{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T18:05:18Z","timestamp":1776189918430,"version":"3.50.1"},"reference-count":146,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"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":["62032006"],"award-info":[{"award-number":["62032006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tpami.2025.3529926","type":"journal-article","created":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T19:52:51Z","timestamp":1736970771000},"page":"3159-3174","source":"Crossref","is-referenced-by-count":16,"title":["OmniTracker: Unifying Visual Object Tracking by Tracking-With-Detection"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8129-7333","authenticated-orcid":false,"given":"Junke","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8689-5807","authenticated-orcid":false,"given":"Zuxuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4642-4373","authenticated-orcid":false,"given":"Dongdong","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft Research, Redmond, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0939-474X","authenticated-orcid":false,"given":"Chong","family":"Luo","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}]},{"given":"Xiyang","family":"Dai","sequence":"additional","affiliation":[{"name":"Microsoft Research, Redmond, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7879-0389","authenticated-orcid":false,"given":"Lu","family":"Yuan","sequence":"additional","affiliation":[{"name":"Microsoft Research, Redmond, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1907-8567","authenticated-orcid":false,"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.286"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.159"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00103"},{"key":"ref6","article-title":"Chatvideo: A tracklet-centric multimodal and versatile video understanding system","author":"Wang","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.534"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00813"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_43"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01319"},{"key":"ref16","first-page":"16743","article-title":"SwinTrack: A simple and strong baseline for transformer tracking","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref17","first-page":"11781","article-title":"Rethinking space-time networks with improved memory coverage for efficient video object segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Cheng"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00225"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref21","article-title":"YOLOX: Exceeding yolo series in 2021","author":"Ge","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_10"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01106"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_34"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref27","article-title":"BoT-SORT: Robust associations multi-pedestrian tracking","author":"Aharon","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref29","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref34","article-title":"The 2017 DAVIS challenge on video object segmentation","author":"Pont-Tuset","year":"2017"},{"key":"ref35","article-title":"MOT16: A benchmark for multi-object tracking","author":"Milan","year":"2016"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00814"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00485"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00688"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00794"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01724"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.230"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00676"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01265"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00551"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.21"},{"key":"ref50","article-title":"Transtrack: Multiple object tracking with transformer","author":"Sun","year":"2020"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01513-4"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.008"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01217"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-020-00195-x"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00976"},{"key":"ref57","first-page":"13352","article-title":"Video instance segmentation using inter-frame communication transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hwang"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00142"},{"key":"ref59","first-page":"726","article-title":"Do different tracking tasks require different appearance models?","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00542"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00858"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"ref63","article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref65","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3150169"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3240881"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_17"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00037"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref76","article-title":"Efficient DETR: Improving end-to-end object detector with dense prior","author":"Yao","year":"2021"},{"key":"ref77","volume-title":"Introduction to Random Signals and Applied Kalman Filtering: With MATLAB Exercises and Solutions","author":"Brown","year":"1997"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_32"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref82","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00716"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00479"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00628"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_13"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01309"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00661"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_9"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_22"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01399"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01792"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25155"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01822"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00935"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01802"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28591"},{"key":"ref106","article-title":"Samurai: Adapting segment anything model for zero-shot visual tracking with motion-aware memory","author":"Yang","year":"2024"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_17"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00774"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2838670"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_4"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00408"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00743"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_46"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_20"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00127"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00304"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3225078"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3165376"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20045"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00387"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW54805.2022.00019"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00934"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02112"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28493"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222576"},{"key":"ref126","article-title":"Featuresort: Essential features for effective tracking","author":"Hashempoor","year":"2024"},{"key":"ref127","article-title":"BoostTrack++: Using tracklet information to detect more objects in multiple object tracking","author":"Stanojevi\u0107","year":"2024"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3524670"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00478"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01720"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28386"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.474"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587581"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3087898"},{"key":"ref135","first-page":"1192","article-title":"Prototypical cross-attention networks for multiple object tracking and segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ke"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00176"},{"key":"ref137","first-page":"31265","article-title":"MinVIS: A minimal video instance segmentation framework without video-based training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref138","first-page":"23109","article-title":"VITA: Video instance segmentation via object token association","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Heo"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01405"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00124"},{"key":"ref141","first-page":"446","article-title":"Improving video segmentation via dynamic anchor queries","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Zhou"},{"key":"ref142","article-title":"NOVIS: A case for end-to-end near-online video instance segmentation","author":"Meinhardt","year":"2023"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00363"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref145","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024"},{"key":"ref146","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10916529\/10842236.pdf?arnumber=10842236","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T18:42:05Z","timestamp":1741372925000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10842236\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":146,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3529926","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}