{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:22:25Z","timestamp":1772907745673,"version":"3.50.1"},"reference-count":60,"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":["62072076"],"award-info":[{"award-number":["62072076"]}],"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":["62372087"],"award-info":[{"award-number":["62372087"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Sichuan, China","award":["2022NSFSC0500"],"award-info":[{"award-number":["2022NSFSC0500"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3312856","type":"journal-article","created":{"date-parts":[[2023,9,7]],"date-time":"2023-09-07T17:36:07Z","timestamp":1694108167000},"page":"3491-3504","source":"Crossref","is-referenced-by-count":13,"title":["Audio-Visual Contrastive and Consistency Learning for Semi-Supervised Action Recognition"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2815-7993","authenticated-orcid":false,"given":"Maregu","family":"Assefa","sequence":"first","affiliation":[{"name":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6181-3900","authenticated-orcid":false,"given":"Wei","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0214-7124","authenticated-orcid":false,"given":"Jinyu","family":"Zhan","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6458-1882","authenticated-orcid":false,"given":"Kumie","family":"Gedamu","sequence":"additional","affiliation":[{"name":"Sichuan Artificial Intelligence Research Institute, Sichuan and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5577-3201","authenticated-orcid":false,"given":"Getinet","family":"Yilma","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Adama Science and Technology University, Adama, Ethiopia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6398-6060","authenticated-orcid":false,"given":"Melese","family":"Ayalew","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3768-0666","authenticated-orcid":false,"given":"Deepak","family":"Adhikari","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref3","first-page":"1","article-title":"A short note on the kinetics-700 human action dataset","author":"Carreira","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1142\/S0218126622501596"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00156"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00934"},{"key":"ref13","first-page":"1","article-title":"Mixmatch: A holistic approach to semi-supervised learning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Berthelot","year":"2019"},{"key":"ref14","first-page":"596","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Sohn","year":"2020"},{"key":"ref15","first-page":"1","article-title":"RemixMatch: Semi-supervised learning with distribution matching and augmentation anchoring","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Berthelot","year":"2020"},{"key":"ref16","first-page":"1","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","volume-title":"Proc. Workshop Challenges Representation Learn.","author":"Lee","year":"2013"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01025"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00325"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00712"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00297"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3210271"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207304"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01229"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3230785"},{"key":"ref25","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Xie","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01407"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00115"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI56018.2022.00102"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3168137"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095478"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3267178"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3265261"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01163"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01105"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3193559"},{"key":"ref39","first-page":"7025","article-title":"Contrastive learning of global and local video representations","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Ma","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00658"},{"key":"ref41","first-page":"5679","article-title":"Self-supervised co-training for video representation learning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Han","year":"2020"},{"key":"ref42","first-page":"1","article-title":"Active contrastive learning of audio-visual video representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma","year":"2021"},{"key":"ref43","first-page":"9758","article-title":"Self-supervised learning by cross-modal audio-video clustering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alwassel","year":"2020"},{"key":"ref44","first-page":"1","article-title":"Cooperative learning of audio and video models from self-supervised synchronization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Korbar","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00354"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108043"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWAMTIP53232.2021.9674096"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412863"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00333"},{"key":"ref51","first-page":"14200","article-title":"Attention bottlenecks for multimodal fusion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nagrani","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3180585"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref56","first-page":"478","article-title":"Unsupervised deep embedding for clustering analysis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xie","year":"2016"},{"key":"ref57","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Khosla","year":"2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10243145.pdf?arnumber=10243145","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T00:26:39Z","timestamp":1709339199000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10243145\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3312856","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}