{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:03:53Z","timestamp":1783530233242,"version":"3.55.0"},"reference-count":96,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"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":["62225604"],"award-info":[{"award-number":["62225604"]}],"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":["62176130"],"award-info":[{"award-number":["62176130"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004945","name":"Nankai University","doi-asserted-by":"publisher","award":["070-63233089"],"award-info":[{"award-number":["070-63233089"]}],"id":[{"id":"10.13039\/501100004945","id-type":"DOI","asserted-by":"publisher"}]},{"name":"A*STAR Career Development Fund","award":["C233312006"],"award-info":[{"award-number":["C233312006"]}]},{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"name":"AI Singapore Programme","award":["AISG2-GC-2023-007"],"award-info":[{"award-number":["AISG2-GC-2023-007"]}]},{"name":"Supercomputing Center of Nankai University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tpami.2025.3577035","type":"journal-article","created":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T13:51:50Z","timestamp":1749563510000},"page":"8180-8192","source":"Crossref","is-referenced-by-count":15,"title":["Low-Resolution Self-Attention for Semantic Segmentation"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8666-3435","authenticated-orcid":false,"given":"Yu-Huan","family":"Wu","sequence":"first","affiliation":[{"name":"Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1973-306X","authenticated-orcid":false,"given":"Shi-Chen","family":"Zhang","sequence":"additional","affiliation":[{"name":"NKIARI, Shenzhen Futian and VCIP, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6143-0264","authenticated-orcid":false,"given":"Yun","family":"Liu","sequence":"additional","affiliation":[{"name":"NKIARI, Shenzhen Futian and VCIP, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6930-8674","authenticated-orcid":false,"given":"Le","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Zhan","sequence":"additional","affiliation":[{"name":"Udeer AI, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4771-1796","authenticated-orcid":false,"given":"Daquan","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6843-0064","authenticated-orcid":false,"given":"Jiashi","family":"Feng","sequence":"additional","affiliation":[{"name":"Bytedance Inc., Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5550-8758","authenticated-orcid":false,"given":"Ming-Ming","family":"Cheng","sequence":"additional","affiliation":[{"name":"NKIARI, Shenzhen Futian and VCIP, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangli","family":"Zhen","sequence":"additional","affiliation":[{"name":"Institute of High Performance Computing (IHPC), A*STAR, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00068"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00388"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3007032"},{"key":"ref9","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref10","first-page":"7281","article-title":"HRformer: High-resolution vision transformer for dense predict","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yuan"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00747"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00199"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00533"},{"key":"ref15","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref16","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3202765"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.11065"},{"key":"ref22","article-title":"Multi-scale context aggregation by dilated convolutions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref25","article-title":"Focal self-attention for local-global interactions in vision transformers","author":"Yang","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref31","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00692"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_26"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_29"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01368"},{"key":"ref36","article-title":"OCNet: Object context network for scene parsing","author":"Yuan","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3058783"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0362-4"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-4061-2"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00134"},{"key":"ref41","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cheng"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref43","first-page":"10326","article-title":"K-net: Towards unified image segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_17"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25321"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"ref50","article-title":"ONE-PEACE: Exploring one general representation model toward unlimited modalities","author":"Wang","year":"2023"},{"key":"ref51","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref52","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00309"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00060"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01167"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01166"},{"key":"ref61","article-title":"More ConvNets in the 2020s: Scaling up kernels beyond 51x51 using sparsity","author":"Liu","year":"2022"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref64","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref67","article-title":"Conditional positional encodings for vision transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chu"},{"key":"ref68","first-page":"27378","article-title":"Understanding the robustness in vision transformers","volume-title":"Proc. Int. Conf Mach. Learn.","author":"Zhou"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-024-1393-8"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0271-y"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00983"},{"key":"ref74","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref76","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref78","first-page":"62429","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhu"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_5"},{"key":"ref81","article-title":"FasterViT: Fast vision transformers with hierarchical attention","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hatamizadeh"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01385"},{"key":"ref83","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref88","article-title":"Focal modulation networks","author":"Yang","year":"2022"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00083"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref91","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref92","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-024-0430-4"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11118328\/11029508.pdf?arnumber=11029508","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T17:44:33Z","timestamp":1754588673000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11029508\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":96,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3577035","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}