{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T05:48:44Z","timestamp":1785822524558,"version":"3.56.0"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Research and Application of Control System Technology for Group Operation of Heavy-Haul Trains Program, China Shenhua Energy Company Ltd.","award":["(2022) 127"],"award-info":[{"award-number":["(2022) 127"]}]},{"DOI":"10.13039\/501100002822","name":"High Performance Computing Center of Central South University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002822","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["202006370295"],"award-info":[{"award-number":["202006370295"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tip.2023.3305090","type":"journal-article","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T17:17:31Z","timestamp":1692379051000},"page":"4757-4772","source":"Crossref","is-referenced-by-count":72,"title":["FsaNet: Frequency Self-Attention for Semantic Segmentation"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9372-1362","authenticated-orcid":false,"given":"Fengyu","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Traffic and Transportation Engineering, Central South University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashkan","family":"Panahi","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Chalmers University of Technology, Göteborg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5098-3306","authenticated-orcid":false,"given":"Guangjun","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Traffic and Transportation Engineering, Central South University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref57","article-title":"Rethinking attention with performers","author":"choromanski","year":"2020","journal-title":"arXiv 2009 14794"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref56","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","author":"katharopoulos","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref59","first-page":"1","article-title":"SOFT: Softmax-free transformer with linear complexity","volume":"34","author":"lu","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"xie","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref58","article-title":"UFO-ViT: High performance linear vision transformer without softmax","author":"song","year":"2021","journal-title":"arXiv 2109 14382"},{"key":"ref53","article-title":"CSWin transformer: A general vision transformer backbone with cross-shaped windows","author":"dong","year":"2021","journal-title":"arXiv 2107 00652"},{"key":"ref52","first-page":"1","article-title":"A2-Nets: Double attention networks","volume":"31","author":"chen","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01828"},{"key":"ref55","first-page":"1","article-title":"Reformer: The efficient transformer","author":"kitaev","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref10","first-page":"10326","article-title":"K-Net: Towards unified image segmentation","volume":"34","author":"zhang","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref54","article-title":"Generating long sequences with sparse transformers","author":"child","year":"2019","journal-title":"arXiv 1904 10509"},{"key":"ref17","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume":"34","author":"cheng","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume":"34","author":"chu","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref18","article-title":"On the connection between local attention and dynamic depth-wise convolution","author":"han","year":"2021","journal-title":"arXiv 2106 04263"},{"key":"ref51","article-title":"Linear attention mechanism: An efficient attention for semantic segmentation","author":"li","year":"2020","journal-title":"arXiv 2007 14902"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00926"},{"key":"ref46","article-title":"Interlaced sparse self-attention for semantic segmentation","author":"huang","year":"2019","journal-title":"arXiv 1907 12273"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3007032"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00690"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00068"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_12"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00959"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00261"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00721"},{"key":"ref49","first-page":"173","article-title":"Object-contextual representations for semantic segmentation","author":"yuan","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6805"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3042065"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2878975"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01515-2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2845918"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01368"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"ref34","first-page":"1","article-title":"Dual graph convolutional network for semantic segmentation","author":"zhang","year":"2019","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3099369"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00052"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3099366"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00747"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref2","first-page":"1","article-title":"An image is worth 16?16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_26"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00533"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00770"},{"key":"ref23","first-page":"9373","article-title":"Cars can’t fly up in the sky: Improving urban-scene segmentation via height-driven attention networks","author":"choi","year":"2020","journal-title":"Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref67","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Computer Vision—ECCV 2014"},{"key":"ref26","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"chen","year":"2017","journal-title":"arXiv 1706 05587"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2962685"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref64","year":"2020","journal-title":"M contributors"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref66","author":"everingham","year":"2012","journal-title":"The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results"},{"key":"ref21","article-title":"Next-ViT: Next generation vision transformer for efficient deployment in realistic industrial scenarios","author":"li","year":"2022","journal-title":"arXiv 2207 05501"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"ref27","first-page":"801","article-title":"Encoder–decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00366"},{"key":"ref60","article-title":"An attention free transformer","author":"zhai","year":"2021","journal-title":"arXiv 2105 14103"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01270"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9991910\/10224845.pdf?arnumber=10224845","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T18:15:57Z","timestamp":1695060957000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10224845\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3305090","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}