{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T08:06:45Z","timestamp":1784102805886,"version":"3.55.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"R&D Program of Beijing Municipal Education Commission","award":["KM202410017006"],"award-info":[{"award-number":["KM202410017006"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-026-08719-8","type":"journal-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T07:33:24Z","timestamp":1784100804000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MATM-Net: a real-time multi-modal object detection network based on mamba and attention mechanism"],"prefix":"10.1007","volume":"82","author":[{"given":"Lili","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenshuo","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongxin","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"key":"8719_CR1","first-page":"1","volume":"62","author":"M Yuan","year":"2024","unstructured":"Yuan M, Wei X (2024) C2Former: calibrated and complementary transformer for RGB-infrared object detection. IEEE Trans Geosci Remote Sens 62:1\u201312","journal-title":"IEEE Trans Geosci Remote Sens"},{"issue":"7","key":"8719_CR2","doi-asserted-by":"publisher","first-page":"7101","DOI":"10.1109\/TCSVT.2025.3539625","volume":"35","author":"K Hu","year":"2025","unstructured":"Hu K, He Y, Li Y, Zhao J, Chen S, Kang Y (2025) EI2Det: edge-guided illumination-aware interactive learning for visible-infrared object detection. IEEE Trans Circuits Syst Video Technol 35(7):7101\u20137115","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"8719_CR3","doi-asserted-by":"crossref","unstructured":"Yang X, Qian Y, Zhu H, Wang C, Yang M (2022) BAANet: learning bi-directional adaptive attention gates for multispectral pedestrian detection. In: 2022 International Conference on Robotics and Automation (ICRA), pp 2920\u20132926","DOI":"10.1109\/ICRA46639.2022.9811999"},{"key":"8719_CR4","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"8719_CR5","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. https:\/\/arxiv.org\/abs\/1409.1556"},{"issue":"12","key":"8719_CR6","doi-asserted-by":"publisher","first-page":"20628","DOI":"10.1109\/TITS.2024.3450584","volume":"25","author":"Y Xing","year":"2024","unstructured":"Xing Y, Yang S, Wang S, Zhang S, Liang G, Zhang X, Zhang Y (2024) MS-DETR: multispectral pedestrian detection transformer with loosely coupled fusion and modality-balanced optimization. IEEE Trans Intell Transp Syst 25(12):20628\u201320642","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"8719_CR7","doi-asserted-by":"crossref","unstructured":"Liu J, Zhang S, Wang S, Metaxas DN (2016) Multispectral deep neural networks for pedestrian detection. https:\/\/arxiv.org\/abs\/1611.02644","DOI":"10.5244\/C.30.73"},{"key":"8719_CR8","doi-asserted-by":"crossref","unstructured":"Lee W-Y, Jovanov L, Philips W (2023) Cross-modality attention and multimodal fusion transformer for pedestrian detection. In: Computer Vision \u2013 ECCV 2022 Workshops. Springer, Cham, pp 608\u2013623","DOI":"10.1007\/978-3-031-25072-9_41"},{"key":"8719_CR9","doi-asserted-by":"crossref","unstructured":"Fang Q, Han D, Wang Z (2021) Cross-Modality fusion transformer for multispectral object detection. https:\/\/arxiv.org\/abs\/2111.00273","DOI":"10.2139\/ssrn.4227745"},{"issue":"3","key":"8719_CR10","doi-asserted-by":"publisher","first-page":"2080","DOI":"10.1109\/TIV.2024.3443264","volume":"10","author":"Z Wang","year":"2025","unstructured":"Wang Z, Liao X, Yuan J, Yao Y, Li Z (2025) CDC-YOLOFusion: leveraging cross-scale dynamic convolution fusion for visible-infrared object detection. IEEE Trans Intell Veh 10(3):2080\u20132093","journal-title":"IEEE Trans Intell Veh"},{"key":"8719_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2026.113350","volume":"177","author":"W Wu","year":"2026","unstructured":"Wu W, Zhang H, Zhang X, Yin H, Zhang Y (2026) Lightweight modal-guided cross-attention fusion network for visible-infrared object detection. Pattern