{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T00:59:18Z","timestamp":1759798758317,"version":"build-2065373602"},"reference-count":145,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"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","award":["62206153","62321005","62336004","62125603"],"award-info":[{"award-number":["62206153","62321005","62336004","62125603"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Key Laboratory of next generation interactive media innovative technology","award":["ZDSYS20210623092001004"],"award-info":[{"award-number":["ZDSYS20210623092001004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tpami.2025.3590012","type":"journal-article","created":{"date-parts":[[2025,7,17]],"date-time":"2025-07-17T17:59:08Z","timestamp":1752775148000},"page":"9731-9748","source":"Crossref","is-referenced-by-count":0,"title":["FLAG3D++: A Benchmark for 3D Fitness Activity Comprehension With Language Instruction"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1534-4549","authenticated-orcid":false,"given":"Yansong","family":"Tang","sequence":"first","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9824-7287","authenticated-orcid":false,"given":"Aoyang","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8689-8248","authenticated-orcid":false,"given":"Jinpeng","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1465-3739","authenticated-orcid":false,"given":"Wenxun","family":"Dai","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7701-234X","authenticated-orcid":false,"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0403-1923","authenticated-orcid":false,"given":"Xiu","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6121-5529","authenticated-orcid":false,"given":"Jiwen","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00979"},{"key":"ref2","first-page":"64331","article-title":"ProteinGym: Large-scale benchmarks for protein fitness prediction and design","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Notin"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2971576"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1249\/FIT.0000000000000836"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5040\/9781718220966"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.10.018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.396"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01232"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26316-3_12"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00527"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00075"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01843"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01040"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00161"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00039"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00238"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00296"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_2"},{"key":"ref25","article-title":"Vicon"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/s17071591"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106414"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00064"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00201"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02027"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_30"},{"article-title":"Openmmlab\u2019s next generation video understanding toolbox and benchmark","year":"2020","author":"Contributors","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548546"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00542"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.381"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00894"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_33"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"article-title":"A large-scale varying-view RGB-D action dataset for arbitrary-view human action recognition","year":"2019","author":"Ji","key":"ref49"},{"key":"ref50","first-page":"25268","article-title":"Motion-X: A large-scale 3D expressive whole-body human motion dataset","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3328180"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02117"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01745"},{"article-title":"RedCaps: Web-curated image-text data created by the people, for the people","year":"2021","author":"Desai","key":"ref57"},{"article-title":"WanJuan: A comprehensive multimodal dataset for advancing english and Chinese large models","year":"2023","author":"He","key":"ref58"},{"article-title":"OpenDataLab: Empowering general artificial intelligence with open datasets","year":"2022","author":"He","key":"ref59"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref61","first-page":"23634","article-title":"MERLOT: Multimodal neural script knowledge models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zellers"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01589"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00498"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref65","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Schuhmann"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463257"},{"article-title":"InternVid: A large-scale video-text dataset for multimodal understanding and generation","year":"2023","author":"Wang","key":"ref67"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01744"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3487242"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587509"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/0031-3203(94)90079-5"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1042"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/34.868681"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.188"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2008.4760949"},{"key":"ref77","first-page":"650","article-title":"Periodicity detection of local motion","volume-title":"Proc. Int. Conf. Multimedia Expo","author":"Tong"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CISP.2011.6099930"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2012.6311341"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00939"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00782"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413560"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_25"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.16"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_36"},{"article-title":"FSD-10: A dataset for competitive sports content analysis","year":"2020","author":"Liu","key":"ref86"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.239"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref89","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Simonyan"},{"article-title":"Audiovisual slowfast networks for video recognition","year":"2020","author":"Xiao","key":"ref90"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298714"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298186"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.233"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00734"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00811"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00371"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00558"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.288"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00742"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00062"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01049"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01761-6"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_36"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00622"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_34"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00551"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01114"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01094"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00200"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00576"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00545"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_19"},{"key":"ref119","first-page":"27940","article-title":"Garment4D: Garment reconstruction from point cloud sequences","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hong"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00229"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.500"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00744"},{"key":"ref123","first-page":"5236","article-title":"Self-supervised learning of motion capture","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tung"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0273-6"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.492"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3450537"},{"key":"ref127","first-page":"26034","article-title":"Benchmarking and analyzing 3D human pose and shape estimation beyond algorithms","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Pang"},{"key":"ref128","article-title":"Unity3D"},{"key":"ref129","article-title":"Unity asset store"},{"key":"ref130","article-title":"Renderpeople"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1007\/BF01589116"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1137\/1011036"},{"article-title":"PoseRAC: Pose saliency transformer for repetitive action counting","year":"2023","author":"Yao","key":"ref133"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2009.5354766"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0908-6_22"},{"article-title":"IVAC-P2L: Enhancing video action counting through irregular repetition priors","year":"2024","author":"Wang","key":"ref136"},{"article-title":"Efficient action counting with dynamic queries","year":"2024","author":"Li","key":"ref137"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123760"},{"key":"ref139","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref140"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475438"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01386"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01126"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01289"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11192800\/11082527.pdf?arnumber=11082527","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:37:24Z","timestamp":1759772244000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11082527\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":145,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3590012","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}