{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:24:47Z","timestamp":1778171087600,"version":"3.51.4"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"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":["61901117"],"award-info":[{"award-number":["61901117"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["2023J01083"],"award-info":[{"award-number":["2023J01083"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen LongHua Fundamental Research Program","award":["10162A20230325B73A546"],"award-info":[{"award-number":["10162A20230325B73A546"]}]},{"name":"OpenI Community"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tcsvt.2024.3395132","type":"journal-article","created":{"date-parts":[[2024,4,29]],"date-time":"2024-04-29T17:49:41Z","timestamp":1714412981000},"page":"9024-9038","source":"Crossref","is-referenced-by-count":8,"title":["CARD: Semantic Segmentation With Efficient Class-Aware Regularized Decoder"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5668-5529","authenticated-orcid":false,"given":"Ye","family":"Huang","sequence":"first","affiliation":[{"name":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8996-0897","authenticated-orcid":false,"given":"Di","family":"Kang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0712-4738","authenticated-orcid":false,"given":"Liang","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0940-3338","authenticated-orcid":false,"given":"Wenjing","family":"Jia","sequence":"additional","affiliation":[{"name":"Global Big Data Technologies Centre, University of Technology Sydney, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangjian","family":"He","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Nottingham Ningbo China, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0723-4016","authenticated-orcid":false,"given":"Lixin","family":"Duan","sequence":"additional","affiliation":[{"name":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5005-7166","authenticated-orcid":false,"given":"Xuefei","family":"Zhe","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9543-3754","authenticated-orcid":false,"given":"Linchao","family":"Bao","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Birmingham, Birmingham, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_30"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2830102"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01465-9"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00909"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00926"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00068"},{"key":"ref14","first-page":"1","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.11065"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00690"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01243"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/235"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27958"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3007032"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00939"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00960"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref26","first-page":"1","article-title":"Axial attention in multidimensional transformers","volume-title":"Proc. ICLR","author":"Ho"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19985"},{"key":"ref28","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. ICLR","author":"Simonyan"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref31","article-title":"ResNeSt: Split-attention networks","author":"Zhang","year":"2020","journal-title":"arXiv:2004.08955"},{"key":"ref32","first-page":"1","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mingxing"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref40","article-title":"FastFCN: Rethinking dilated convolution in the backbone for semantic segmentation","author":"Wu","year":"2019","journal-title":"arXiv:1903.11816"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00721"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.10882"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"ref46","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017","journal-title":"arXiv:1706.05587"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00747"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref53","first-page":"1","article-title":"SegNeXt: Rethinking convolutional attention design for semantic segmentation","volume-title":"Proc. NeurIPS","author":"Guo"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3292156"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_39"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3271523"},{"key":"ref57","first-page":"1","article-title":"HRFormer: High-resolution transformer for dense prediction","volume-title":"Proc. NeurIPS","author":"Yuan"},{"key":"ref58","first-page":"1","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. NeurIPS","author":"Xie"},{"key":"ref59","first-page":"1","article-title":"SegViT: Semantic segmentation with plain vision transformers","volume-title":"Proc. NeurIPS","author":"Zhang"},{"key":"ref60","article-title":"Representation separation for semantic segmentation with vision transformers","author":"Hong","year":"2023","journal-title":"arXiv:2212.13764"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref62","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. NeurIPS","author":"Schuhmann"},{"key":"ref63","first-page":"1","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. ICLR","author":"Bao"},{"key":"ref64","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_7"},{"key":"ref66","first-page":"1","article-title":"Understanding the robustness in vision transformers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhou"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_36"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3252807"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10739868\/10510312.pdf?arnumber=10510312","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:11:01Z","timestamp":1732666261000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10510312\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":70,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3395132","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}