{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T16:41:24Z","timestamp":1780418484002,"version":"3.54.1"},"reference-count":61,"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\/501100020771","name":"Young Scientists Fund of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402490"],"award-info":[{"award-number":["62402490"]}],"id":[{"id":"10.13039\/501100020771","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004517","name":"Tianjin University","doi-asserted-by":"publisher","award":["62422118"],"award-info":[{"award-number":["62422118"]}],"id":[{"id":"10.13039\/501100004517","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"publisher","award":["2025A1515010101"],"award-info":[{"award-number":["2025A1515010101"]}],"id":[{"id":"10.13039\/501100021171","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\/iccv51701.2025.00701","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"7472-7482","source":"Crossref","is-referenced-by-count":1,"title":["VOVTrack: Exploring the Potentiality in Raw Videos for Open-Vocabulary Multi-Object Tracking"],"prefix":"10.1109","author":[{"given":"Zekun","family":"Qian","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruize","family":"Han","sequence":"additional","affiliation":[{"name":"Shenzhen University of Advanced Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junhui","family":"Hou","sequence":"additional","affiliation":[{"name":"City University of Hong Kong\\\\ \\{clarkqian"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linqi","family":"Song","sequence":"additional","affiliation":[{"name":"City University of Hong Kong\\\\ \\{clarkqian"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Feng","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2008.4587583"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_24"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00103"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2017.8078516"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00792"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00187"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_26"},{"key":"ref8","article-title":"MOT20: A benchmark for multi object tracking in crowded scenes","author":"Dendorfer","year":"2020","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093355"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00897"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27921"},{"key":"ref12","article-title":"1st place solution to ECCV-TA O-2020: Detect and represent any object for tracking","author":"Du","year":"2021","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3240881"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3463966"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3301975"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref18","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"In International Conference on Learning Representations","author":"Gu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3070562"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01857-z"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00636"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00577"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.23919\/FUSION59988.2024.10706432"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.59"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_29"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00539"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73383-3_1"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01846"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2969183"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11194"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_41"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2016.7487487"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2018.8460975"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196949"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01720"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International Conference on Machine Learning","author":"Radford"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6868"},{"key":"ref41","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.41"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01410"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3577925"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1111\/2041-210X.13166"},{"key":"ref47","article-title":"Transtrack: Multiple object tracking with transformer","volume":"2","author":"Sun","year":"2020","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02032"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3285651"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_5"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00679"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01513-4"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_28"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00857"}],"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\/11444453.pdf?arnumber=11444453","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:46:08Z","timestamp":1777531568000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444453\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00701","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}