{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T06:17:49Z","timestamp":1782973069741,"version":"3.54.5"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62373009"],"award-info":[{"award-number":["62373009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017688","name":"Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology","doi-asserted-by":"publisher","award":["2024B1212010006"],"award-info":[{"award-number":["2024B1212010006"]}],"id":[{"id":"10.13039\/501100017688","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3544484","type":"journal-article","created":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T13:43:06Z","timestamp":1741009386000},"page":"1686-1699","source":"Crossref","is-referenced-by-count":16,"title":["MiLNet: Multiplex Interactive Learning Network for RGB-T Semantic Segmentation"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5745-5036","authenticated-orcid":false,"given":"Jinfu","family":"Liu","sequence":"first","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence and Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Peking University Shenzhen Graduate School, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7498-6541","authenticated-orcid":false,"given":"Hong","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence and Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Peking University Shenzhen Graduate School, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2284-1700","authenticated-orcid":false,"given":"Xia","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science, ETH Zürich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5289-6928","authenticated-orcid":false,"given":"Jiale","family":"Ren","sequence":"additional","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence and Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Peking University Shenzhen Graduate School, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0378-5209","authenticated-orcid":false,"given":"Xinhua","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence and Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Peking University Shenzhen Graduate School, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3122293"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3401020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2974099"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3293771"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref6","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Sys. (NIPS)","volume":"34","author":"Xie"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3326400"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54181-5_14"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00266"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01597"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3233089"},{"key":"ref12","first-page":"1","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin"},{"key":"ref13","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"OpenAI","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-81-322-3972-7_19"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3109518"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3208833"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3275314"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2904733"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.2993143"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206396"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196831"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/34.969114"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.852206"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.178"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00163"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00388"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.041"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00897"},{"key":"ref34","first-page":"134","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref36","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. Adv. neural Inf. Process. Syst.","volume":"34","author":"Chu"},{"key":"ref37","first-page":"4971","article-title":"SegViT: Semantic segmentation with plain vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Zhang"},{"key":"ref38","article-title":"Universal few-shot learning of dense prediction tasks with visual token matching","author":"Kim","year":"2023","journal-title":"arXiv:2303.14969"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00735"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00700"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_40"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_9"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_33"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3161852"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2021.110176"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-02687-7"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636084"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108881"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.11.056"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3216313"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3300537"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3349072"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3374793"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127913"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110092"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00464"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3099120"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20269"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3229359"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3164899"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3086618"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3211086"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191977"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3242651"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3349865"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref69","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/10908980.pdf?arnumber=10908980","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:10:14Z","timestamp":1770671414000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10908980\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3544484","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}