{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T08:19:50Z","timestamp":1769674790932,"version":"3.49.0"},"reference-count":98,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62072112"],"award-info":[{"award-number":["62072112"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018625","name":"Scientific and Technological Innovation Action Plan of Shanghai Science and Technology Committee","doi-asserted-by":"publisher","award":["22511101502"],"award-info":[{"award-number":["22511101502"]}],"id":[{"id":"10.13039\/501100018625","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018625","name":"Scientific and Technological Innovation Action Plan of Shanghai Science and Technology Committee","doi-asserted-by":"publisher","award":["21DZ2203300"],"award-info":[{"award-number":["21DZ2203300"]}],"id":[{"id":"10.13039\/501100018625","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tcsvt.2025.3599005","type":"journal-article","created":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T18:49:08Z","timestamp":1755197348000},"page":"320-334","source":"Crossref","is-referenced-by-count":2,"title":["ClickVOS: Click Video Object Segmentation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4388-9757","authenticated-orcid":false,"given":"Pinxue","family":"Guo","sequence":"first","affiliation":[{"name":"Shanghai Engineering Research Center of AI and Robotics, Academy for Engineering and Technology, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2749-5133","authenticated-orcid":false,"given":"Lingyi","family":"Hong","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}]},{"given":"Xinyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8992-0756","authenticated-orcid":false,"given":"Shuyong","family":"Gao","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0669-0661","authenticated-orcid":false,"given":"Wanyun","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}]},{"given":"Jinglun","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Engineering Research Center of AI and Robotics, Academy for Engineering and Technology, Fudan University, Shanghai, China"}]},{"given":"Zhaoyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Engineering Research Center of AI and Robotics, Academy for Engineering and Technology, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7243-2783","authenticated-orcid":false,"given":"Xiaoqiang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Engineering and Science, Shanghai University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2358-8543","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3339-8751","authenticated-orcid":false,"given":"Wenqiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Engineering Research Center of AI and Robotics, Ministry of Education, Academy for Engineering and Technology, and Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3010293"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.565"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3098118"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3284979"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_46"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3296629"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00743"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_6"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.372"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_4"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3137660"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_20"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3219230"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01240"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00770"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2706197"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3117964"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2645616"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3108405"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2857489"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2906195"},{"key":"ref23","article-title":"Multiple-human parsing in the wild","author":"Li","year":"2017","journal-title":"arXiv:1705.07206"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240509"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3456004"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3418217"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01181-5"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093335"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00988"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3082763"},{"key":"ref31","article-title":"End to end video segmentation for driving: Lane detection for autonomous car","author":"Zhang","year":"2018","journal-title":"arXiv:1812.05914"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref33","article-title":"The 2017 Davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv:1704.00675"},{"key":"ref34","article-title":"YouTube-VOS: A large-scale video object segmentation benchmark","author":"Xu","year":"2018","journal-title":"arXiv:1809.03327"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_34"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1515\/gth-2017-0007"},{"key":"ref37","first-page":"36324","article-title":"Decoupling features in hierarchical propagation for video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00542"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00551"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00865"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3060015"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00971"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3404469"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2682578"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00683"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00933"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_13"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.228"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.480"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.81"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1122-2"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7008"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611804"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3057872"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00374"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_29"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01520"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3288878"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00539"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01038"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_18"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01519"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00130"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00624"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00996"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00404"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00259"},{"key":"ref73","article-title":"Towards robust referring video object segmentation with cyclic relational consensus","author":"Li","year":"2022","journal-title":"arXiv:2207.01203"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3419119"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00091"},{"key":"ref76","first-page":"1","article-title":"SOC: Semantic-assisted object cluster for referring video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Luo"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110535"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298987"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240638"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00946"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_18"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1004210"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.2018.8650146"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547912"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.12.006"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.567"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.239"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2834221"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref92","first-page":"2491","article-title":"Associating objects with transformers for video object segmentation","volume-title":"Proc. NIPS","author":"Yang"},{"key":"ref93","article-title":"Segment and track anything","author":"Cheng","year":"2023","journal-title":"arXiv:2305.06558"},{"key":"ref94","article-title":"Segment anything meets point tracking","author":"Raji\u010d","year":"2023","journal-title":"arXiv:2307.01197"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref96","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11365019\/11124887.pdf?arnumber=11124887","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T21:01:47Z","timestamp":1769634107000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11124887\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":98,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3599005","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}