{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:46:03Z","timestamp":1777657563717,"version":"3.51.4"},"reference-count":66,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611587","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"12420-12427","source":"Crossref","is-referenced-by-count":5,"title":["Doduo: Learning Dense Visual Correspondence from Unsupervised Semantic-Aware Flow"],"prefix":"10.1109","author":[{"given":"Zhenyu","family":"Jiang","sequence":"first","affiliation":[{"name":"the University of Texas at Austin,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanwen","family":"Jiang","sequence":"additional","affiliation":[{"name":"the University of Texas at Austin,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuke","family":"Zhu","sequence":"additional","affiliation":[{"name":"the University of Texas at Austin,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126513"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2047196.2047270"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2011.6092378"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2015.XI.001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911434148"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007939232436"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139655"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00553"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abd8803"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2574713"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459161"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1023\/b:visi.0000029664.99615.94"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_28"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00828"},{"key":"ref17","volume":"abs\/1606.03558","author":"Choy","year":"2016","journal-title":"Universal correspondence network"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00615"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2634089"},{"key":"ref21","author":"Florence","year":"2018","journal-title":"Dense object nets: Learning dense visual object descriptors by and for robotic manipulation"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2956365"},{"key":"ref23","author":"Manuelli","year":"2020","journal-title":"Keypoints into the future: Self-supervised correspondence in model-based reinforcement learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812291"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12276"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10723"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_1"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00470"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01098"},{"key":"ref32","volume":"abs\/2304.07193","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref36","volume":"abs\/2211.03726","author":"Doersch","year":"2022","journal-title":"Tap-vid: A benchmark for tracking any point in a video"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_44"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2634089"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_24"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00267"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00140"},{"key":"ref43","volume":"abs\/1709.00930","author":"Zhong","year":"2017","journal-title":"Self-supervised learning for stereo matching with self-improving ability"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00127"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00851"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00513"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_42"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_33"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00388"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00992"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01003"},{"key":"ref53","volume":"abs\/2006.14613","author":"Jabri","year":"2020","journal-title":"Space-time correspondence as a contrastive random walk"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00651"},{"key":"ref55","volume":"abs\/1905.00875","author":"Lai","year":"2019","journal-title":"Self-supervised learning for video correspondence flow"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_6"},{"key":"ref57","first-page":"871","article-title":"Learning dense visual descriptors using image augmentations for robot manipulation tasks","volume-title":"Conference on Robot Learning","author":"Graf"},{"key":"ref58","volume":"abs\/2112.10764","author":"Cheng","year":"2021","journal-title":"Mask2former for video instance segmentation"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00513"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24673-2_3"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.1994.413553"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_1"},{"key":"ref63","volume":"abs\/2108.08420","author":"Xu","year":"2021","journal-title":"D3d-hoi: Dynamic 3d human-object interactions from videos"},{"key":"ref64","volume":"abs\/1704.00675","author":"Pont-Tuset","year":"2017","journal-title":"The 2017 davis challenge on video object segmentation"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611971484"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.001"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611587.pdf?arnumber=10611587","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:08:18Z","timestamp":1723349298000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611587\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611587","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}