Recogn 177:113350","journal-title":"Pattern Recogn"},{"key":"8719_CR12","doi-asserted-by":"crossref","unstructured":"Zhu H, Dong W, Yang L, Li H, Yang Y, Ren Y, Zhu Q, Feng Z, Li C, Lin S, Wang R, Luo X, Zhang B (2025) WaveMamba: wavelet-driven mamba fusion for RGB-infrared object detection. https:\/\/arxiv.org\/abs\/2507.18173","DOI":"10.1109\/ICCV51701.2025.01044"},{"key":"8719_CR13","doi-asserted-by":"publisher","first-page":"464","DOI":"10.1007\/978-3-031-73383-3_27","volume-title":"Computer vision \u2013 ECCV 2024","author":"J Guo","year":"2025","unstructured":"Guo J, Gao C, Liu F, Meng D, Gao X (2025) DAMSDet: dynamic adaptive multispectral detection transformer with competitive query selection and adaptive feature fusion. Computer vision \u2013 ECCV 2024. Springer, Cham, pp 464\u2013481"},{"issue":"4","key":"8719_CR14","doi-asserted-by":"publisher","first-page":"3017","DOI":"10.1109\/TCSVT.2023.3306870","volume":"34","author":"Q Li","year":"2024","unstructured":"Li Q, Zhang C, Hu Q, Zhu P, Fu H, Chen L (2024) Stabilizing multispectral pedestrian detection with evidential hybrid fusion. IEEE Trans Circuits Syst Video Technol 34(4):3017\u20133029","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"8719_CR15","volume":"130","author":"C Jiang","year":"2024","unstructured":"Jiang C, Ren H, Yang H, Huo H, Zhu P, Yao Z, Li J, Sun M, Yang S (2024) M2FNet: multi-modal fusion network for object detection from visible and thermal infrared images. Int J Appl Earth Obs Geoinf 130:103918","journal-title":"Int J Appl Earth Obs Geoinf"},{"key":"8719_CR16","doi-asserted-by":"crossref","unstructured":"Yuan M, Cui B, Zhao T, Wang J, Fu S, Yang X, Wei X (2025) UniRGB-IR: a unified framework for visible-infrared semantic tasks via adapter tuning. In: Proceedings of the 33rd ACM International Conference on Multimedia, pp 2409\u20132418","DOI":"10.1145\/3746027.3754806"},{"key":"8719_CR17","doi-asserted-by":"crossref","unstructured":"Jang J, Park C, Kim H, Lee J, Paik J (2025) Multispectral object detection enhanced by cross-modal information complementary and cosine similarity channel resampling modules. In: 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp 9437\u20139446","DOI":"10.1109\/WACV61041.2025.00914"},{"key":"8719_CR18","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee J-Y, Kweon IS (2018) CBAM: convolutional block attention module. In: Computer Vision \u2013 ECCV 2018. Springer, Cham, pp 3\u201319","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"8719_CR19","doi-asserted-by":"crossref","unstructured":"Xia Z, Pan X, Song S, Li LE, Huang G (2022) Vision transformer with deformable attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 4784\u20134793","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"8719_CR20","doi-asserted-by":"crossref","unstructured":"Vaswani A, Ramachandran P, Srinivas A, Parmar N, Hechtman B, Shlens J (2021) Scaling local self-attention for parameter efficient visual backbones. https:\/\/arxiv.org\/abs\/2103.12731","DOI":"10.1109\/CVPR46437.2021.01270"},{"key":"8719_CR21","doi-asserted-by":"crossref","unstructured":"Hou Q, Zhou D, Feng J (2021) Coordinate attention for efficient mobile network design. https:\/\/arxiv.org\/abs\/2103.02907","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"8719_CR22","unstructured":"Gu A, Dao T (2024) Mamba: linear-time sequence modeling with selective state spaces. https:\/\/arxiv.org\/abs\/2312.00752"},{"key":"8719_CR23","doi-asserted-by":"crossref","unstructured":"Liu Y, Tian Y, Zhao Y, Yu H, Xie L, Wang Y, Ye Q, Jiao J, Liu Y (2024) VMamba: visual state space model. https:\/\/arxiv.org\/abs\/2401.10166","DOI":"10.52202\/079017-3273"},{"key":"8719_CR24","unstructured":"Zhu L, Liao B, Zhang Q, Wang X, Liu W, Wang X (2024) Vision mamba: efficient visual representation learning with bidirectional state space model. https:\/\/arxiv.org\/abs\/2401.09417"},{"key":"8719_CR25","doi-asserted-by":"crossref","unstructured":"Li T, Ye M, Wu T, Li N, Li S, Tang S, Ji L (2025) Pseudo