{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T20:26:42Z","timestamp":1783628802591,"version":"3.55.0"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"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":["62322117"],"award-info":[{"award-number":["62322117"]}],"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":["62371365"],"award-info":[{"award-number":["62371365"]}],"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":["U24B20136"],"award-info":[{"award-number":["U24B20136"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tcsvt.2024.3520318","type":"journal-article","created":{"date-parts":[[2024,12,19]],"date-time":"2024-12-19T14:41:24Z","timestamp":1734619284000},"page":"4713-4726","source":"Crossref","is-referenced-by-count":13,"title":["SeaDATE: Remedy Dual-Attention Transformer With Semantic Alignment via Contrast Learning for Multimodal Object Detection"],"prefix":"10.1109","volume":"35","author":[{"given":"Shuhan","family":"Dong","sequence":"first","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8310-024X","authenticated-orcid":false,"given":"Weiying","family":"Xie","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8906-7830","authenticated-orcid":false,"given":"Danian","family":"Yang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0234-6270","authenticated-orcid":false,"given":"Yunsong","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3111-1116","authenticated-orcid":false,"given":"Jiaqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayuan","family":"Tian","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0851-6565","authenticated-orcid":false,"given":"Jie","family":"Lei","sequence":"additional","affiliation":[{"name":"School of Electrical and Data Engineering, University of Technology Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deep learning for generic object detection: A survey","author":"Liu","year":"2018","journal-title":"arXiv:1809.02165"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107992"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3157594"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3067107"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3264658"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3439557"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.110080"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCA49541.2020.9250836"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2876865"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2972974"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2926164"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1080\/09500341003693011"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3241196"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.73"},{"key":"ref15","article-title":"Multispectral pedestrian detection via simultaneous detection and segmentation","author":"Li","year":"2018","journal-title":"arXiv:1808.04818"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.inffus.2018.09.015","article-title":"Cross-modality interactive attention network for multispectral pedestrian detection","volume":"50","author":"Zhang","year":"2019","journal-title":"Inf. Fusion"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.02.004"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2738401"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3387732"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TLA.2024.10412035"},{"key":"ref21","article-title":"Multimodal object detection via probabilistic ensembling","author":"Chen","year":"2021","journal-title":"arXiv:2104.02904"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3160589"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.36"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2021.106990","article-title":"A robust and fast multispectral pedestrian detection deep network","volume":"227","author":"Ding","year":"2021","journal-title":"Knowledge-Based Syst."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3289170"},{"key":"ref26","article-title":"Cross-modality fusion transformer for multispectral object detection","author":"Qingyun","year":"2021","journal-title":"arXiv:2111.00273"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/PRML52754.2021.9520732"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3296745"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00320"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3306361"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/141"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8435-0_32"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3292615"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3109895"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3245607"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref42","article-title":"R-FCN: Object detection via region-based fully convolutional networks","author":"Dai","year":"2016","journal-title":"arXiv:1605.06409"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref45","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv:1804.02767"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.10934"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00046"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3238181"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_46"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00311"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3390\/rs14092020"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3266487"},{"key":"ref53","article-title":"VoxelNextFusion: A simple, unified and effective voxel fusion framework for multi-modal 3D object detection","author":"Song","year":"2024","journal-title":"arXiv:2401.02702"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3127149"},{"key":"ref56","first-page":"509","article-title":"Multispectral pedestrian detection using deep fusion convolutional neural Networks.","volume-title":"Proc. Eur. Symp. Artif. Neural Netw. (ESANN)","author":"Wagner"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.08.005"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00523"},{"key":"ref59","article-title":"Learning to generate diverse dance motions with transformer","author":"Li","year":"2020","journal-title":"arXiv:2008.08171"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00374"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3247607"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3265751"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02201-9"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref66","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref68","article-title":"ContrastAlign: Toward robust BEV feature alignment via contrastive learning for multi-modal 3D object detection","author":"Song","year":"2024","journal-title":"arXiv:2405.16873"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00727"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00721"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191080"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10989278\/10807244.pdf?arnumber=10807244","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T19:45:50Z","timestamp":1783626350000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10807244\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":71,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3520318","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}