{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T20:27:46Z","timestamp":1783542466617,"version":"3.55.0"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"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":["62203012"],"award-info":[{"award-number":["62203012"]}],"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":["U25A20486"],"award-info":[{"award-number":["U25A20486"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Anhui Higher Education Institutions of China","award":["2023AH030020"],"award-info":[{"award-number":["2023AH030020"]}]},{"name":"Natural Science Foundation of Anhui Higher Education Institutions of China","award":["2023AH050928"],"award-info":[{"award-number":["2023AH050928"]}]},{"name":"Open Research Fund of Anhui Provincial Key Laboratory of Advanced Detection and Intelligent Perception"},{"name":"Open Foundation of State Key Laboratory of High-end Compressor and System Technology","award":["SKL-YSJ202513"],"award-info":[{"award-number":["SKL-YSJ202513"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tcsvt.2026.3672884","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:39:46Z","timestamp":1773347986000},"page":"10577-10590","source":"Crossref","is-referenced-by-count":0,"title":["Unifying Modality and Scale: Visual Mamba for Feature Fusion in RGB-X Crowd Counting"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9332-7528","authenticated-orcid":false,"given":"Yaocong","family":"Hu","sequence":"first","affiliation":[{"name":"Anhui Provincial Key Laboratory of Advanced Detection and Intelligent Perception, Anhui Polytechnic University, Wuhu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengbo","family":"Jia","sequence":"additional","affiliation":[{"name":"Anhui Provincial Key Laboratory of Advanced Detection and Intelligent Perception, Anhui Polytechnic University, Wuhu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pindeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Anhui Provincial Key Laboratory of Advanced Detection and Intelligent Perception, Anhui Polytechnic University, Wuhu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1286-0839","authenticated-orcid":false,"given":"Ning","family":"Jiang","sequence":"additional","affiliation":[{"name":"Anhui Provincial Key Laboratory of Advanced Detection and Intelligent Perception, Anhui Polytechnic University, Wuhu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Anhui Polytechnic University, Wuhu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4474-4752","authenticated-orcid":false,"given":"Wenbo","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Anhui Polytechnic University, Wuhu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-1270","authenticated-orcid":false,"given":"Chao","family":"Xie","sequence":"additional","affiliation":[{"name":"College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huanjie","family":"Tao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6272-8660","authenticated-orcid":false,"given":"Tianming","family":"Ni","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Anhui Polytechnic University, Wuhu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0111-0108","authenticated-orcid":false,"given":"Teng","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3171250"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3293333"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3335157"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00335"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3208714"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3392500"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00283"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3445-y"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.70"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00120"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2016.03.021"},{"key":"ref12","article-title":"CCTrans: Simplifying and improving crowd counting with transformer","author":"Tian","year":"2021","journal-title":"arXiv:2109.14483"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01901"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-024-01318-8"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00192"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3124956"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3262978"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3171352"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115071"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2911128"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00479"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106885"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3203385"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3418111"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3321328"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3588815"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IC-NIDC54101.2021.9660586"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69544-6_30"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2023.104631"},{"key":"ref30","article-title":"Wavelet-guided misalignment-aware network for visible-infrared object detection","author":"Zhang","year":"2025","journal-title":"arXiv:2507.20146"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3356492"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3553478"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112481","article-title":"Dynamic proxy domain generalizes the crowd localization by better binary segmentation","volume":"172","author":"Gao","year":"2026","journal-title":"Pattern Recognit."},{"key":"ref34","article-title":"Context-coordinated multi-modal fusion network for RGB-T crowd counting","author":"Zhang","journal-title":"Available SSRN"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26284-5_2"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111376"},{"key":"ref37","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.107070","article-title":"CMFX: Cross-modal fusion network for RGB-X crowd counting","volume":"184","author":"Duan","year":"2025","journal-title":"Neural Netw."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00720"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3420449"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3540867"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3535330"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32885"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3362820"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-024-01642-z"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-024-01643-y"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"ref47","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021","journal-title":"arXiv:2111.00396"},{"key":"ref48","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3273"},{"key":"ref50","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024","journal-title":"arXiv:2401.09417"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00423"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3485721"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3767748"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3542995"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3599020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02183"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_13"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3530090"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3551723"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3535939"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3549750"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3414293"},{"key":"ref63","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112522","article-title":"Multi-modal mamba framework for RGB-T crowd counting with linear complexity","volume":"172","author":"Gan","year":"2026","journal-title":"Pattern Recognit."},{"issue":"2","key":"ref64","doi-asserted-by":"crossref","DOI":"10.1007\/s00371-025-04238-4","article-title":"DFMNet: Deep fusion mamba network for multimodal crowd counting","volume":"42","author":"Yang","year":"2026","journal-title":"Vis. Comput."},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref66","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00624"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00552"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3655110"},{"key":"ref70","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_45"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2025.3555712"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11598845\/11430616.pdf?arnumber=11430616","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T19:45:36Z","timestamp":1783539936000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11430616\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":73,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3672884","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}