{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T14:38:27Z","timestamp":1784212707132,"version":"3.55.0"},"reference-count":57,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076262"],"award-info":[{"award-number":["62076262"]}],"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":[[2023]]},"DOI":"10.1109\/tmm.2022.3171679","type":"journal-article","created":{"date-parts":[[2022,5,3]],"date-time":"2022-05-03T20:02:18Z","timestamp":1651608138000},"page":"4121-4134","source":"Crossref","is-referenced-by-count":150,"title":["Multimodal Information Bottleneck: Learning Minimal Sufficient Unimodal and Multimodal Representations"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9763-375X","authenticated-orcid":false,"given":"Sijie","family":"Mai","sequence":"first","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4884-323X","authenticated-orcid":false,"given":"Haifeng","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0055"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_35"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.02.003"},{"key":"ref56","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2013.34"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2482228"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3082398"},{"key":"ref55","first-page":"269","article-title":"Modality-transferable emotion embeddings for low-resource multimodal emotion recognition","author":"dai","year":"0","journal-title":"Proc AACL-IJCNLP"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2716835"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475585"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1109\/T-AFFC.2010.16","article-title":"Emotion recognition of affective speech based on multiple classifiers using acoustic-prosodic information and semantic labels","volume":"2","author":"wu","year":"2011","journal-title":"IEEE Trans Affect Comput"},{"key":"ref16","first-page":"1","article-title":"Ensemble of SVM trees for multimodal emotion recognition","author":"rozgic","year":"0","journal-title":"Proc Signal Inf Process Assoc Summit Conf"},{"key":"ref19","first-page":"606","article-title":"Investigating audio, visual, and text fusion methods for end-to-end automatic personality prediction","author":"kampman","year":"0","journal-title":"Proc Assoc Comput Linguistics"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993176"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611975673.5"},{"key":"ref45","article-title":"Predicting the popularity of micro-videos with multimodal variational encoder-decoder framework","author":"zhu","year":"2020"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.17763\/haer.47.3.8840364413869005"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00769"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"ref41","article-title":"Learning robust representations via multi-view information bottleneck","author":"federici","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref44","first-page":"1513","article-title":"A variational information bottleneck approach to multi-omics data integration","author":"lee","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref43","first-page":"5580","article-title":"Multimodal generative models for scalable weakly-supervised learning","author":"wu","year":"2018","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/S0927-0507(03)10006-0"},{"key":"ref8","first-page":"368","article-title":"The information bottleneck method","author":"tishby","year":"1999","journal-title":"Proc 37th Annu Allerton Conf Commun Control Comput"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1046"},{"key":"ref9","article-title":"Deep variational information bottleneck","author":"alemi","year":"2017","journal-title":"Proc Int Conf Learn Representation"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3068598"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref5","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref40","first-page":"9908","article-title":"Learning efficient multi-agent communication: An information bottleneck approach","author":"wang","year":"0","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"ref34","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc North Amer Chapter Assoc Comput Linguistics Hum Lang Technol -HLT"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413690"},{"key":"ref36","first-page":"1","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","author":"yang","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.143"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.08.006"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1014"},{"key":"ref39","article-title":"InfoBot: Transfer and exploration via the information bottleneck","author":"goyal","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref38","article-title":"Variational discriminator bottleneck: Improving imitation learning, inverse RL, and GANS by constraining information flow","author":"peng","year":"2019","journal-title":"Proc Int Conf Learn Representation"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2925966"},{"key":"ref26","first-page":"2236","article-title":"Multimodal language analysis in the wild: Cmu-mosei dataset and interpretable dynamic fusion graph","author":"zadeh","year":"0","journal-title":"Proc Assoc Comput Linguistics"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5347"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1152"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1034"},{"key":"ref27","article-title":"Analyzing unaligned multimodal sequence via graph convolution and graph pooling fusion","author":"mai","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.challengehml-1.3"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09767641.pdf?arnumber=9767641","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T19:45:40Z","timestamp":1699299940000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9767641\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3171679","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}