{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T04:30:08Z","timestamp":1768797008559,"version":"3.49.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T00:00:00Z","timestamp":1718323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T00:00:00Z","timestamp":1718323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural science foundation of China","doi-asserted-by":"crossref","award":["82370512"],"award-info":[{"award-number":["82370512"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"project of Key lab of digital signal and image Processing of Guangdong province","award":["2022GDDSIPL-03"],"award-info":[{"award-number":["2022GDDSIPL-03"]}]},{"name":"open fund project of Key Laboratory of System Control and Information Processing","award":["Scip202105"],"award-info":[{"award-number":["Scip202105"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1007\/s00138-024-01564-w","type":"journal-article","created":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T15:01:40Z","timestamp":1718377300000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MFMANet: a multispectral pedestrian detection network using multi-resolution RGB feature reuse with multi-scale FIR attentions"],"prefix":"10.1007","volume":"35","author":[{"given":"Jiaren","family":"Guo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuzhen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianyin","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihao","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanyun","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,6,14]]},"reference":[{"issue":"9","key":"1564_CR1","doi-asserted-by":"publisher","first-page":"4913","DOI":"10.1109\/TPAMI.2021.3076733","volume":"44","author":"J Cao","year":"2021","unstructured":"Cao, J., Pang, Y., Xie, J., Khan, F.S., Shao, L.: From handcrafted to deep features for pedestrian detection: A survey. IEEE Trans. Pattern Anal. Mach. Intell. 44(9), 4913\u20134934 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"1564_CR2","doi-asserted-by":"publisher","first-page":"1037","DOI":"10.3390\/app13021037","volume":"13","author":"D Hong","year":"2023","unstructured":"Hong, D., et al.: Multi-task learning for building extraction and change detection from Remote sensing images. Appl. Sci. 13(2), 1037 (2023)","journal-title":"Appl. Sci."},{"key":"1564_CR3","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1016\/j.inffus.2022.12.007","volume":"92","author":"Y Rao","year":"2023","unstructured":"Rao, Y., et al.: AT-GAN: A generative adversarial network with attention and transition for infrared and visible image fusion. Inform. Fusion. 92, 336\u2013349 (2023)","journal-title":"Inform. Fusion"},{"key":"1564_CR4","doi-asserted-by":"crossref","unstructured":"Zhou, Z., et al.: Rgb-event fusion for moving object detection in autonomous driving. 2023 IEEE International Conference on Robotics and Automation (ICRA). IEEE, (2023)","DOI":"10.1109\/ICRA48891.2023.10161563"},{"key":"1564_CR5","doi-asserted-by":"crossref","unstructured":"Bavirisetti, D., Prasad, G.X., Liu, G.: Multi-sensor image fusion based on fourth order partial differential Eq.\u00a02017 20th International conference on information fusion (Fusion). IEEE, (2017)","DOI":"10.23919\/ICIF.2017.8009719"},{"key":"1564_CR6","unstructured":"Yan, C., et al.: Cross-modality complementary information fusion for multispectral pedestrian detection. Neural Comput. Appl. : 1\u201326. (2023)"},{"key":"1564_CR7","unstructured":"Wanqi, J.: A real-time multi-modal fusion model for visible and infrared images: A light-weight and real-time CNN-based fusion model for visible and infrared images in surveillance. (2023)"},{"issue":"8","key":"1564_CR8","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1049\/iet-cvi.2018.5315","volume":"12","author":"Y Chen","year":"2018","unstructured":"Chen, Y., Xie, H., Shin, H.: Multi-layer fusion techniques using a CNN for multispectral pedestrian detection. IET Comput. Vision. 