{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:18:25Z","timestamp":1783700305544,"version":"3.55.0"},"reference-count":88,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372329"],"award-info":[{"award-number":["62372329"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Scientific Innovation Foundation","award":["23DZ1203400"],"award-info":[{"award-number":["23DZ1203400"]}]},{"name":"Shanghai Rising Star Program","award":["21QC1400900"],"award-info":[{"award-number":["21QC1400900"]}]},{"name":"Tongji\u2013Qomolo Autonomous Driving Commercial Vehicle Joint Laboratory Project"},{"name":"Xiaomi Young Talents Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tits.2024.3417813","type":"journal-article","created":{"date-parts":[[2024,7,3]],"date-time":"2024-07-03T17:38:40Z","timestamp":1720028320000},"page":"15934-15946","source":"Crossref","is-referenced-by-count":17,"title":["SDPT: Semantic-Aware Dimension-Pooling Transformer for Image Segmentation"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8225-858X","authenticated-orcid":false,"given":"Hu","family":"Cao","sequence":"first","affiliation":[{"name":"Chair of Robotics, Artificial Intelligence and Real-Time Systems, Technical University of Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7416-592X","authenticated-orcid":false,"given":"Guang","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8277-2706","authenticated-orcid":false,"given":"Hengshuang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Hong Kong, Pokfulam, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7390-9173","authenticated-orcid":false,"given":"Dongsheng","family":"Jiang","sequence":"additional","affiliation":[{"name":"Huawei Technologies, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6337-5748","authenticated-orcid":false,"given":"Xiaopeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei Technologies, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7252-5047","authenticated-orcid":false,"given":"Qi","family":"Tian","sequence":"additional","affiliation":[{"name":"Huawei Technologies, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4840-076X","authenticated-orcid":false,"given":"Alois","family":"Knoll","sequence":"additional","affiliation":[{"name":"Chair of Robotics, Artificial Intelligence and Real-Time Systems, Technical University of Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-0761-4_105"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/83.701170"},{"issue":"6","key":"ref4","first-page":"28","article-title":"The watershed transformation applied to image segmentation","volume":"1992","author":"Beucher","year":"1992","journal-title":"Scanning Microsc."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/34.1000236"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/4.996"},{"issue":"1","key":"ref8","first-page":"15","article-title":"Object enhancement and extraction","volume":"10","author":"Prewitt","year":"1970","journal-title":"Picture Process. Psychopictorics"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059968"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00163"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/GCWkshps56602.2022.10008782"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09425-0"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114417"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-021-02432-y"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561398"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2021.3071290"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3144358"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2909066"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2985815"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2972974"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3207665"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCC54389.2021.9674634"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref29","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref30","first-page":"10347","article-title":"Training data-efficient image transformers distillation through attention","volume-title":"Proc. ICML","author":"Touvron"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref37","first-page":"12077","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. NIPS","author":"Xie"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref39","first-page":"1","article-title":"SegViT: Semantic segmentation with plain vision transformers","volume-title":"Proc. NIPS","author":"Zhang"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3202765"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref45","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. NIPS","author":"Cheng"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00091"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/0734-189X(90)90053-X"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1080\/2151237X.2007.10129236"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00406"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00143"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref58","first-page":"1140","article-title":"SegNeXt: Rethinking convolutional attention design for semantic segmentation","volume-title":"Proc. NIPS","author":"Guo"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01058"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00959"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01177"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01871"},{"key":"ref66","first-page":"1","article-title":"Seaformer: Squeeze-enhanced axial transformer for mobile semantic segmentation","volume-title":"Proc. ICLR","author":"Wan"},{"key":"ref67","first-page":"516","article-title":"Head-free lightweight semantic segmentation with linear transformer","volume-title":"Proc. AAAI","author":"Bo"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28457"},{"key":"ref69","first-page":"1","article-title":"Multi-scale representations by varing window attention for semantic segmentation","volume-title":"Proc. ICLR","author":"Yan"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3300537"},{"key":"ref71","first-page":"30392","article-title":"Early convolutions help transformers see better","volume-title":"Proc. NIPS","author":"Xiao"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref73","first-page":"1","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. NIPS","author":"Paszke"},{"key":"ref74","article-title":"PyTorch image models","author":"Wightman","year":"2019","journal-title":"GitHub, GitHub Repository"},{"key":"ref75","volume-title":"MMSegmentation: OpenMMLab Semantic Segmentation Toolbox and Benchmark","year":"2020"},{"key":"ref76","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref78","first-page":"7281","article-title":"HRFormer: High-resolution vision transformer for dense predict","volume-title":"Proc. NIPS","author":"Yuan"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_36"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01178"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01515-2"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00747"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.11065"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00299"},{"key":"ref87","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. NIPS","author":"Chu"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/10742224\/10584449.pdf?arnumber=10584449","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T02:50:50Z","timestamp":1733885450000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10584449\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":88,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tits.2024.3417813","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}