{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T10:10:44Z","timestamp":1773137444923,"version":"3.50.1"},"reference-count":90,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62176035"],"award-info":[{"award-number":["62176035"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62201111"],"award-info":[{"award-number":["62201111"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017607","name":"Shenzhen Municipal Fundamental Research Program","doi-asserted-by":"publisher","award":["JCYJ20240813151216022"],"award-info":[{"award-number":["JCYJ20240813151216022"]}],"id":[{"id":"10.13039\/501100017607","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2025.3640020","type":"journal-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:43:18Z","timestamp":1764787398000},"page":"1469-1482","source":"Crossref","is-referenced-by-count":0,"title":["A Fusion-Enhanced Network for Infrared and Visible High-Level Vision Tasks"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1845-9907","authenticated-orcid":false,"given":"Fangcen","family":"Liu","sequence":"first","affiliation":[{"name":"School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4174-4148","authenticated-orcid":false,"given":"Chenqiang","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4899-8474","authenticated-orcid":false,"given":"Fang","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, School of Engineering, University of California, Merced, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0691-7966","authenticated-orcid":false,"given":"Pengcheng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Hainan University, Haikou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8957-8419","authenticated-orcid":false,"given":"Junjie","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1294-8283","authenticated-orcid":false,"given":"Deyu","family":"Meng","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_24"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3266487"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3349072"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3275538"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3122004"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3233089"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3268209"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3410113"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3405714"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01952-1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00571"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01341"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00012"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3306870"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3161852"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.01.016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3174338"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3393298"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3374793"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3381377"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3266452"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3289142"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3268063"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3350926"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-025-00099-6"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00363"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3362475"},{"key":"ref30","first-page":"197","article-title":"SatMAE: Pre-training transformers for temporal and multi-spectral satellite imagery","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Cong","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/rs16020327"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"ref33","first-page":"38728","article-title":"mplug-2: A modularized multi-modal foundation model across text, image and video","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01050"},{"key":"ref35","first-page":"35632","article-title":"McMAE: Masked convolution meets masked autoencoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Gao","year":"2022"},{"key":"ref36","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3408154"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02704"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref42","article-title":"Meta-transformer: A unified framework for multimodal learning","author":"Zhang","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02510"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02501"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00572"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101870"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00745"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00266"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611200"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3300537"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00116"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00046"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73383-3_27"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_20"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3077767"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3242775"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612466"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3234702"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3233131"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00678"},{"key":"ref62","article-title":"SpiderMesh: Spatial-aware demand-guided recursive meshing for RGB-T semantic segmentation","author":"Fan","year":"2023"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206396"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.03.007"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196831"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611738"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00389"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-1702-6_36"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924578"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3171688"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3272269"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO58561.2023.10354613"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127913"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3247175"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3208833"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3086618"},{"key":"ref77","article-title":"HAPNet: Toward superior RGB-thermal scene parsing via hybrid, asymmetric, and progressive heterogeneous feature fusion","author":"Li","year":"2024"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref79","article-title":"MMSegmentation: OpenmmLab semantic segmentation toolbox and benchmark","author":"Contributors","year":"2020"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20269"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109913"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_9"},{"key":"ref83","article-title":"Cross-modality fusion transformer for multispectral object detection","author":"Qingyun","year":"2021"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3443455"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref86","article-title":"MMDetection: Open mmlab detection toolbox and benchmark","author":"Chen","year":"2019"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00720"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3077058"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02020-y"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11274403.pdf?arnumber=11274403","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T19:59:12Z","timestamp":1773086352000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11274403\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":90,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3640020","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}