visible feature fine-grained fusion for thermal object detection. In: 2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 6710\u20136719","DOI":"10.1109\/CVPR52734.2025.00629"},{"key":"8719_CR26","doi-asserted-by":"publisher","first-page":"7392","DOI":"10.1109\/TMM.2025.3599020","volume":"27","author":"W Dong","year":"2025","unstructured":"Dong W, Zhu H, Lin S, Luo X, Shen Y, Guo G, Zhang B (2025) Fusion-Mamba: fusion-mamba for cross-modality object detection. IEEE Trans Multimedia 27:7392\u20137406","journal-title":"IEEE Trans Multimedia"},{"key":"8719_CR27","doi-asserted-by":"crossref","unstructured":"Liu J, Fan X, Huang Z, Wu G, Liu R, Zhong W, Luo Z (2022) Target-aware dual adversarial learning and a multi-scenario multi-modality benchmark to fuse infrared and visible for object detection. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 5792\u20135801","DOI":"10.1109\/CVPR52688.2022.00571"},{"issue":"7","key":"8719_CR28","doi-asserted-by":"publisher","first-page":"6088","DOI":"10.1109\/TPAMI.2025.3544621","volume":"47","author":"X Ying","year":"2025","unstructured":"Ying X, Xiao C, An W, Li R, He X, Li B, Cao X, Li Z, Wang Y, Hu M, Xu Q, Lin Z, Li M, Zhou S, Liu L, Sheng W (2025) Visible-thermal tiny object detection: a benchmark dataset and baselines. IEEE Trans Pattern Anal Mach Intell 47(7):6088\u20136096","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8719_CR29","unstructured":"Jia X, Zhu C, Li M, Tang W, Liu S, Zhou W (2023) LLVIP: a visible-infrared paired dataset for low-light vision. https:\/\/arxiv.org\/abs\/2108.10831"},{"key":"8719_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109913","volume":"145","author":"J Shen","year":"2024","unstructured":"Shen J, Chen Y, Liu Y, Zuo X, Fan H, Yang W (2024) ICAFusion: iterative cross-attention guided feature fusion for multispectral object detection. Pattern Recognit 145:109913","journal-title":"Pattern Recognit"},{"issue":"7","key":"8719_CR31","doi-asserted-by":"publisher","first-page":"13276","DOI":"10.1109\/TNNLS.2024.3443455","volume":"36","author":"X Zhang","year":"2025","unstructured":"Zhang X, Zhang X, Wang J, Ying J, Sheng Z, Yu H, Li C, Shen H-L (2025) TFDet: target-aware fusion for RGB-T pedestrian detection. IEEE Trans Neural Netw Learn Syst 36(7):13276\u201313290","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"8","key":"8719_CR32","first-page":"8673","volume":"39","author":"Y Xiao","year":"2025","unstructured":"Xiao Y, Xu T, Xin Y, Li J (2025) FBRT-YOLO: faster and better for real-time aerial image detection. Proc AAAI Conf Artif Intell 39(8):8673\u20138681","journal-title":"Proc AAAI Conf Artif Intell"},{"issue":"19","key":"8719_CR33","doi-asserted-by":"publisher","DOI":"10.3390\/rs15194887","volume":"15","author":"M He","year":"2023","unstructured":"He M, Wu Q, Ngan KN, Jiang F, Meng F, Xu L (2023) Misaligned RGB-infrared object detection via adaptive dual-discrepancy calibration. Remote Sens 15(19):4887","journal-title":"Remote Sens"},{"key":"8719_CR34","doi-asserted-by":"crossref","unstructured":"Li K, Wang D, Hu Z, Li S, Ni W, Zhao L, Wang Q (2024) FD2-Net: frequency-driven feature decomposition network for infrared-visible object detection. https:\/\/arxiv.org\/abs\/2412.09258","DOI":"10.1609\/aaai.v39i5.32507"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-026-08719-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-026-08719-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-026-08719-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T07:33:30Z","timestamp":1784100810000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-026-08719-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,15]]},"references-count":34,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["8719"],"URL":"https:\/\/doi.org\/10.1007\/s11227-026-08719-8","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,15]]},"assertion":[{"value":"4 May 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interest","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"567"}}