{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T08:01:04Z","timestamp":1777104064098,"version":"3.51.4"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2024YFC3014900"],"award-info":[{"award-number":["2024YFC3014900"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tcsvt.2025.3578340","type":"journal-article","created":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T13:54:59Z","timestamp":1749563699000},"page":"11041-11053","source":"Crossref","is-referenced-by-count":2,"title":["Confidence-Driven Unimodal Interference Removal for Enhanced Multimodal Object Detection"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7282-0176","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"first","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3803-9763","authenticated-orcid":false,"given":"Shikui","family":"Wei","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4522-5460","authenticated-orcid":false,"given":"Sen","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4606-7174","authenticated-orcid":false,"given":"Ying","family":"Qin","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8581-9554","authenticated-orcid":false,"given":"Yao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00389"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00571"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00572"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612135"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612651"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00012"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110423"},{"key":"ref9","article-title":"Cross-modality fusion transformer for multispectral object detection","author":"Qingyun","year":"2021","journal-title":"arXiv:2111.00273"},{"key":"ref10","volume-title":"FreeTeledyne FLIR Thermal Dataset for Algorithm Training","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00289"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00174"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.3001665"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.17781\/p002618"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00327"},{"key":"ref19","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3300537"},{"key":"ref21","first-page":"41753","article-title":"Provable dynamic fusion for low-quality multimodal data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref22","first-page":"10944","article-title":"What makes multi-modal learning better than single (provably)","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3238524"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611928"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2876865"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3075323"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3178871"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3294003"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3221658"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/BF00994018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1997.1504"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref35","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref40","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv:1804.02767"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.10934"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref45","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref46","article-title":"Efficient DETR: Improving end-to-end object detector with dense prior","author":"Yao","year":"2021","journal-title":"arXiv:2104.01318"},{"key":"ref47","first-page":"107984","article-title":"YOLOv10: Real-time end-to-end object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191080"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2015.11.002"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298706"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3168279"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613849"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3229571"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109913"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3163847"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3306870"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3076466"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_46"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811999"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3315544"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3390\/math10213966"},{"key":"ref62","first-page":"1","article-title":"DFormer: Rethinking RGBD representation learning for semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yin"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref65","article-title":"Ultralytics\/YOLOv5: V6.0\u2014YOLOv5n \u2018nano\u2019 models, roboflow integration, TensorFlow export, OpenCV DNN support","author":"Jocher","year":"2021"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3258666"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108786"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00046"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3454631"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3539625"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"11","key":"ref73","first-page":"1","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van Der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11223720\/11029233.pdf?arnumber=11029233","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T18:47:37Z","timestamp":1762195657000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11029233\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":73,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3578340","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}