{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:21:59Z","timestamp":1792786919430,"version":"4.5.0"},"reference-count":131,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"New Generation Artificial Intelligence-National Science and Technology","award":["2025ZD0123100"],"award-info":[{"award-number":["2025ZD0123100"]}]},{"name":"NSFC","award":["92470202"],"award-info":[{"award-number":["92470202"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"National Key Research and Development Program of China","award":["2023YFA1008503"],"award-info":[{"award-number":["2023YFA1008503"]}]},{"name":"Guangdong NSF Project","award":["2023B1515040025"],"award-info":[{"award-number":["2023B1515040025"]}]},{"name":"Guangdong Key Research and Development Program","award":["2024B0101040004"],"award-info":[{"award-number":["2024B0101040004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tpami.2026.3704589","type":"journal-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T19:43:43Z","timestamp":1781639023000},"page":"13026-13043","source":"Crossref","is-referenced-by-count":0,"title":["XOV-Action: Toward Generalizable Open-Vocabulary Action Recognition"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0013-3730","authenticated-orcid":false,"given":"Kun-Yu","family":"Lin","sequence":"first","affiliation":[{"name":"Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4868-6526","authenticated-orcid":false,"given":"Henghui","family":"Ding","sequence":"additional","affiliation":[{"name":"Fudan University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4678-3716","authenticated-orcid":false,"given":"Jia-Run","family":"Du","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4760-9708","authenticated-orcid":false,"given":"Jiaming","family":"Zhou","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou)","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4248-9820","authenticated-orcid":false,"given":"Yi-Xing","family":"Peng","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5472-0079","authenticated-orcid":false,"given":"Yu-Ming","family":"Tang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhilin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5345-1591","authenticated-orcid":false,"given":"Chen Change","family":"Loy","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"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":"Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01594-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3183112"},{"key":"ref3","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref4","article-title":"ActionCLIP: A new paradigm for video action recognition","author":"Wang","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25386"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00633"},{"key":"ref9","first-page":"36978","article-title":"Open-VCLIP: Transforming CLIP to an open-vocabulary video model via interpolated weight optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Weng","year":"2023"},{"key":"ref10","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Simonyan","year":"2014"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00642"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3116945"},{"key":"ref17","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref19","article-title":"ARID: A comprehensive study on recognizing actions in the dark and a new benchmark dataset","author":"Xu","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093511"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1759"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.103"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"ref24","first-page":"853","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Choi","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_40"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01163"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01823"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00940"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_21"},{"key":"ref30","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky","year":"2012"},{"key":"ref31","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref34","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutskever","year":"2014"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00887"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02588"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6872"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00118"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref46","article-title":"V4D: 4D convolutional neural networks for video-level representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2020"},{"key":"ref47","article-title":"CT-Net: Channel tensorization network for video classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475272"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01332"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3302471"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01248"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_23"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00640"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01281"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01755"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00933"},{"key":"ref60","article-title":"FROSTER: Frozen CLIP is a strong teacher for open-vocabulary action recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Huang","year":"2024"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00634"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612490"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28361"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01768"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01751"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_5"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995353"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.282"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.521"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10466"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10605-2_38"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1027-5"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01338"},{"key":"ref74","article-title":"ActionHub: A large-scale action video description dataset for zero-shot action recognition","author":"Zhou","year":"2024"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2016.01.001"},{"key":"ref76","first-page":"264","article-title":"Deep domain adaptation in action space","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Jamal","year":"2018"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00920"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2880750"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_9"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3429387"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6854"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3212909"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413897"},{"key":"ref84","first-page":"23386","article-title":"Contrast and mix: Temporal contrastive video domain adaptation with background mixing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sahoo","year":"2021"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00020"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00966"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01336"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01431"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01342"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00024"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2443"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01256"},{"key":"ref93","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref96","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021"},{"key":"ref97","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/762"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref100","first-page":"1","article-title":"DINOv2: Learning robust visual features without supervision","volume":"2024","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01049"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1919"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3361862"},{"key":"ref107","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu","year":"2022"},{"key":"ref108","article-title":"Language-driven semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2022"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01396"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02206"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0412"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01428"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01427"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01034"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01332"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28202"},{"key":"ref119","article-title":"Qwen2.5-VL technical report","author":"Bai","year":"2025"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"ref121","article-title":"Foundation models for video understanding: A survey","author":"Madan","year":"2024"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref123","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68279-0_2"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3234307"},{"key":"ref126","first-page":"97","article-title":"Learning transferable features with deep adaptation networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Long","year":"2015"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_35"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00467"},{"key":"ref129","first-page":"876","article-title":"Averaging weights leads to wider optima and better generalization","volume-title":"Proc. 34th Conf. Uncertainty Artif. Intell.","author":"Izmailov","year":"2018"},{"key":"ref130","article-title":"AIM: Adapting image models for efficient video action recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang","year":"2023"},{"issue":"11","key":"ref131","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/11674301\/11568850-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11674301\/11568850.pdf?arnumber=11568850","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T15:36:33Z","timestamp":1790264193000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11568850\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":131,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3704589","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]}}}