{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:26:54Z","timestamp":1772908014667,"version":"3.50.1"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFE0200300"],"award-info":[{"award-number":["2022YFE0200300"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972323"],"award-info":[{"award-number":["61972323"]}],"id":[{"id":"10.13039\/501100001809","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":[[2024,8]]},"DOI":"10.1109\/tcsvt.2023.3284165","type":"journal-article","created":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T17:46:09Z","timestamp":1686246369000},"page":"6722-6734","source":"Crossref","is-referenced-by-count":13,"title":["Unified Multi-Modality Video Object Segmentation Using Reinforcement Learning"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3697-7927","authenticated-orcid":false,"given":"Mingjie","family":"Sun","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9416-2486","authenticated-orcid":false,"given":"Jimin","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0199-7386","authenticated-orcid":false,"given":"Eng Gee","family":"Lim","sequence":"additional","affiliation":[{"name":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6745-9674","authenticated-orcid":false,"given":"Cairong","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8581-9554","authenticated-orcid":false,"given":"Yao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3232608"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3073718"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207518"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3211734"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2938527"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2900907"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3122801"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/cta.2907"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00954"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107706"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01255"},{"key":"ref12","first-page":"2546","article-title":"Transfer-based semantic anomaly detection","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Deecke"},{"key":"ref13","first-page":"8703","article-title":"Neural transformation learning for deep anomaly detection beyond images","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Qiu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01526"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01662"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00284"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01559"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00297"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00286"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01289"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01080"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01384"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3058684"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2021.3139467"},{"key":"ref25","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","first-page":"1","article-title":"Reinforcement learning algorithm for partially observable Markov decision problems","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"7","author":"Jaakkola"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref29","article-title":"YouTube-VOS: A large-scale video object segmentation benchmark","author":"Xu","year":"2018","journal-title":"arXiv:1809.03327"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20017"},{"key":"ref31","first-page":"1","article-title":"Rethinking space-time networks with improved memory coverage for efficient video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Cheng"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2930152"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2500820"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2834221"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3210245"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.565"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref40","article-title":"The 2017 Davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv:1704.00675"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.116"},{"key":"ref42","first-page":"3430","article-title":"Video object segmentation with adaptive feature bank and uncertain-region refinement","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"33","author":"Liang"},{"key":"ref43","first-page":"1218","article-title":"Delving into the cyclic mechanism in semi-supervised video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Li"},{"key":"ref44","first-page":"1","article-title":"Associating objects with transformers for video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Yang"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01265"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00953"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.122"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3159403"},{"key":"ref52","article-title":"Rethinking cross-modal interaction from a top-down perspective for referring video object segmentation","author":"Liang","year":"2021","journal-title":"arXiv:2106.01061"},{"key":"ref53","article-title":"RefVOS: A closer look at referring expressions for video object segmentation","author":"Bellver","year":"2020","journal-title":"arXiv:2010.00263"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00946"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107465"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1082"},{"key":"ref57","first-page":"1","article-title":"Actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"12","author":"Konda"},{"key":"ref58","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013","journal-title":"arXiv:1301.3781"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref60","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079993"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00542"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00680"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00770"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00940"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_43"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00698"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00743"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_35"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00135"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3081597"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_46"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_38"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_39"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00413"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00551"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00134"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547824"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00142"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10634006\/10146303.pdf?arnumber=10146303","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T05:50:38Z","timestamp":1723528238000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10146303\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":80,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3284165","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}