{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T10:42:53Z","timestamp":1789468973523,"version":"build-2803163510"},"reference-count":80,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1007\/s00530-026-02594-2","type":"journal-article","created":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T10:05:44Z","timestamp":1787565944000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MFS: a saliency-driven interactive multimodal fusion framework for robust semantic segmentation and object detection in complex and occluded scenes"],"prefix":"10.1007","volume":"32","author":[{"given":"Zhu","family":"Qiangxi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luo","family":"Xiangfeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,24]]},"reference":[{"issue":"19","key":"2594_CR1","doi-asserted-by":"publisher","first-page":"8802","DOI":"10.3390\/app11198802","volume":"11","author":"I Papadeas","year":"2021","unstructured":"Papadeas, I., Tsochatzidis, L., Amanatiadis, A., Pratikakis, I.: Real-time semantic image segmentation with deep learning for autonomous driving: A survey. Appl. Sci. 11(19), 8802 (2021)","journal-title":"Appl. Sci."},{"key":"2594_CR2","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1016\/j.inffus.2016.05.004","volume":"33","author":"A Toet","year":"2017","unstructured":"Li, S., Kang, X., Fang, L., Hu, J., Yin, H. Pixel-level image fusion: A survey of the state of the art. Inf. Fusion 2017, 33, 100\u2013112 (2017) https:\/\/doi.org\/10.1016\/j.inffus.2016.05.004","journal-title":"Information Fusion"},{"key":"2594_CR3","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. Information fusion 45, 153\u2013178 (2019)","journal-title":"Information fusion"},{"issue":"5","key":"2594_CR4","doi-asserted-by":"publisher","first-page":"2614","DOI":"10.1109\/TIP.2018.2887342","volume":"28","author":"H Li","year":"2019","unstructured":"Li, H., Wu, X.-J.: Densefuse: a fusion approach to infrared and visible images. IEEE Trans. Image Process. 28(5), 2614\u20132623 (2019)","journal-title":"IEEE Trans. Image Process."},{"issue":"12","key":"2594_CR5","doi-asserted-by":"publisher","first-page":"9645","DOI":"10.1109\/TIM.2020.3005230","volume":"69","author":"H Li","year":"2020","unstructured":"Li, H., Wu, X.-J., Durrani, T.: Nestfuse: an infrared and visible image fusion architecture based on nest connection and spatial\/channel attention models. IEEE Trans. Instrum. Meas. 69(12), 9645\u20139656 (2020)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"2594_CR6","first-page":"1","volume":"70","author":"J Ma","year":"2021","unstructured":"Ma, J., Tang, L., Xu, M., Zhang, H., Xiao, G.: Stdfusionnet: an infrared and visible image fusion network based on salient target detection. IEEE Trans. Instrum. Meas. 70, 1\u201313 (2021)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"2594_CR7","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1016\/j.inffus.2021.02.023","volume":"73","author":"H Li","year":"2021","unstructured":"Li, H., Wu, X.-J., Kittler, J.: Rfn-nest: an end-to-end residual fusion network for infrared and visible images. Informat. Fusion 73, 72\u201386 (2021)","journal-title":"Informat. Fusion"},{"key":"2594_CR8","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.inffus.2018.09.004","volume":"48","author":"J Ma","year":"2019","unstructured":"Ma, J., Yu, W., Liang, P., Li, C., Jiang, J.: Fusiongan: a generative adversarial network for infrared and visible image fusion. Informat. Fusion 48, 11\u201326 (2019)","journal-title":"Informat. Fusion"},{"key":"2594_CR9","first-page":"1","volume":"70","author":"J Ma","year":"2021","unstructured":"Ma, J., Zhang, H., Shao, Z., Liang, P., Xu, H.: Ganmcc: a generative adversarial network with multiclassification constraints for infrared and visible image fusion. IEEE Trans. Instrum. Meas. 70, 1\u201314 (2021)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"2594_CR10","doi-asserted-by":"publisher","unstructured":"Geng, M., Zhu, L., Wang, L., Zhang, W., Xiong, R., Tian, Y.: Event-based visible and infrared fusion via multi-task collaboration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 26929\u201326939 (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.02543","DOI":"10.1109\/CVPR52733.2024.02543"},{"key":"2594_CR11","doi-asserted-by":"crossref","unstructured":"Liu, J., Fan, X., Huang, Z., Wu, G., Liu, R., Zhong, W., Luo, Z.: Target-aware dual adversarial learning and a multi-scenario multimodality benchmark to fuse infrared and visible for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5802\u20135811 (2022). IEEE","DOI":"10.1109\/CVPR52688.2022.00571"},{"key":"2594_CR12","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.inffus.2021.06.008","volume":"76","author":"H Zhang","year":"2021","unstructured":"Zhang, H., Xu, H., Tian, X., Jiang, J., Ma, J.: Image fusion meets deep learning: a survey and perspective. Informat. Fusion 76, 323\u2013336 (2021)","journal-title":"Informat. Fusion"},{"issue":"12","key":"2594_CR13","doi-asserted-by":"publisher","first-page":"2121","DOI":"10.1109\/JAS.2022.106082","volume":"9","author":"L Tang","year":"2022","unstructured":"Tang, L., Deng, Y., Ma, Y., Huang, J., Ma, J.: Superfusion: a versatile image registration and fusion network with semantic awareness. IEEE\/CAA J. Automat. Sinica 9(12), 2121\u20132137 (2022)","journal-title":"IEEE\/CAA J. Automat. Sinica"},{"issue":"7","key":"2594_CR14","doi-asserted-by":"publisher","first-page":"1200","DOI":"10.1109\/JAS.2022.105686","volume":"9","author":"J Ma","year":"2022","unstructured":"Ma, J., Tang, L., Fan, F., Huang, J., Mei, X., Ma, Y.: Swinfusion: cross-domain long-range learning for general image fusion via swin transformer. IEEE\/CAA J. Automat. Sinica 9(7), 1200\u20131217 (2022)","journal-title":"IEEE\/CAA J. Automat. Sinica"},{"issue":"8","key":"2594_CR15","doi-asserted-by":"publisher","first-page":"985","DOI":"10.1016\/S0167-8655(02)00029-6","volume":"23","author":"S Li","year":"2002","unstructured":"Li, S., Multifocus image fusion using artificial neural networks. Pattern Recogn. Lett. 23(8), 985\u2013997 (2002)","journal-title":"Pattern Recogn. Lett."},{"issue":"7","key":"2594_CR16","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1109\/34.192463","volume":"11","author":"S Mallat","year":"1989","unstructured":"Mallat, S., A theory for multiresolution signal decomposition. IEEE Trans. Pattern Anal. Mach. Intell. 11(7), 674\u2013693 (1989)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2594_CR17","doi-asserted-by":"crossref","unstructured":"Burt, P.J., Adelson, E.H.: The laplacian pyramid as a compact image code. IEEE Trans. Commun., pp. 532-540. (1983)","DOI":"10.1109\/TCOM.1983.1095851"},{"issue":"4","key":"2594_CR18","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/0167-8655(89)90003-2","volume":"9","author":"A Toet","year":"1989","unstructured":"Toet, A.: Image fusion by a ratio of low-pass pyramid. Pattern Recogn. Lett. 9(4), 245\u2013253 (1989)","journal-title":"Pattern Recogn. Lett."},{"issue":"9","key":"2594_CR19","doi-asserted-by":"publisher","first-page":"4779","DOI":"10.1109\/TGRS.2012.2230332","volume":"51","author":"S Li","year":"2013","unstructured":"Li, S., Yin, H., Fang, L.: Remote sensing image fusion via sparse representations over learned dictionaries. IEEE Trans. Geosci. Remote Sens. 51(9), 4779\u20134789 (2013) https:\/\/doi.org\/10.1109\/TGRS.2012.2230332","journal-title":"IEEE Trans. Image Process."