{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T07:16:22Z","timestamp":1761808582150,"version":"3.37.3"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Italy\u2013China Collaboration Project TALENT","award":["2018YFE0118400"],"award-info":[{"award-number":["2018YFE0118400"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272438","61931008","61772494","61836002","61976069"],"award-info":[{"award-number":["62272438","61931008","61772494","61836002","61976069"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental Research Funds for Central Universities"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tnnls.2022.3219936","type":"journal-article","created":{"date-parts":[[2022,11,16]],"date-time":"2022-11-16T20:38:50Z","timestamp":1668631130000},"page":"7671-7684","source":"Crossref","is-referenced-by-count":5,"title":["Self Supervised Progressive Network for High Performance Video Object Segmentation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3954-2387","authenticated-orcid":false,"given":"Guorong","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7468-073X","authenticated-orcid":false,"given":"Dexiang","family":"Hong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7286-6151","authenticated-orcid":false,"given":"Kai","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3423-1539","authenticated-orcid":false,"given":"Bineng","family":"Zhong","sequence":"additional","affiliation":[{"name":"Guangxi Key Laboratory of Multisource Information Mining and Security, Guangxi Normal University, Guilin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4038-753X","authenticated-orcid":false,"given":"Li","family":"Su","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9970-5152","authenticated-orcid":false,"given":"Zhenjun","family":"Han","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences (UCAS), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-296X","authenticated-orcid":false,"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2455418"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.565"},{"issue":"6","key":"ref3","first-page":"1","article-title":"Online adaptation of convolutional neural networks for the 2017 DAVIS challenge on video object segmentation","volume-title":"Proc. DAVIS Challenge Video Object Segmentation-CVPR Workshops","volume":"5","author":"Voigtlaender"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00971"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00408"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00770"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00651"},{"key":"ref9","first-page":"318","article-title":"Joint-task self-supervised learning for temporal correspondence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref10","first-page":"1","article-title":"Self-supervised learning for video correspondence flow","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Lai"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00267"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_24"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475551"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00992"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0908-3"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.238"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_20"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2838670"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_35"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3054769"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3043099"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2963282"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2021.3098118"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00413"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00953"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00152"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413942"},{"key":"ref31","first-page":"1","article-title":"Self-supervised learning by cross-modal audio-video clustering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Alwassel"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref34","first-page":"667","article-title":"Dynamic filter networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jia"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00629"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.607"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00586"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00186"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_19"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.79"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.262"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00021"},{"key":"ref43","article-title":"Learning visual groups from co-occurrences in space and time","author":"Isola","year":"2015","journal-title":"arXiv:1511.06811"},{"key":"ref44","first-page":"4016","article-title":"Unsupervised learning of object landmarks through conditional image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jakab"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.166"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018545"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01058"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00413"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00658"},{"key":"ref50","first-page":"1","article-title":"Space-time correspondence as a contrastive random walk","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jabri"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3026913"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00698"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107312"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00941"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.5201\/ipol.2013.26"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00680"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20009"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01265"},{"key":"ref60","first-page":"11781","article-title":"Rethinking space-time networks with improved memory coverage for efficient video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Cheng"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref62","article-title":"The 2017 Davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv:1704.00675"},{"key":"ref63","article-title":"YouTube-VOS: A large-scale video object segmentation benchmark","author":"Xu","year":"2018","journal-title":"arXiv:1809.03327"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.273"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2004.1273918"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref67","article-title":"The Kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10547160\/09953060.pdf?arnumber=9953060","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,3]],"date-time":"2024-09-03T04:41:16Z","timestamp":1725338476000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9953060\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":68,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3219936","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}