{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T05:03:27Z","timestamp":1768280607243,"version":"3.49.0"},"reference-count":92,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2025ZD0121800"],"award-info":[{"award-number":["2025ZD0121800"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council (ARC) Discovery Project","doi-asserted-by":"publisher","award":["DP210102674"],"award-info":[{"award-number":["DP210102674"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tnnls.2025.3602089","type":"journal-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T17:38:03Z","timestamp":1758303483000},"page":"176-190","source":"Crossref","is-referenced-by-count":0,"title":["Toward an Effective Action-Region Tracking Framework for Fine-Grained Video Action Recognition"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2861-4288","authenticated-orcid":false,"given":"Baoli","family":"Sun","sequence":"first","affiliation":[{"name":"DUT-RU International School of Information Science and Engineering, Dalian University of Technology, Dalian, China"}]},{"given":"Yihan","family":"Wang","sequence":"additional","affiliation":[{"name":"DUT-RU International School of Information Science and Engineering, Dalian University of Technology, Dalian, China"}]},{"given":"Xinzhu","family":"Ma","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5011-9726","authenticated-orcid":false,"given":"Zhihui","family":"Wang","sequence":"additional","affiliation":[{"name":"DUT-RU International School of Information Science and Engineering, Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4942-7019","authenticated-orcid":false,"given":"Kun","family":"Lu","sequence":"additional","affiliation":[{"name":"DUT-RU International School of Information Science and Engineering, Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8043-0312","authenticated-orcid":false,"given":"Zhiyong","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Sydney, Sydney, NSW, Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3297079"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3266452"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3252172"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00081"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3190367"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00446"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref12","article-title":"A short note on the Kinetics-700-2020 human action dataset","author":"Carreira","year":"2020","journal-title":"arXiv:2010.10864"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01261"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3282631"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00333"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_24"},{"key":"ref22","first-page":"13937","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Rao"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01082"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3633781"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612206"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00953"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3387127"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531950"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00103"},{"key":"ref33","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548046"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref39","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst., Annu. Conf. Neural Inf. Process. Syst.","volume":"27","author":"Simonyan"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093274"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105184"},{"key":"ref49","first-page":"5373","article-title":"UniFormerV2: Spatiotemporal learning by arming image ViTs with video UniFormer","volume-title":"Proc. IEEE\/CVF","author":"Li"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3493-7"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00651"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3218471"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25860"},{"key":"ref55","article-title":"Not all patches are what you need: Expediting vision transformers via token reorganizations","author":"Liang","year":"2022","journal-title":"arXiv:2202.07800"},{"key":"ref56","first-page":"12493","article-title":"Keeping your eye on the ball: Trajectory attention in video transformers","volume-title":"Proc. NeurIPS","author":"Patrick"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01739"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3377192"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-023-01457-4"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28001"},{"key":"ref61","first-page":"1","article-title":"Token merging: Your ViT but faster","volume-title":"Proc. ICLR","author":"Bolya"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref65","first-page":"21271","article-title":"Bootstrap your own latent\u2014A new approach to self-supervised learning","volume-title":"Proc. NeurIPS","author":"Grill"},{"key":"ref66","first-page":"3569","article-title":"Pixel-level cycle association: A new perspective for domain adaptive semantic segmentation","volume-title":"Proc. NeurIPS","author":"Kang"},{"key":"ref67","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. ICML","author":"Chen"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01641"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01105"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3141051"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01362"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3147032"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_23"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01432"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3331841"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25386"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00092"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"ref82","first-page":"1","article-title":"Human activity recognition with pose-driven attention to RGB","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Baradel"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2967577"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16430"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00333"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3127885"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00056"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3263288"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11339259\/11173836.pdf?arnumber=11173836","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:01:55Z","timestamp":1768255315000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11173836\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":92,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3602089","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}