{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T22:48:07Z","timestamp":1774651687506,"version":"3.50.1"},"reference-count":77,"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":["U22A20102"],"award-info":[{"award-number":["U22A20102"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272419"],"award-info":[{"award-number":["62272419"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402449"],"award-info":[{"award-number":["62402449"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LQ23F020010"],"award-info":[{"award-number":["LQ23F020010"]}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LZ22F020010"],"award-info":[{"award-number":["LZ22F020010"]}]},{"name":"Open Project Program of the State Key Laboratory of CAD&amp;CG","award":["A2421"],"award-info":[{"award-number":["A2421"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3557619","type":"journal-article","created":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T15:59:13Z","timestamp":1743695953000},"page":"3009-3022","source":"Crossref","is-referenced-by-count":8,"title":["Open-Vocabulary Multi-Object Tracking With Domain Generalized and Temporally Adaptive Features"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8175-2076","authenticated-orcid":false,"given":"Run","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang Normal University, Jinhua, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7593-1593","authenticated-orcid":false,"given":"Dawei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang Normal University, Jinhua, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9493-5411","authenticated-orcid":false,"given":"Yanchao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang Normal University, Jinhua, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4500-5836","authenticated-orcid":false,"given":"Yunliang","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang Normal University, Jinhua, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5271-9215","authenticated-orcid":false,"given":"Zhonglong","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang Normal University, Jinhua, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0199-2254","authenticated-orcid":false,"given":"Sang-Woon","family":"Jeon","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Hanyang University, Ansan, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8465-0996","authenticated-orcid":false,"given":"Hua","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute for Sustainable Industries and Liveable Cities, College of Engineering and Science, Victoria University, Melbourne, VIC, Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref2","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref3","article-title":"Sora: A review on background, technology, limitations, and opportunities of large vision models","author":"Liu","year":"2024"},{"key":"ref4","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Zconf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01846"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_29"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_26"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611695"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3062489"},{"key":"ref10","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2400250"},{"key":"ref12","first-page":"1","article-title":"DoraemonGPT: Toward understanding dynamic scenes with large language models (exemplified as a video agent)","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Yang","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00539"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref15","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3240881"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3367537"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref22","first-page":"29935","article-title":"Data augmentation can improve robustness","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Rebuffi","year":"2021"},{"key":"ref23","first-page":"1","article-title":"Towards robust object detection invariant to real-world domain shifts","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Fan","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/127"},{"key":"ref26","article-title":"Transtrack: Multiple object tracking with transformer","author":"Sun","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3222614"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3060862"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222576"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28471"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01327"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.104125"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3299412"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3285441"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01857-z"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3070562"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3463966"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"ref40","article-title":"MOT16: A benchmark for multi-object tracking","author":"Milan","year":"2016"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3140919"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3323852"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3009717"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref45","article-title":"Bot-sort: Robust associations multi-pedestrian tracking","author":"Aharon","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00934"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3115815"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3262578"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123456"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2899569"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_24"},{"key":"ref54","first-page":"24950","article-title":"DetectGPT: Zero-shot machine-generated text detection using probability curvature","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mitchell","year":"2023"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3040258"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3365249"},{"issue":"3","key":"ref57","first-page":"1","article-title":"Zero-shot detection via vision and language knowledge distillation","volume":"2","author":"Gu","year":"2021"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00665"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.168"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.220"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging9020046"},{"key":"ref62","first-page":"1","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren","year":"2015"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01513-4"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3301975"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00103"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-024-03544-7"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.3390\/app12188972"},{"key":"ref76","article-title":"1st Place solution to ECCV-TAO-2020: Detect and represent any object for tracking","author":"Du","year":"2021"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10948331.pdf?arnumber=10948331","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T18:38:45Z","timestamp":1767119925000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10948331\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3557619","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}