12(8), 1179\u20131187 (2018)","journal-title":"IET Comput. Vision"},{"key":"1564_CR9","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Multispectral fusion for object detection with cyclic fuse-and-refine blocks. 2020 IEEE International conference on image processing (ICIP). IEEE, (2020)","DOI":"10.1109\/ICIP40778.2020.9191080"},{"key":"1564_CR10","doi-asserted-by":"publisher","first-page":"103178","DOI":"10.1016\/j.infrared.2019.103178","volume":"105","author":"D Pei","year":"2020","unstructured":"Pei, D., et al.: A fast RetinaNet fusion framework for multi-spectral pedestrian detection. Infrared Phys. Technol. 105, 103178 (2020)","journal-title":"Infrared Phys. Technol."},{"key":"1564_CR11","doi-asserted-by":"publisher","first-page":"9396","DOI":"10.1109\/TPAMI.2021.3126387","volume":"44","author":"C Li","year":"2022","unstructured":"Li, C., Guo, C., Han, L., Jiang, J., Cheng, M.M., Gu, J., Loy, C.C.: Low-light image and video enhancement using deep learning:A Survey. IEEE Trans. Pattern Anal. Mach. Intell. 44, 9396\u20139416 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1564_CR12","doi-asserted-by":"crossref","unstructured":"Chen, Z., Liang, Y., Du, M.: Attention-based Broad Self-guided Network for Low-light Image Enhancement. In Proceedings of the 26th International Conference on Pattern Recognition (ICPR), Montreal, QC, Canada, 21\u201325 August ; pp. 31\u201338. (2022)","DOI":"10.1109\/ICPR56361.2022.9956143"},{"key":"1564_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.inffus.2022.06.008","volume":"88","author":"Y Cao","year":"2022","unstructured":"Cao, Y., et al.: Locality guided cross-modal feature aggregation and pixel-level fusion for multispectral pedestrian detection. Inform. Fusion. 88, 1\u201311 (2022)","journal-title":"Inform. Fusion"},{"key":"1564_CR14","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: Multispectral deep neural networks for pedestrian detection. arXiv preprint arXiv:1611.02644 (2016)","DOI":"10.5244\/C.30.73"},{"key":"1564_CR15","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.inffus.2018.09.015","volume":"50","author":"L Zhang","year":"2019","unstructured":"Zhang, L., et al.: Cross-modality interactive attention network for multispectral pedestrian detection. Inform. Fusion. 50, 20\u201329 (2019)","journal-title":"Inform. Fusion"},{"key":"1564_CR16","doi-asserted-by":"crossref","unstructured":"Chowdary, G., Jignesh: and Zhaozheng Yin. Diffusion Transformer U-Net for Medical Image Segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer Nature Switzerland, (2023)","DOI":"10.1007\/978-3-031-43901-8_59"},{"key":"1564_CR17","unstructured":"Bochkovskiy, A., Wang, C.-Y., Hong-Yuan Mark, Liao: Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"1564_CR18","doi-asserted-by":"crossref","unstructured":"Hwang, S., Park, J., Kim, N., Choi, Y., Kweon, I.S.: Multispectral pedestrian detection: Benchmark dataset and baselines, in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 1037\u20131045. (2015)","DOI":"10.1109\/CVPR.2015.7298706"},{"key":"1564_CR19","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1016\/j.inffus.2023.02.031","volume":"95","author":"H Zhang","year":"2023","unstructured":"Zhang, H., Ma, J.: IID-MEF: A multi-exposure fusion network based on intrinsic image decomposition. Inform. Fusion. 95, 326\u2013340 (2023)","journal-title":"Inform. Fusion"},{"key":"1564_CR20","doi-asserted-by":"crossref","unstructured":"Li, R., et al.: Multi-scale cross-modal homogeneity enhancement and confidence-aware Fusion for Multispectral Pedestrian Detection. IEEE Trans. Multimedia (2023)","DOI":"10.1109\/TMM.2023.3272471"},{"key":"1564_CR21","doi-asserted-by":"crossref","unstructured":"Guo, T., Seyed Mousavi, H., Huu Vu, T., Monga, V.: Deep wavelet prediction for image super-resolution, in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops, pp. 104\u2013113. (2017)","DOI":"10.1109\/CVPRW.2017.148"},{"key":"1564_CR22","doi-asserted-by":"crossref","unstructured":"Kim, J., Kim, H., Kim, T., Kim, N., Choi, Y.: MLPD: Multi-label pedestrian detector in multispectral domain, IEEE