{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T20:06:42Z","timestamp":1780603602596,"version":"3.54.1"},"reference-count":48,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61801516"],"award-info":[{"award-number":["61801516"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3694554","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T19:50:38Z","timestamp":1779220238000},"page":"81813-81823","source":"Crossref","is-referenced-by-count":0,"title":["CAC-Net: Convolutional Additive Cross-Modal Fusion for Real-Time RGB-T Object Detection"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5649-8042","authenticated-orcid":false,"given":"Ziwen","family":"Zhu","sequence":"first","affiliation":[{"name":"Engineering University of the People’s Armed Police, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5074-1512","authenticated-orcid":false,"given":"Xiaoou","family":"Song","sequence":"additional","affiliation":[{"name":"Engineering University of the People’s Armed Police, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3937-9027","authenticated-orcid":false,"given":"Guangming","family":"Zhou","sequence":"additional","affiliation":[{"name":"Engineering University of the People’s Armed Police, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4150-1204","authenticated-orcid":false,"given":"Mingmei","family":"Chen","sequence":"additional","affiliation":[{"name":"Engineering University of the People’s Armed Police, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2797-2271","authenticated-orcid":false,"given":"Xiaobing","family":"Deng","sequence":"additional","affiliation":[{"name":"Engineering University of the People’s Armed Police, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.112722"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103414"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102246"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2026.113189"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3454631"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3599020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130505"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP55912.2026.11463789"},{"key":"ref9","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01802"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.127229"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3418965"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2025.3553747"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.129865"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01598"},{"key":"ref16","article-title":"CAS-ViT: Convolutional additive self-attention vision transformers for efficient mobile applications","author":"Zhang","year":"2024","journal-title":"arXiv:2408.03703"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111383"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889505"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.113003"},{"key":"ref20","article-title":"YOLOv12: Attention-centric real-time object detectors","author":"Tian","year":"2025","journal-title":"arXiv:2502.12524"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.32996"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103985"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.104110","article-title":"Regional defeats global: An efficient regional feature fusion via convolutional architecture for multispectral object detection","volume":"130","author":"Wang","year":"2026","journal-title":"Inf. Fusion"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.108421","article-title":"Balanced multi-modality knowledge mining for RGB-infrared object detection","volume":"196","author":"Ma","year":"2026","journal-title":"Neural Netw."},{"key":"ref25","article-title":"YOLOv11-RGBT: Towards a comprehensive single-stage multispectral object detection framework","author":"Wan","year":"2025","journal-title":"arXiv:2506.14696"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103895","article-title":"Multispectral state-space feature fusion: Bridging shared and cross-parametric interactions for object detection","volume":"127","author":"Shen","year":"2026","journal-title":"Inf. Fusion"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3539625"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103924","article-title":"CPMFusion: A method for infrared and visible image registration and fusion using modal correlation","volume":"127","author":"Xiao","year":"2026","journal-title":"Inf. Fusion"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3450584"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2025.105468","article-title":"Joint transformer and mamba fusion for multispectral object detection","volume":"156","author":"Li","year":"2025","journal-title":"Image Vis. Comput."},{"key":"ref31","article-title":"CrossModalNet: A dual-modal object detection network based on cross-modal fusion and channel interaction","volume":"298","author":"Li","year":"2026","journal-title":"Expert Syst. Appl."},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3437685"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2025.3599733"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3612939"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref36","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2025.3648007"},{"key":"ref38","article-title":"DPDETR: Decoupled position detection transformer for infrared-visible object detection","author":"Guo","year":"2024","journal-title":"arXiv:2408.06123"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3375634"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3599097"},{"key":"ref41","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109913","article-title":"ICAFusion: Iterative cross-attention guided feature fusion for multispectral object detection","volume":"145","author":"Shen","year":"2024","journal-title":"Pattern Recognit."},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3443455"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3551947"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.1016\/j.infrared.2025.106346","article-title":"MRT-DETR: A robust visible\u2013infrared object detector with adaptive cross-modal feature fusion","volume":"153","author":"An","year":"2026","journal-title":"Infr. Phys. Technol."},{"key":"ref45","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2026.131570","article-title":"A novel implicit cross-attention framework for RGB-T object detection","volume":"314","author":"Liu","year":"2026","journal-title":"Expert Syst. Appl."},{"key":"ref46","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2026.113350","article-title":"Lightweight modal-guided cross-attention fusion network for visible-infrared object detection","volume":"177","author":"Wu","year":"2026","journal-title":"Pattern Recognit."},{"key":"ref47","article-title":"Cross-modality fusion transformer for multispectral object detection","author":"Qingyun","year":"2021","journal-title":"arXiv:2111.00273"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3612257"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11523476.pdf?arnumber=11523476","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:57:17Z","timestamp":1780603037000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11523476\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3694554","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}