{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T16:29:34Z","timestamp":1793377774611,"version":"4.5.0"},"reference-count":57,"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":["62176027"],"award-info":[{"award-number":["62176027"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Chongqing Talent","award":["cstc2024ycjh-bgzxm0082"],"award-info":[{"award-number":["cstc2024ycjh-bgzxm0082"]}]},{"name":"Joint Equipment Pre Research and Key"},{"name":"Project of the Ministry of Education","award":["8091B012207"],"award-info":[{"award-number":["8091B012207"]}]},{"name":"Central University Operating Expenses","award":["2024CDJGF-044"],"award-info":[{"award-number":["2024CDJGF-044"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3599097","type":"journal-article","created":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T18:48:19Z","timestamp":1755197299000},"page":"7444-7458","source":"Crossref","is-referenced-by-count":66,"title":["COFNet: Contrastive Object-Aware Fusion Using Box-Level Masks for Multispectral Object Detection"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1874-3641","authenticated-orcid":false,"given":"Mingliang","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Computer Science, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunyao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8388-7310","authenticated-orcid":false,"given":"Guangchao","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3761-1759","authenticated-orcid":false,"given":"Xuekai","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Computer Science, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9830-3955","authenticated-orcid":false,"given":"Huayan","family":"Pu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Mechanical Transmissions, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1314-5631","authenticated-orcid":false,"given":"Jun","family":"Luo","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Mechanical Transmissions, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1000-3937","authenticated-orcid":false,"given":"Weijia","family":"Jia","sequence":"additional","affiliation":[{"name":"BNU-UIC Institute of Artificial Intelligence and Future Networks, Beijing Normal University Zhuhai, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.09.015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109913"},{"key":"ref3","article-title":"Multispectral pedestrian detection via simultaneous detection and segmentation","author":"Li","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.02.005"},{"key":"ref5","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref6","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","author":"Li","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191080"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00389"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298706"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2015.11.002"},{"key":"ref11","first-page":"57","article-title":"Infrared and visible images fusion method based on discrete wavelet transform","volume":"28","author":"Zhan","year":"2017","journal-title":"J. Comput."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.4028\/www.scientific.net\/AMR.756-759.2850"},{"issue":"9","key":"ref13","first-page":"1643","article-title":"Infrared and visible image fusion with spectral graph wavelet transform","volume-title":"J. Opt. Soc. Amer. A","volume":"32","author":"Yan","year":"2015"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3207621"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3245607"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2013.2287891"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3160589"},{"issue":"7","key":"ref18","article-title":"A novel multi-model decision fusion network for object detection in remote sensing images","volume-title":"Remote Sens.","volume":"11","author":"Ma","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-18907-4_30"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3412417"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/s24134098"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00309"},{"issue":"12","key":"ref23","doi-asserted-by":"crossref","DOI":"10.3390\/s21124184","article-title":"Attention fusion for one-stage multispectral pedestrian detection","volume":"21","author":"Cao","year":"2021","journal-title":"Sensors"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00046"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3022623"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.181"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015720"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2537320"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00267"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01009"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3381377"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref35","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Caron","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref38","article-title":"Cross-modality fusion transformer for multispectral object detection","author":"Qingyun","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_9"},{"key":"ref40","article-title":"Removal and selection: Improving RGB-infrared object detection via coarse-to-fine fusion","author":"Zhao","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298706"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.5244\/c.30.73"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.36"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.11.017"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.08.005"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00523"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_46"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3099870"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3076466"},{"key":"ref50","article-title":"Improving RGB-infrared object detection with cascade alignment-guided transformer","volume-title":"Inf. Fusion","volume":"105","author":"Yuan","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3306870"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3272471"},{"key":"ref53","article-title":"[EB\/OL]","year":"2025"},{"key":"ref54","first-page":"108786","article-title":"Cross-modality attentive feature fusion for object detection in multispectral remote sensing imagery","volume":"130","author":"Fang","year":"2021"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3258666"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3293147"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11124580.pdf?arnumber=11124580","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T17:25:52Z","timestamp":1761153952000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11124580\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3599097","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}