{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T17:11:54Z","timestamp":1778605914474,"version":"3.51.4"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0102001"],"award-info":[{"award-number":["2018AAA0102001"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61725202"],"award-info":[{"award-number":["61725202"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62006036"],"award-info":[{"award-number":["62006036"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1903215"],"award-info":[{"award-number":["U1903215"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61829102"],"award-info":[{"award-number":["61829102"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61906031"],"award-info":[{"award-number":["61906031"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tip.2022.3201603","type":"journal-article","created":{"date-parts":[[2022,9,2]],"date-time":"2022-09-02T19:51:54Z","timestamp":1662148314000},"page":"5801-5812","source":"Crossref","is-referenced-by-count":6,"title":["From Pixels to Semantics: Self-Supervised Video Object Segmentation With Multiperspective Feature Mining"],"prefix":"10.1109","volume":"31","author":[{"given":"Ruoqi","family":"Li","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1911-2526","authenticated-orcid":false,"given":"Yifan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Innovation and Entrepreneurship, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lijun","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6668-9758","authenticated-orcid":false,"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8497-611X","authenticated-orcid":false,"given":"Xiaopeng","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3776-9799","authenticated-orcid":false,"given":"Qiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00651"},{"key":"ref2","first-page":"1","article-title":"Joint-task self-supervised learning for temporal correspondence","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17220"},{"key":"ref4","article-title":"Self-supervised video object segmentation","author":"Zhu","year":"2020","journal-title":"arXiv:2006.12480"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref6","article-title":"The 2017 Davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv:1704.00675"},{"key":"ref7","article-title":"YouTube-VOS: A large-scale video object segmentation benchmark","author":"Xu","year":"2018","journal-title":"arXiv:1809.03327"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00542"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.480"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00374"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16308"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00159"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3013162"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2021.3057872"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2682578"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20011"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.372"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.565"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2438550"},{"key":"ref20","article-title":"Lucid data dreaming for video object segmentation","author":"Khoreva","year":"2017","journal-title":"arXiv:1703.09554"},{"key":"ref21","first-page":"1","article-title":"MaskRNN: Instance level video object segmentation","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Hu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_35"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00125"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00971"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_4"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_43"},{"key":"ref28","article-title":"Self-supervised video object segmentation by motion-aware mask propagation","author":"Miao","year":"2021","journal-title":"arXiv:2107.12569"},{"key":"ref29","first-page":"1","article-title":"Space-time correspondence as a contrastive random walk","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Jabri"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00992"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref32","first-page":"1601","article-title":"Do convnets learn correspondence?","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Long"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.203"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00238"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3077138"},{"key":"ref36","first-page":"1","article-title":"Joint line segmentation and transcription for end-to-end handwritten paragraph recognition","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Bluche"},{"key":"ref37","article-title":"Learnable pooling with context gating for video classification","author":"Miech","year":"2017","journal-title":"arXiv:1706.06905"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.338"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref41","first-page":"1","article-title":"Spatial transformer networks","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Jaderberg"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00679"},{"key":"ref43","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2017","journal-title":"arXiv:1709.01507"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref46","first-page":"1","article-title":"BAM: Bottleneck attention module","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Park"},{"key":"ref47","first-page":"1","article-title":"Attention is all you need","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref48","article-title":"A structured self-attentive sentence embedding","author":"Lin","year":"2017","journal-title":"arXiv:1703.03130"},{"key":"ref49","article-title":"Dual attention network for scene segmentation","author":"Fu","year":"2018","journal-title":"arXiv:1809.02983"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_6"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2838670"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.116"},{"key":"ref55","first-page":"1","article-title":"Self-supervised learning for video correspondence flow","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Lai"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_24"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00267"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00680"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00142"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00408"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_41"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.238"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00130"},{"key":"ref66","article-title":"SEED: Self-supervised distillation for visual representation","author":"Fang","year":"2021","journal-title":"arXiv:2101.04731"},{"key":"ref67","first-page":"1","article-title":"DisCo: Remedy self-supervised learning on lightweight models with distilled contrastive learning","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Gao"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9626658\/09875116.pdf?arnumber=9875116","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T06:20:28Z","timestamp":1709360428000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9875116\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/tip.2022.3201603","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}