{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T11:32:24Z","timestamp":1779363144070,"version":"3.51.4"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,8]]},"DOI":"10.1109\/icip49359.2023.10222383","type":"proceedings-article","created":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T17:58:31Z","timestamp":1694455111000},"page":"1000-1004","source":"Crossref","is-referenced-by-count":5,"title":["Self-Supervised Contrastive Learning for Audio-Visual Action Recognition"],"prefix":"10.1109","author":[{"given":"Yang","family":"Liu","sequence":"first","affiliation":[{"name":"Sun Yat-Sen University,School of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Tan","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University,School of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyuan","family":"Lan","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University,School of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1362-z"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3284038"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.79"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3147032"},{"key":"ref5","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statis","author":"Gutmann"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref7","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"ICML","author":"Chen"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.2985586"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"ref12","first-page":"4733","article-title":"Learning representations from audio-visual spatial alignment","author":"Morgado","year":"2020","journal-title":"NeurIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413869"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref16","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.617"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01058"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00658"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413694"},{"key":"ref23","first-page":"21271","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","volume-title":"NeurIPS","author":"Grill"},{"key":"ref24","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"ICML","author":"Zbontar"}],"event":{"name":"2023 IEEE International Conference on Image Processing (ICIP)","location":"Kuala Lumpur, Malaysia","start":{"date-parts":[[2023,10,8]]},"end":{"date-parts":[[2023,10,11]]}},"container-title":["2023 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10221937\/10221892\/10222383.pdf?arnumber=10222383","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T20:57:20Z","timestamp":1710363440000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10222383\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,8]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icip49359.2023.10222383","relation":{},"subject":[],"published":{"date-parts":[[2023,10,8]]}}}