{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T05:18:04Z","timestamp":1783315084571,"version":"3.54.6"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100015291","name":"Scientific Research Foundation of Higher Education Institutions of Ningxia","doi-asserted-by":"publisher","award":["NYG2024182"],"award-info":[{"award-number":["NYG2024182"]}],"id":[{"id":"10.13039\/501100015291","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s00530-026-02239-4","type":"journal-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T13:56:35Z","timestamp":1773150995000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FusionYOLO: application of target-aware guided multimodal image fusion for object detection"],"prefix":"10.1007","volume":"32","author":[{"given":"Hongfang","family":"Ma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihong","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Dang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,10]]},"reference":[{"issue":"3","key":"2239_CR1","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1109\/TITS.2020.2972974","volume":"22","author":"D Feng","year":"2020","unstructured":"Feng, D., Rosenbaum, L., et al.: Deep multi-modal object detection and semantic segmentation for autonomous driving: Datasets, methods, and challenges. IEEE Trans. Intell. Transp. Syst. 22(3), 1341\u20131360 (2020)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"2239_CR2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3544621","author":"X Ying","year":"2025","unstructured":"Ying, X., Xiao, C., An, W., et al.: Visible-thermal tiny object detection: a benchmark dataset and baselines. IEEE Trans. Pattern Anal. Mach. Intell. (2025). https:\/\/doi.org\/10.1109\/TPAMI.2025.3544621","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2239_CR3","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/j.neucom.2019.04.028","volume":"350","author":"Z Li","year":"2019","unstructured":"Li, Z., Dong, M., Wen, S., et al.: CLU-cnns: object detection for medical images. Neurocomputing 350, 53\u201359 (2019)","journal-title":"Neurocomputing"},{"issue":"5","key":"2239_CR4","doi-asserted-by":"publisher","first-page":"4340","DOI":"10.1109\/TGRS.2020.3016820","volume":"59","author":"D Hong","year":"2020","unstructured":"Hong, D., Gao, L., Yokoya, N., et al.: More diverse means better: multimodal deep learning meets remote-sensing imagery classification. IEEE Trans. Geosci. Remote Sens. 59(5), 4340\u20134354 (2020)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"2239_CR5","doi-asserted-by":"crossref","unstructured":"Liu, J., Wu, G., Liu, Z., et al. Infrared and visible image fusion: From data compatibility to task adaption. IEEE Trans Pattern Anal Mach Intell. 47(4),2349-2369 (2024)","DOI":"10.1109\/TPAMI.2024.3521416"},{"key":"2239_CR6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3535617","author":"H Li","year":"2025","unstructured":"Li, H., Yang, Z., Zhang, Y., et al.: MulFS-CAP: multimodal fusion-supervised cross-modality alignment perception for unregistered infrared-visible image fusion. IEEE Trans. Pattern Anal. Mach. Intell. (2025). https:\/\/doi.org\/10.1109\/TPAMI.2025.3535617","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2239_CR7","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.inffus.2022.03.007","volume":"83","author":"L Tang","year":"2022","unstructured":"Tang, L., Yuan, J., Zhang, H., et al.: PIAFusion: a progressive infrared and visible image fusion network based on illumination aware. Inf. Fusion 83, 79\u201392 (2022)","journal-title":"Inf. Fusion"},{"issue":"21","key":"2239_CR8","doi-asserted-by":"publisher","DOI":"10.3390\/rs16214034","volume":"16","author":"R Guo","year":"2024","unstructured":"Guo, R., Guo, X., Sun, X., et al.: Background-aware cross-attention multiscale fusion for multispectral object detection. Remote Sens. 16(21), 4034 (2024)","journal-title":"Remote Sens."},{"key":"2239_CR9","doi-asserted-by":"crossref","unstructured":"Yang, Y., Loquercio, A., Scaramuzza, D., et al.: Unsupervised moving object detection via contextual information separation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 879\u2013888. (2019)","DOI":"10.1109\/CVPR.2019.00097"},{"key":"2239_CR10","doi-asserted-by":"crossref","unstructured":"Yuan, M., Wang, Y., Wei, X.: Translation, scale and rotation: cross-modal alignment meets RGB-infrared vehicle detection. In: European Conference on Computer Vision. Cham: Springer Nature Switzerland, 509\u2013525. (2022)","DOI":"10.1007\/978-3-031-20077-9_30"},{"key":"2239_CR11","doi-asserted-by":"publisher","first-page":"1497","DOI":"10.1109\/JSTARS.2020.3041316","volume":"14","author":"M Sharma","year":"2020","unstructured":"Sharma, M., Dhanaraj, M., Karnam, S., et al.: YOLOrs: Object detection in multimodal remote sensing imagery. IEEE J. Select. Topics Appl. Earth Observ. Remote Sens. 14, 1497\u20131508 (2020)","journal-title":"IEEE J. Select. Topics Appl. Earth Observ. Remote Sens."