{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T12:01:40Z","timestamp":1774699300420,"version":"3.50.1"},"reference-count":49,"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\/501100001459","name":"Ministry of Education - Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Academic Research Fund Tier 1","award":["RG73\/21"],"award-info":[{"award-number":["RG73\/21"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2023.3252270","type":"journal-article","created":{"date-parts":[[2023,3,3]],"date-time":"2023-03-03T18:24:32Z","timestamp":1677867872000},"page":"9437-9448","source":"Crossref","is-referenced-by-count":10,"title":["Pace-Adaptive and Noise-Resistant Contrastive Learning for Multimodal Feature Fusion"],"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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6262-8125","authenticated-orcid":false,"given":"Alex","family":"Kot","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9728-9511","authenticated-orcid":false,"given":"Adams Wai-Kin","family":"Kong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2738401"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987728"},{"key":"ref4","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref6","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Khosla","year":"2020"},{"key":"ref7","first-page":"4182","article-title":"Data-efficient image recognition with contrastive predictive coding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Henaff","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.72"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref11","first-page":"642","article-title":"Unilmv2: Pseudo-masked language models for unified language model pre-training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bao","year":"2020"},{"key":"ref12","first-page":"8765","article-title":"Debiased contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chuang","year":"2020,"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref15","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref17","first-page":"25","article-title":"Self-supervised multimodal versatile networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Alayrac","year":"2020,"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01091"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1239"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3031549"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00079"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00186"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01617"},{"key":"ref24","first-page":"1","article-title":"Understanding dimensional collapse in contrastive self-supervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jing","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref27","first-page":"4835","article-title":"Deep multimodal fusion by channel exchanging","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wang","year":"2020,"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01014"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref32","first-page":"9929","article-title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref34","first-page":"5628","article-title":"A theoretical analysis of contrastive unsupervised representation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Saunshi","year":"2019"},{"key":"ref35","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist., JMLR Workshop Conf. Proc.","author":"Gutmann","year":"2010"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.23919\/FUSION45008.2020.9190246"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref38","first-page":"14200","article-title":"Attention bottlenecks for multimodal fusion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Nagrani","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref40","first-page":"1","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani","year":"2017,"},{"key":"ref41","article-title":"Heated-up softmax embedding","author":"Zhang","year":"2018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2822810"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10894"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref46","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Kenton","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/wacv.2016.7477553"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2014.6853739"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/10058603.pdf?arnumber=10058603","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:51:15Z","timestamp":1705017075000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10058603\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3252270","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}