{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T03:38:50Z","timestamp":1783741130332,"version":"3.55.0"},"reference-count":63,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62495061,62276145"],"award-info":[{"award-number":["62495061,62276145"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Project of China","doi-asserted-by":"publisher","award":["2024YFE0100700"],"award-info":[{"award-number":["2024YFE0100700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02076","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22361-22371","source":"Crossref","is-referenced-by-count":7,"title":["Revisiting Efficient Semantic Segmentation: Learning Offsets for Better Spatial and Class Feature Alignment"],"prefix":"10.1109","author":[{"given":"Shi-Chen","family":"Zhang","sequence":"first","affiliation":[{"name":"VCIP, CS, Nankai University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunheng","family":"Li","sequence":"additional","affiliation":[{"name":"VCIP, CS, Nankai University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Huan","family":"Wu","sequence":"additional","affiliation":[{"name":"IHPC, A*STAR,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qibin","family":"Hou","sequence":"additional","affiliation":[{"name":"VCIP, CS, Nankai University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming-Ming","family":"Cheng","sequence":"additional","affiliation":[{"name":"VCIP, CS, Nankai University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref2","article-title":"Efficient self-ensemble for semantic segmentation","author":"Bousselham","year":"2022","journal-title":"BMVC"},{"key":"ref3","first-page":"1209","article-title":"Cocostuff: Thing and stuff classes incontext","author":"Caesar","year":"2018","journal-title":"IEEE CVPR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01496"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3449959"},{"key":"ref6","article-title":"Semantic image segmentation with deep convolutional nets and fully connected crfs","author":"Chen","year":"2014","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref8","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref10","first-page":"17864","article-title":"Perpixel classification is not all you need for semantic segmentation","volume":"34","author":"Cheng","year":"2021","journal-title":"NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref12","volume-title":"MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref14","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-023-00019-6"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00959"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref18","first-page":"1140","article-title":"Segnext: Rethinking convolutional attention design for semantic segmentation","volume":"35","author":"Guo","year":"2022","journal-title":"NeurIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00406"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-023-1385-0"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00714"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00975"},{"key":"ref23","first-page":"12934","article-title":"Efficientformer: Vision transformers at mobilenet speed","volume":"35","author":"Li","year":"2022","journal-title":"NeurIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01549"},{"key":"ref25","article-title":"Unbiased regionlanguage alignment for open-vocabulary dense prediction","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","first-page":"28243","article-title":"Cascade-CLIP: Cascaded visionlanguage embeddings alignment for zero-shot semantic segmentation","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Li"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-4061-2"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0302-8"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref32","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"ICLR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_14"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25321"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00358"},{"key":"ref40","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref41","article-title":"Seaformer: Squeeze-enhanced axial transformer for mobile semantic segmentation","volume-title":"The eleventh international conference on learning representations","author":"Wan"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0539"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3202765"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3577035"},{"key":"ref46","first-page":"12077","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie","year":"2021","journal-title":"NeurIPS"},{"key":"ref47","article-title":"Multi-scale representations by varying window attention for semantic segmentation","author":"Yan","year":"2024","journal-title":"ICLR"},{"key":"ref48","article-title":"Dformer: Rethinking rgbd representation learning for semantic segmentation","author":"Yin","year":"2024","journal-title":"ICLR"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01802"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01515-2"},{"key":"ref52","article-title":"Multi-scale context aggregation by dilated convolutions","author":"Yu","year":"2015","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_6"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_11"},{"key":"ref55","first-page":"7281","article-title":"Hrformer: Highresolution vision transformer for dense predict","volume":"34","author":"Yuan","year":"2021","journal-title":"NeurIPS"},{"key":"ref56","first-page":"4971","article-title":"Segvit: Semantic segmentation with plain vision transformers","volume":"35","author":"Zhang","year":"2022","journal-title":"NeurIPS"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3590-1"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01177"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3367952"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00889-5_1"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445364.pdf?arnumber=11445364","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:14:42Z","timestamp":1777529682000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445364\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02076","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}