},{"key":"2239_CR12","doi-asserted-by":"crossref","unstructured":"Liu, J., Fan, X., Huang, Z., et al.: Target-aware dual adversarial learning and a multi-scenario multi-modality benchmark to fuse infrared and visible for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 5802\u20135811. (2022)","DOI":"10.1109\/CVPR52688.2022.00571"},{"key":"2239_CR13","doi-asserted-by":"crossref","unstructured":"Liu, J., Liu, Z., Wu, G., et al.: Multi-interactive feature learning and a full-time multi-modality benchmark for image fusion and segmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision. 8115\u20138124. (2023)","DOI":"10.1109\/ICCV51070.2023.00745"},{"key":"2239_CR14","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.inffus.2021.12.004","volume":"82","author":"L Tang","year":"2022","unstructured":"Tang, L., Yuan, J., Ma, J.: Image fusion in the loop of high-level vision tasks: a semantic-aware real-time infrared and visible image fusion network. Inf. Fusion 82, 28\u201342 (2022)","journal-title":"Inf. Fusion"},{"key":"2239_CR15","first-page":"1","volume":"61","author":"J Zhang","year":"2023","unstructured":"Zhang, J., Lei, J., Xie, W., et al.: SuperYOLO: super resolution assisted object detection in multimodal remote sensing imagery. IEEE Trans. Geosci. Remote Sens. 61, 1\u201315 (2023)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"2239_CR16","doi-asserted-by":"crossref","unstructured":"Fu, H., Wang, S., Duan, P, et al. Lraf-net: long-range attention fusion network for visible\u2013infrared object detection. IEEE Trans Neural Networks Learn Syst. 35(10), 13232-13245 (2023)","DOI":"10.1109\/TNNLS.2023.3266452"},{"key":"2239_CR17","doi-asserted-by":"crossref","unstructured":"Zhang, L., Liu, Z., Zhu, X., et al.: Weakly aligned feature fusion for multimodal object detection. IEEE Trans Neural Networks Learn Syst. 36(3), 4145-4159 (2021)","DOI":"10.1109\/TNNLS.2021.3105143"},{"key":"2239_CR18","volume":"130","author":"C Jiang","year":"2024","unstructured":"Jiang, C., Ren, H., Yang, H., et al.: M2FNet: multi-modal fusion network for object detection from visible and thermal infrared images. Int. J. Appl. Earth Obs. Geoinf. 130, 103918 (2024)","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"issue":"5","key":"2239_CR19","doi-asserted-by":"publisher","first-page":"2614","DOI":"10.1109\/TIP.2018.2887342","volume":"28","author":"H Li","year":"2018","unstructured":"Li, H., Wu, X.J.: Densefuse: a fusion approach to infrared and visible images. IEEE Trans. Image Process. 28(5), 2614\u20132623 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"2239_CR20","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1016\/j.inffus.2018.02.004","volume":"45","author":"J Ma","year":"2019","unstructured":"Ma, J., Ma, Y., Li, C.: Infrared and visible image fusion methods and applications: a survey. Inf. Fusion 45, 153\u2013178 (2019)","journal-title":"Inf. Fusion"},{"key":"2239_CR21","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1109\/LSP.2023.3266980","volume":"30","author":"Y Wu","year":"2023","unstructured":"Wu, Y., Liu, Z., Liu, J., et al.: Breaking free from fusion rule: a fully semantic-driven infrared and visible image fusion. IEEE Signal Process. Lett. 30, 418\u2013422 (2023)","journal-title":"IEEE Signal Process. Lett."},{"key":"2239_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128116","volume":"600","author":"G Yang","year":"2024","unstructured":"Yang, G., Li, J., Lei, H., et al.: A multi-scale information integration framework for infrared and visible image fusion. Neurocomputing 600, 128116 (2024)","journal-title":"Neurocomputing"},{"issue":"5","key":"2239_CR23","doi-asserted-by":"publisher","first-page":"1748","DOI":"10.1007\/s11263-023-01952-1","volume":"132","author":"J Liu","year":"2024","unstructured":"Liu, J., Lin, R., Wu, G., et al.: Coconet: coupled contrastive learning network with multi-level feature ensemble for multi-modality image fusion. Int. J. Comput. Vision 132(5), 1748\u20131775 (2024)","journal-title":"Int. J. Comput. Vision"},{"key":"2239_CR24","doi-asserted-by":"crossref","unstructured":"Huang, T., Liu, Z., Chen, X., et al.: Epnet: enhancing point features with image semantics for 3d object detection. Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, proceedings, part XV 16. Springer International Publishing, 35\u201352. (2020)","DOI":"10.1007\/978-3-030-58555-6_3"},{"key":"2239_CR25","doi-asserted-by":"crossref","unstructured":"Yang, Q., Zhao, Y., Cheng, H.: MMLF: multi-modal multi-class late fusion for object detection with uncertainty estimation. arXiv preprint arXiv:2410.08739 (2024)","DOI":"10.1109\/CVCI66304.2025.11348238"},{"key":"2239_CR26","doi-asserted-by":"crossref","unstructured":"Lin, Z., Shen, Y., Zhou, S., et al.: Mlf-det: multi-level fusion for cross-modal 3d object detection. In: International Conference on Artificial Neural Networks. Cham: Springer Nature Switzerland, 136\u2013149. (2023)","DOI":"10.1007\/978-3-031-44195-0_12"},{"issue":"10","key":"2239_CR27","doi-asserted-by":"publisher","first-page":"6591","DOI":"10.1007\/s11760-024-03337-4","volume":"18","author":"P Xue","year":"2024","unstructured":"Xue, P., Zhang, Z.: EBFF-YOLO: enhanced bimodal feature fusion network for UAV image object detection. Signal Image Video Process. 18(10), 6591\u20136600 (2024)","journal-title":"Signal Image Video Process."},{"key":"2239_CR28","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wang, P., Liu, W., et al.: Distance-IoU loss: faster and better learning for bounding box regression. In: Proceedings of the AAAI conference on artificial intelligence 34(07): 12993\u201313000 (2020)","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"2239_CR29","doi-asserted-by":"crossref","unstructured":"Han, K., Wang, Y., Tian, Q., et al.: Ghostnet: more features from cheap operations. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 1580\u20131589. (2020)","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"2239_CR30","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 7132\u20137141. (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2239_CR31","unstructured":"Gevorgyan, Z.: SIoU loss: more powerful learning for bounding box regression. arXiv preprint arXiv:2205.12740 (2022)"},{"issue":"1","key":"2239_CR32","volume":"1924","author":"Z Yang","year":"2021","unstructured":"Yang, Z., Wang, X., Li, J.: EIoU: an improved vehicle detection algorithm based on vehiclenet neural network. J. Phys.: Conf. Ser. IOP Publishing 1924(1), 012001 (2021)","journal-title":"J. Phys.: Conf. Ser. IOP Publishing"},{"key":"2239_CR33","unstructured":"Cho, Y.J.: Weighted Intersection over Union (wIoU) for Evaluating Image Segmentation. arXiv preprint arXiv:2107.09858 (2021)"},{"key":"2239_CR34","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J.Y., et al.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 658\u2013666. (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"2239_CR35","unstructured":"Yang, X., Yan, J., Ming, Q., et al.: Rethinking rotated object detection with gaussian wasserstein distance loss. In: International conference on machine learning. PMLR, 11830\u201311841. (2021)"},{"key":"2239_CR36","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., et al.: Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision. 2980\u20132988. (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"2239_CR37","doi-asserted-by":"publisher","unstructured":"Zhao, Z., Bai, H., Zhang, J., Zhang, Y., Xu, S., Lin, Z., Timofte, R., Van Gool, L.: CDDFuse: correlation-driven dual-branch feature decomposition for multi-modality image fusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Piscataway, NJ: IEEE, 5906\u20135916. (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00572.","DOI":"10.1109\/CVPR52729.2023.00572"},{"key":"2239_CR38","doi-asserted-by":"crossref","unstructured":"Yi, X., Zhang, Y., Xiang, X., et al. LUT-Fuse: towards extremely fast infrared and visible image fusion via distillation to learnable look-up tables. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 14559\u201314568 (2025)","DOI":"10.1109\/ICCV51701.2025.01351"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02239-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02239-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02239-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T05:05:24Z","timestamp":1783314324000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02239-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,10]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["2239"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02239-4","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,10]]},"assertion":[{"value":"5 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"189"}}