{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T21:23:06Z","timestamp":1772140986036,"version":"3.50.1"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2024YFB4709800"],"award-info":[{"award-number":["2024YFB4709800"]}]},{"name":"Guangdong S&T Program","award":["2024B0101050002"],"award-info":[{"award-number":["2024B0101050002"]}]},{"name":"Shenzhen Innovation in Science and Technology Foundation for the Excellent Youth Scholars","award":["RCYX20231211090248064"],"award-info":[{"award-number":["RCYX20231211090248064"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tpami.2025.3640697","type":"journal-article","created":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:37:55Z","timestamp":1764959875000},"page":"3726-3743","source":"Crossref","is-referenced-by-count":0,"title":["Heatmap Pooling Network for Action Recognition From RGB Videos"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6332-8316","authenticated-orcid":false,"given":"Mengyuan","family":"Liu","sequence":"first","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0994-9146","authenticated-orcid":false,"given":"Jinfu","family":"Liu","sequence":"additional","affiliation":[{"name":"Imaging Department, DJI Technology Company Ltd., Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2768-6159","authenticated-orcid":false,"given":"Yongkang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3193-6269","authenticated-orcid":false,"given":"Bin","family":"He","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.02.030"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3177813"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01736"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3157033"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.123061"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3077512"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3271811"},{"key":"ref13","article-title":"ActionCLIP: A new paradigm for video action recognition","author":"Wang","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3543034"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12366"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610217"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00127"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref20","article-title":"InternVideo: General video foundation models via generative and discriminative learning","author":"Wang","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00942"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00943"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_6"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00064"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3132734.3132739"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.339"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"ref30","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_5"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01330"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16430"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3466212"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3363831"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3325463"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.115"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref40","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3222784"},{"key":"ref45","first-page":"24327","article-title":"Heatmap distribution matching for human pose estimation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Qu","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3127885"},{"key":"ref47","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tong","year":"2022"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00338"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00333"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28290"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32894"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3552604"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01784"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02723"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00810"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_25"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_37"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.12.054"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547811"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611900"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160564"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW63481.2024.10645450"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00649"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2025.3568099"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3562877"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00092"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3169976"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01600"},{"key":"ref70","article-title":"What is YOLOv5: A deep look into the internal features of the popular object detector","author":"Khanam","year":"2024"},{"key":"ref71","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref72","article-title":"Generalized fisher score for feature selection","author":"Gu","year":"2012"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00958"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3378886"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11372200\/11278750.pdf?arnumber=11278750","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:44:20Z","timestamp":1772138660000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11278750\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":77,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3640697","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":[[2026,3]]}}}