{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T19:11:43Z","timestamp":1764184303643,"version":"3.46.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Sindh Research Support Program (SRSP) Grant and Sindh Higher Education Commission","award":["SHEC\/SRSP\/MS-2\/281\/2022-23","SHEC\/SRSP\/IT&CS-1\/282\/2022-23"],"award-info":[{"award-number":["SHEC\/SRSP\/MS-2\/281\/2022-23","SHEC\/SRSP\/IT&CS-1\/282\/2022-23"]}]},{"name":"NORPART CONNECT Project"},{"name":"DIKU, Norway","award":["NORPART-2021\/10502"],"award-info":[{"award-number":["NORPART-2021\/10502"]}]},{"name":"NTNU"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3634778","type":"journal-article","created":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T18:46:49Z","timestamp":1763578009000},"page":"197544-197561","source":"Crossref","is-referenced-by-count":0,"title":["SSF4VSU: A Self-Supervised Synergetic Framework for Visual Scene Understanding"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9040-3177","authenticated-orcid":false,"given":"Saif","family":"Hassan","sequence":"first","affiliation":[{"name":"Department of Computer Science, Sukkur IBA University, Sukkur, Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1563-1142","authenticated-orcid":false,"given":"Ghulam","family":"Mujtaba","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Sukkur IBA University, Sukkur, Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2434-0849","authenticated-orcid":false,"given":"Habib","family":"Ullah","sequence":"additional","affiliation":[{"name":"Faculty of Science and Technology (REALTEK), Norwegian University of Life Sciences (NMBU), Ås, Norway"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2416-2878","authenticated-orcid":false,"given":"Ali Shariq","family":"Imran","sequence":"additional","affiliation":[{"name":"Department of Computer Science (IDI), Intelligent Systems and Analytics (ISA) Research Group, Norwegian University of Science and Technology (NTNU), GjØvik, Norway"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6034-4137","authenticated-orcid":false,"given":"Ahmet","family":"Soylu","sequence":"additional","affiliation":[{"name":"School of Economics, Innovation, and Technology (SEIT), Kristiania University of Applied Sciences, Oslo, Norway"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0222-6340","authenticated-orcid":false,"given":"Mohib","family":"Ullah","sequence":"additional","affiliation":[{"name":"Department of Computer Science (IDI), Intelligent Systems and Analytics (ISA) Research Group, Norwegian University of Science and Technology (NTNU), GjØvik, Norway"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01393-0"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00813"},{"key":"ref4","first-page":"726","article-title":"Do different tracking tasks require different appearance models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Wang"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_43"},{"key":"ref6","article-title":"OmniTracker: Unifying object tracking by tracking-with-detection","author":"Wang","year":"2023","journal-title":"arXiv:2303.12079"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00661"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01319"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3402436"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2025.3553429"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/AIITA65135.2025.11047957"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00657"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3376582"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2025.3601075"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_28"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01513-4"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00485"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3225078"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3432156"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3546818"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3455348"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3602953"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01265"},{"key":"ref30","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.","author":"Cheng"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00225"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA63115.2024.00098"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3341457"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3321977"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3383592"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01217"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"ref39","article-title":"TransTrack: Multiple object tracking with transformer","author":"Sun","year":"2020","journal-title":"arXiv:2012.15460"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3450370"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3411617"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3551672"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3567349"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3569732"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.26599\/BDMA.2025.9020024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02112"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00672"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00142"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00716"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07456-2"},{"key":"ref52","article-title":"PointTrack++ for effective online multi-object tracking and segmentation","author":"Xu","year":"2020","journal-title":"arXiv:2007.01549"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_10"},{"key":"ref55","first-page":"1192","article-title":"Prototypical cross-attention networks for multiple object tracking and segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ke"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11258901.pdf?arnumber=11258901","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T19:05:24Z","timestamp":1764183924000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11258901\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3634778","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}