Rob. Autom. Lett., vol. 6, no. 4, pp. 7846\u20137853, (2021)","DOI":"10.1109\/LRA.2021.3099870"},{"key":"1564_CR23","doi-asserted-by":"crossref","unstructured":"Zhou, K., Chen, L., Cao, X.: Improving multispectral pedestrian detection by addressing modality imbalance problems, in Proc. Eur.Conf. Comput. Vis., pp. 787\u2013803. (2020)","DOI":"10.1007\/978-3-030-58523-5_46"},{"key":"1564_CR24","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.isprsjprs.2020.12.010","volume":"173","author":"T Kattenborn","year":"2021","unstructured":"Kattenborn, T., et al.: Review on convolutional neural networks (CNN) in vegetation remote sensing. ISPRS J. Photogrammetry Remote Sens. 173, 24\u201349 (2021)","journal-title":"ISPRS J. Photogrammetry Remote Sens."},{"issue":"11","key":"1564_CR25","doi-asserted-by":"publisher","first-page":"7705","DOI":"10.1109\/TPAMI.2021.3115139","volume":"44","author":"B Zheng","year":"2021","unstructured":"Zheng, B., Yuan, S., Yan, C., Tian, X., Zhang, J., Sun, Y., Liu, L., Leonardis, A., Slabaugh, G.: Learning frequency domain priors for image demoir\u00b4eing. IEEE Trans. Pattern Anal. Mach. Intell. 44(11), 7705\u20137717 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"1564_CR26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s41074-017-0037-0","volume":"10","author":"R Yoshihashi","year":"2018","unstructured":"Yoshihashi, R., et al.: Pedestrian detection with motion features via two-stream ConvNets. IPSJ Trans. Comput. Vis. Appl. 10(1), 1\u201313 (2018)","journal-title":"IPSJ Trans. Comput. Vis. Appl."},{"key":"1564_CR27","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.infrared.2018.08.029","volume":"94","author":"Y-L Hou","year":"2018","unstructured":"Hou, Y.-L., et al.: Multispectral pedestrian detection based on deep convolutional neural networks. Infrared Phys. Technol. 94, 69\u201377 (2018)","journal-title":"Infrared Phys. Technol."},{"key":"1564_CR28","first-page":"1","volume":"72","author":"Y Zhang","year":"2023","unstructured":"Zhang, Y., Yu, H., He, Y., Wang, X., Yang, W.: Illumination-guided rgbt object detection with Inter- and intra-modality fusion. IEEE Trans. Instrum. Meas. 72, 1\u201313 (2023)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"1564_CR29","unstructured":"Zhang, L., et al.: Weakly aligned feature fusion for multimodal object detection. IEEE Trans. Neural Networks Learn. Syst. (2021)"},{"key":"1564_CR30","doi-asserted-by":"crossref","unstructured":"Zhou, K., Chen, L., Cao, X.: Improving multispectral pedestrian detection by addressing modality imbalance problems. Computer Vision\u2013ECCV : 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XVIII 16. Springer International Publishing, 2020. (2020)","DOI":"10.1007\/978-3-030-58523-5_46"},{"key":"1564_CR31","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.patcog.2018.08.005","volume":"85","author":"C Li","year":"2019","unstructured":"Li, C., et al.: Illumination-aware faster R-CNN for robust multispectral pedestrian detection. Pattern Recogn. 85, 161\u2013171 (2019)","journal-title":"Pattern Recogn."},{"key":"1564_CR32","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1016\/j.inffus.2018.11.017","volume":"50","author":"D Guan","year":"2019","unstructured":"Guan, D., et al.: Fusion of multispectral data through illumination-aware deep neural networks for pedestrian detection. Inform. Fusion. 50, 148\u2013157 (2019)","journal-title":"Inform. Fusion"},{"key":"1564_CR33","unstructured":"Zheng, Y., Izzat, I.H., Ziaee, S.: GFD-SSD: gated fusion double SSD for multispectral pedestrian detection. arXiv preprint arXiv:1903.06999 (2019)"},{"key":"1564_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Guided attentive feature fusion for multispectral pedestrian detection. Proceedings of the IEEE\/CVF winter conference on applications of computer vision. (2021)","DOI":"10.1109\/WACV48630.2021.00012"},{"key":"1564_CR35","doi-asserted-by":"crossref","unstructured":"Liu, T., Zhao, R., Kin-Man, L.: Attention-based cross-modality interaction for multispectral