772\/54002"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20221"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01050"},{"issue":"7","key":"ref27","first-page":"38","article-title":"Distilling the knowledge in a neural network","volume":"14","author":"Hinton","year":"2015","journal-title":"Comput. Sci."},{"key":"ref28","first-page":"1","article-title":"Transferring knowledge to smaller network with class-distance loss","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim","year":"2017"},{"key":"ref29","first-page":"742","article-title":"Learning efficient object detection models with knowledge distillation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Chen","year":"2017"},{"key":"ref30","first-page":"1","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zagoruyko","year":"2017"},{"key":"ref31","first-page":"1","article-title":"FitNets: Hints for thin deep nets","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Romero","year":"2015"},{"key":"ref32","first-page":"6373","article-title":"Matching structure for dual learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fei","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref34","first-page":"1","article-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2923608"},{"key":"ref37","article-title":"Deep learning using rectified linear units (ReLu)","author":"Agarap","year":"2018"},{"key":"ref38","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475665"},{"key":"ref40","article-title":"MOSI: Multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos","author":"Zadeh","year":"2016"},{"key":"ref41","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Glorot","year":"2010"},{"key":"ref42","first-page":"1","article-title":"ADAM: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3302"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3309"},{"key":"ref46","article-title":"Improving multi-modal learning with uni-modal teachers","author":"Du","year":"2021"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10491325.pdf?arnumber=10491325","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T04:14:19Z","timestamp":1725164059000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10491325\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3385180","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}