{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T20:18:24Z","timestamp":1778271504168,"version":"3.51.4"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"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":["62302130"],"award-info":[{"award-number":["62302130"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Postdoctoral Fellowship Program of CPSF","award":["GZC20251050"],"award-info":[{"award-number":["GZC20251050"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tcsvt.2026.3651347","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:04:02Z","timestamp":1768255442000},"page":"7337-7351","source":"Crossref","is-referenced-by-count":0,"title":["Balancing Performance and Efficiency: Toward Superior Image Segmentation With Adaptive Sparse Attention"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6361-9460","authenticated-orcid":false,"given":"Xiaoqing","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8195-9322","authenticated-orcid":false,"given":"Chaojun","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Hainan University, Haikou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4096-9134","authenticated-orcid":false,"given":"Yuan","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4682-4839","authenticated-orcid":false,"given":"Jing","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7986-4244","authenticated-orcid":false,"given":"Laurence T.","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9584-2160","authenticated-orcid":false,"given":"Jieming","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_17"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/technologies12020015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3293166"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3271523"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3260240"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3387116"},{"key":"ref7","article-title":"Progressive token length scaling in transformer encoders for efficient universal segmentation","author":"Aich","year":"2024","journal-title":"arXiv:2404.14657"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.26599\/cai.2024.9390002"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127468"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref15","article-title":"A review of transformer-based models for computer vision tasks: Capturing global context and spatial relationships","author":"Astlin Pereira","year":"2024","journal-title":"arXiv:2408.15178"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084827"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10595-0"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-46005-0_8"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3378465"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102608"},{"key":"ref24","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. NIPS","author":"Cheng"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3507383"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01496"},{"key":"ref28","first-page":"73480","article-title":"ReMaX: Relaxing for better training on efficient panoptic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Sun"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3332435"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01118"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059968"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3465055"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/121"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3523316"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00355"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105605"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref39","article-title":"Axial attention in multidimensional transformers","author":"Ho","year":"2019","journal-title":"arXiv:1912.12180"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_7"},{"key":"ref41","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00261"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3367952"},{"key":"ref45","article-title":"Multi-scale representations by varying window attention for semantic segmentation","author":"Yan","year":"2024","journal-title":"arXiv:2404.16573"},{"key":"ref46","article-title":"PanSR: An object-centric mask transformer for panoptic segmentation","author":"\u017dust","year":"2024","journal-title":"arXiv:2412.10589"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1577"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02362"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3592621"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01777"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01709"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.aej.2025.09.072"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0940"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00585"},{"key":"ref56","first-page":"62429","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Zhu"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_5"},{"key":"ref58","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.534"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11511351\/11333296.pdf?arnumber=11333296","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T19:42:22Z","timestamp":1778269342000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11333296\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":62,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3651347","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}