{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:03:03Z","timestamp":1777888983107,"version":"3.51.4"},"reference-count":58,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00410","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"4306-4316","source":"Crossref","is-referenced-by-count":0,"title":["ReTracker: Exploring Image Matching for Robust Online Any Point Tracking"],"prefix":"10.1109","author":[{"given":"Dongli","family":"Tan","sequence":"first","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingyi","family":"He","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sida","family":"Peng","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiqing","family":"Gong","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xing","family":"Zhu","sequence":"additional","affiliation":[{"name":"Ant Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaming","family":"Sun","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruizhen","family":"Hu","sequence":"additional","affiliation":[{"name":"Shenzhen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujun","family":"Shen","sequence":"additional","affiliation":[{"name":"Ant Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hujun","family":"Bao","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaowei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"End-toend object detection with transformers","author":"Carion","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01876"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00045-y"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_18"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00829"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"ref9","article-title":"Tap-vid: A benchmark for tracking any point in a video","author":"Doersch","year":"2022","journal-title":"arXiv"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0989"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0901-7_28"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00923"},{"key":"ref13","article-title":"D2-Net: A Trainable CNN for Joint Detection and Description of Local Features","author":"Dusmanu","year":"2019","journal-title":"CVPR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01704"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01871"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.062"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00373"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_4"},{"key":"ref19","article-title":"Matchanything: Universal cross-modality image matching with large-scale pre-training","author":"He","year":"2025","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Rekep: Spatio-temporal reasoning of relational keypoint constraints for robotic manipulation","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","author":"Jeong","year":"2024","journal-title":"Track4gen: Teaching video diffusion models to track points improves video generation. ArXiv, abs\/2412.06016"},{"key":"ref22","article-title":"Cotracker3: Simpler and better point tracking by pseudolabelling real videos","author":"Karaev","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01815"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3205"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00218"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01616"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00068-5"},{"key":"ref30","article-title":"Distinctive image features from scaleinvariant keypoints","author":"LoweDavid","year":"2004","journal-title":"IJCV"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2463671"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tro.2017.2705103"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00669"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00669"},{"key":"ref35","article-title":"Delta: Dense efficient long-range 3d tracking for any video","author":"Duc Ngo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00901"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_35"},{"key":"ref40","article-title":"Neighbourhood consensus networks","author":"Rocco","year":"2018","journal-title":"Advances in neural information processing systems, 31"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00784"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24894\/sprengglossarium_g09306"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"ref46","article-title":"Quadtree attention for vision transformers","author":"Tang","year":"2022","journal-title":"ICLR"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00566"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_21"},{"key":"ref50","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref51","article-title":"Robotap: Tracking arbitrary points for few-shot visual imitation","author":"Vecerik","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611409"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01813"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01929"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref57","article-title":"Protracker: Probabilistic integration for robust and accurate point tracking","author":"Zhang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01818"}],"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\/11445937.pdf?arnumber=11445937","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:04:23Z","timestamp":1777611863000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445937\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00410","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}