pedestrian detection. International Workshop on Advanced Imaging Technology (IWAIT) 2021. Vol. 11766. SPIE, (2021)","DOI":"10.1117\/12.2590661"},{"key":"1564_CR36","doi-asserted-by":"crossref","unstructured":"Oyallon, E., Belilovsky, E., Zagoruyko, S.: Scaling the scattering transform: Deep hybrid networks, in Proc. IEEE Int. Conf. Comput. Vis., pp. 5618\u20135627. (2017)","DOI":"10.1109\/ICCV.2017.599"},{"key":"1564_CR37","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-Excitation networks, in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 7132\u20137141. (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1564_CR38","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.inffus.2018.09.015","volume":"50","author":"L Zhang","year":"2019","unstructured":"Zhang, L., Liu, Z., Zhang, S., Yang, X., Qiao, H., Huang, K., Hussain, A.: Cross-modality interactive attention network for multispectral pedestrian detection. Inf. Fusion. 50, 20\u201329 (2019)","journal-title":"Inf. Fusion"},{"key":"1564_CR39","doi-asserted-by":"crossref","unstructured":"Kieu, M., Bagdanov, A.D., Bertini, M., del Bimbo, A.: Task-conditioned domain adaptation for pedestrian detection in thermal imagery, in Proc. Eur. Conf. Comput. Vis., pp. 546\u2013562. (2020)","DOI":"10.1007\/978-3-030-58542-6_33"},{"key":"1564_CR40","doi-asserted-by":"crossref","unstructured":"Leng, Y., et al.: MBNet: MOS prediction for synthesized speech with mean-bias network. ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, (2021)","DOI":"10.1109\/ICASSP39728.2021.9413877"},{"issue":"6","key":"1564_CR41","doi-asserted-by":"publisher","first-page":"2427","DOI":"10.1109\/TCSVT.2020.3017344","volume":"31","author":"Z Wen, Xin","year":"2020","unstructured":"Wen, Xin, Z., Han, Yu-Shen Liu: CMPD: Using cross memory network with pair discrimination for image-text retrieval. IEEE Trans. Circuits Syst. Video Technol. 31(6), 2427\u20132437 (2020)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"1564_CR42","doi-asserted-by":"crossref","unstructured":"Lu, T., Wang, Y., Zhang, Y., et al.: Face Hallucination via split-attention in split-attention network. Proceedings of the 29th ACM International Conference on Multimedia (ACMMM 2021). Chengdu, China, Oct 20\u201324, (2021)","DOI":"10.1145\/3474085.3475682"},{"key":"1564_CR43","doi-asserted-by":"publisher","first-page":"2314","DOI":"10.1109\/TMM.2023.3294808","volume":"26","author":"Y Wang","year":"2023","unstructured":"Wang, Y., Lu, T., Yao, Y., et al.: Learning to hallucinate face in the dark. IEEE Trans. Multimedia. 26, 2314\u20132326 (2023)","journal-title":"IEEE Trans. Multimedia"},{"issue":"6","key":"1564_CR44","first-page":"2533","volume":"33","author":"X Lin","year":"2022","unstructured":"Lin, X., Li, R., Zheng, X.: FaceFormer: Aggregating global and local representation for face hallucination. IEEE Trans. Circuits Syst. Video Technol. 33(6), 2533\u20132545 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-024-01564-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-024-01564-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-024-01564-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T19:26:45Z","timestamp":1722454005000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-024-01564-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,14]]},"references-count":44,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["1564"],"URL":"https:\/\/doi.org\/10.1007\/s00138-024-01564-w","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,14]]},"assertion":[{"value":"2 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 June 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 June 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 June 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The text in this study has been translated with the assistance of artificial intelligence software.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"The authors declare that they have no conflict of interest.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"80"}}