{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T15:53:31Z","timestamp":1774626811543,"version":"3.50.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"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":["62272227"],"award-info":[{"award-number":["62272227"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tetci.2024.3449911","type":"journal-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T14:01:01Z","timestamp":1725890461000},"page":"202-212","source":"Crossref","is-referenced-by-count":3,"title":["MUSTER: A Multi-Scale Transformer-Based Decoder for Semantic Segmentation"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8450-341X","authenticated-orcid":false,"given":"Jing","family":"Xu","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9466-6318","authenticated-orcid":false,"given":"Wentao","family":"Shi","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4492-5430","authenticated-orcid":false,"given":"Pan","family":"Gao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}]},{"given":"Qizhu","family":"Li","sequence":"additional","affiliation":[{"name":"TikTok Pte. Ltd., Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7706-553X","authenticated-orcid":false,"given":"Zhengwei","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"key":"ref2","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref4","first-page":"7262","article-title":"Segmenter: Tranfsformer for semantic segmentation","volume-title":"Proc. Comput. Vis. Pattern Recognit.","author":"Strudel","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.04.024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00068"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref10","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Comput. Vis. Pattern Recognit.","author":"Xie","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref12","article-title":"ViT-LSLA: Vision transformer with light self-limited-attention","author":"Hechen","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103280"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20144"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059968"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3154443"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/S0031-3203(00)00149-7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.200"},{"key":"ref24","first-page":"19","article-title":"Markov random fields in statistics","author":"Clifford","year":"1990","journal-title":"Disorder Phys. Syst.: A. Vol. Honour John M. Hammersley"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP55362.2022.9949177"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106330"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3107449"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00762"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25079"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/228"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01169"},{"key":"ref35","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","author":"Chu","year":"2024"},{"key":"ref36","first-page":"12124","article-title":"CSWin transformer: A general vision transformer backbone with cross-shaped windows","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Dong","year":"2021"},{"key":"ref37","article-title":"Shuffle transformer: Rethinking spatial shuffle for vision transformer","volume-title":"Proc. Comput. Vis. Pattern Recognit.","author":"Huang","year":"2021"},{"key":"ref38","article-title":"LocalVit: Bringing locality to vision transformers","volume-title":"Proc. Comput. Vis. Pattern Recognit.","author":"Li","year":"2021"},{"key":"ref39","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Douze","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CCAI55564.2022.9807763"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00299"},{"key":"ref43","first-page":"30392","article-title":"Early convolutions help transformers see better","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","author":"Xiao","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-45183-7_27"},{"key":"ref49","article-title":"Decoupled weight decay regularization","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00366"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"ref55","article-title":"MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark","author":"Contributors","year":"2020"},{"key":"ref56","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref57","article-title":"Recurseed and edgepredictmix: Single-stage learning is sufficient for weakly-supervised semantic segmentation","author":"Jo","year":"2022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00426"},{"key":"ref59","article-title":"Papers with code","year":"2023"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7433297\/10850886\/10669920.pdf?arnumber=10669920","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T19:05:55Z","timestamp":1764183955000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10669920\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":59,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2024.3449911","relation":{},"ISSN":["2471-285X"],"issn-type":[{"value":"2471-285X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}