{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:41:48Z","timestamp":1791913308622,"version":"4.3.4"},"reference-count":69,"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":"NSFC","doi-asserted-by":"publisher","award":["U21A20471"],"award-info":[{"award-number":["U21A20471"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["U1911401"],"award-info":[{"award-number":["U1911401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong NSF Project","award":["2023B1515040025"],"award-info":[{"award-number":["2023B1515040025"]}]},{"name":"Guangdong NSF Project","award":["2020B1515120085"],"award-info":[{"award-number":["2020B1515120085"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2024.3362135","type":"journal-article","created":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T20:23:38Z","timestamp":1708374218000},"page":"1600-1613","source":"Crossref","is-referenced-by-count":57,"title":["Multimodal Action Quality Assessment"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8125-8024","authenticated-orcid":false,"given":"Ling-An","family":"Zeng","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Sun Yat-sen University, Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8327-0003","authenticated-orcid":false,"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413560"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_36"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00323"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.16"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2927118"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00986"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00643"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_14"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00782"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00940"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506257"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00044"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126534"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3143549"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_25"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00296"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-018-1704-z"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00634"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00805"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00539"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_7"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref23","article-title":"Audiovisual SlowFast networks for video recognition","author":"Xiao","year":"2020","journal-title":"arXiv:2001.08740"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01342"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01957"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00139"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref29","first-page":"1","article-title":"Cross-attentional audio-visual fusion for weakly-supervised action localization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lee"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01936"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01029"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2980956"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3137988"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746660"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1814"},{"key":"ref37","article-title":"Contrastive learning of global-local video representations","author":"Ma","year":"2021","journal-title":"arXiv:2104.05418"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_18"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00802"},{"key":"ref40","article-title":"MSAF: Multimodal split attention fusion","author":"Su","year":"2020","journal-title":"arXiv:2012.07175"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00305"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_21"},{"key":"ref43","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2016","journal-title":"arXiv:1611.01144"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475438"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref47","volume-title":"Statistical Theory of Extreme Values and Some Practical","volume":"33","author":"Gumbel","year":"1954"},{"key":"ref48","first-page":"3086","article-title":"A* sampling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Maddison"},{"key":"ref49","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref51","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Paszke","year":"2019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-698"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref57","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref58","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096513"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00748"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.526"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.114"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_51"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00135"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_18"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00308"},{"key":"ref69","first-page":"709","article-title":"Probing visual-audio representation for video highlight detection via hard-pairs guided contrastive learning","volume-title":"Proc. 33rd Brit. Mach. Vis. Conf. (BMVC)","author":"Li"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/10346232\/10440264.pdf?arnumber=10440264","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T03:35:55Z","timestamp":1709264155000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10440264\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3362135","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}