{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:31:07Z","timestamp":1777656667466,"version":"3.51.4"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62176047"],"award-info":[{"award-number":["62176047"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Sichuan Science and Technology Program","award":["2022YFS0600"],"award-info":[{"award-number":["2022YFS0600"]}]},{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan Province","doi-asserted-by":"publisher","award":["2024NSFTD0041"],"award-info":[{"award-number":["2024NSFTD0041"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["ZYGX2021YGLH208"],"award-info":[{"award-number":["ZYGX2021YGLH208"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3543033","type":"journal-article","created":{"date-parts":[[2025,2,17]],"date-time":"2025-02-17T13:36:16Z","timestamp":1739799376000},"page":"5283-5295","source":"Crossref","is-referenced-by-count":6,"title":["Simultaneous Detection and Interaction Reasoning for Object-Centric Action Recognition"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5803-6691","authenticated-orcid":false,"given":"Xunsong","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengzhan","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1720-2199","authenticated-orcid":false,"given":"Yangcen","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0723-4016","authenticated-orcid":false,"given":"Lixin","family":"Duan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5559-8594","authenticated-orcid":false,"given":"Wen","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2862341"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref4","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Informat. Process. Syst.","volume":"27","author":"Simonyan","year":"2014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref9","first-page":"12493","article-title":"Keeping your eye on the ball: Trajectory attention in video transformers","volume":"34","author":"Patrick","year":"2021","journal-title":"Adv. Neural Informat. Process. Syst."},{"key":"ref10","first-page":"853","article-title":"Why can\u2019t i dance in the mall? learning to mitigate scene bias in action recognition","volume-title":"Proc. Adv. Neural Informat. Process. Syst.","volume":"32","author":"Choi","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00315"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475472"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01283"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261659"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00113"},{"key":"ref16","first-page":"26839","article-title":"Bringing image scene structure to video via frame-clip consistency of object tokens","volume":"35","author":"Avraham","year":"2022","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2943753"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26316-3_23"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3307896"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.278"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3271811"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01950"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00089"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_7"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00233"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2971175"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2965434"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.52"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00753"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_33"},{"key":"ref36","article-title":"Stat: Towards generalizable temporal action localization","author":"Liu","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3292615"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018529"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3164253"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00678"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00401"},{"key":"ref43","first-page":"23345","article-title":"Video-based human-object interaction detection from tubelet tokens","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Tu","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3463944.3469097"},{"key":"ref45","article-title":"Discovering a variety of objects in spatio-temporal human-object interactions","author":"Li","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32318"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00800"},{"key":"ref49","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01027"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01948"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref56","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref57","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3384392"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10891539.pdf?arnumber=10891539","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T18:10:22Z","timestamp":1756404622000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10891539\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3543033","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}