{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:42:24Z","timestamp":1783183344628,"version":"3.54.6"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":["62372014,62525201,62132001,62432001"],"award-info":[{"award-number":["62372014,62525201,62132001,62432001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4252040,L247006"],"award-info":[{"award-number":["4252040,L247006"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01467","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15812-15821","source":"Crossref","is-referenced-by-count":1,"title":["TRKT: Weakly Supervised Dynamic Scene Graph Generation with Temporal-Enhanced Relation-Aware Knowledge Transferring"],"prefix":"10.1109","author":[{"given":"Zhu","family":"Xu","sequence":"first","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Lei","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhimin","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guan","family":"Wang","sequence":"additional","affiliation":[{"name":"Baidu Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingchao","family":"Chen","sequence":"additional","affiliation":[{"name":"National Institute of Health Data Science, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxin","family":"Peng","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00801"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_33"},{"key":"ref3","article-title":"Video scene graph generation from single-frame weak supervision","volume-title":"The Eleventh International Conference on Learning Representations","author":"Chen","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01606"},{"key":"ref5","article-title":"3d vision and language pretraining with large-scale synthetic data","volume-title":"Proceedings of the ThirtySecond International Joint Conference on Artificial Intelligence, IJCAI-24","author":"Mo","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00510"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479231"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01889"},{"key":"ref9","author":"Gao","year":"2023","journal-title":"Compositional prompt tuning with motion cues for open-vocabulary video relation detection"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01025"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00800"},{"key":"ref12","author":"Kim","year":"2025","journal-title":"Weakly supervised video scene graph generation via natural language supervision"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00596"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01576"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_1"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1049\/cje.2020.00.088"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01350"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01350"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/cje.2022.00.173"},{"key":"ref20","article-title":"Training free video temporal grounding using large-scale pre-trained models","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Chen","year":"2024"},{"key":"ref21","volume-title":"ACM International Conference on Multimedia","author":"Shang"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104117"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01343"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548324"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28222"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01393"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00993"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01573"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00846"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00303"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2712"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01979"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1049\/cje.2021.00.455"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681660"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445218.pdf?arnumber=11445218","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:35:32Z","timestamp":1777530932000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445218\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01467","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}