},{"key":"2594_CR20","doi-asserted-by":"crossref","unstructured":"Yang, B., Li, S.: Multifocus image fusion via sparse representation. IEEE Trans. Instrum. Meas. 59(4), 884\u2013892 (2010)","DOI":"10.1109\/TIM.2009.2026612"},{"key":"2594_CR21","doi-asserted-by":"publisher","unstructured":"Hazirbas, C., Ma, L., Domokos, C., Cremers, D.: Fusenet: Incorporating depth into semantic segmentation via fusion-based cnn architecture. In: Proceedings of the Asian Conference on Computer Vision, pp. 213\u2013228. Springer, (2016). https:\/\/doi.org\/10.1007\/978-3-319-54181-5_14","DOI":"10.1007\/978-3-319-54181-5_14"},{"key":"2594_CR22","doi-asserted-by":"crossref","unstructured":"Ferrod, R., Dantas, C.F., Di Caro, L., Ienco, D.: Revisiting cross-modal knowledge distillation: A disentanglement approach for rgbd semantic segmentation, (2025). arXiv preprint arXiv:2505.24361","DOI":"10.1007\/978-3-032-06078-5_28"},{"key":"2594_CR23","unstructured":"Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., Lu, L., Yuille, A.L., Zhou, Y.: Transunet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306 (2021)"},{"key":"2594_CR24","doi-asserted-by":"crossref","unstructured":"Wei, Z., Chen, L., Tu, T., Ling, P., Chen, H., Jin, Y.: Disentangle then parse: Night-time semantic segmentation with illumination disentanglement. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 21593\u201321603 (2023)","DOI":"10.1109\/ICCV51070.2023.01974"},{"key":"2594_CR25","unstructured":"Chen, C.-F., Panda, R., Fan, Q.: Regionvit: Regional-to-local attention for vision transformers. In: Proceedings of the Tenth International Conference on Learning Representations. OpenReview.net, (2022). https:\/\/openreview.net\/forum?id=T_V3uLix7V"},{"key":"2594_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.125682","volume":"264","author":"B Qi","year":"2025","unstructured":"Qi, B., Zhang, Y., Nie, T., Yu, D., Lv, H., Li, G.: A novel infrared and visible image fusion network based on cross-modality reinforcement and multi-attention fusion strategy. Expert Syst. Appl. 264, 125682 (2025). https:\/\/doi.org\/10.1016\/j.eswa.2024.125682","journal-title":"Expert Syst. Appl."},{"issue":"3","key":"2594_CR27","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1002\/mp.16703","volume":"51","author":"GY Li","year":"2024","unstructured":"Li, G.Y., Chen, J., Jang, S.-I., Gong, K., Li, Q.: Swincross: cross-modal swin transformer for head-and-neck tumor segmentation in PET\/CT images. Med. Phys. 51(3), 2096\u20132107 (2024) https:\/\/doi.org\/10.1002\/mp.16703","journal-title":"Med. Phys."},{"key":"2594_CR28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475","author":"Z Xia","year":"2022","unstructured":"Xia, Z., Pan, X., Song, S., Li, L.E., Huang, G.: Vision Transformer with Deformable Attention. In: CVPR, pp. 4794\u20134803 (2022) https:\/\/doi.org\/10.1109\/CVPR52688.2022.00475","journal-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)"},{"key":"2594_CR29","doi-asserted-by":"crossref","unstructured":"Li, J., Chen, J., Liu, J., Ma, H.: Learning a graph neural network with cross modality interaction for image fusion. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 4471\u20134479 (2023)","DOI":"10.1145\/3581783.3612135"},{"key":"2594_CR30","doi-asserted-by":"publisher","unstructured":"Jiang, Y., Shen, Y.: M$$^4$$oe: A foundation model for medical multimodal image segmentation with mixture of experts. In: Proceedings of the Medical Image Computing and Computer Assisted Intervention, pp. 621\u2013631 (2024). https:\/\/doi.org\/10.1007\/978-3-031-72390-2_58","DOI":"10.1007\/978-3-031-72390-2_58"},{"key":"2594_CR31","first-page":"7537","volume":"33","author":"M Tancik","year":"2020","unstructured":"Tancik, M., Srinivasan, P.P., Mildenhall, B., Fridovich-Keil, S., Raghavan, N., Singhal, U., Ramamoorthi, R., Barron, J.T., Ng, R.: Fourier features let networks learn high frequency functions in low dimensional domains. Adv. Neural Informat. Process. Syst. (NeurIPS) 33, 7537\u20137547 (2020)","journal-title":"Adv. Neural Informat. Process. Syst. (NeurIPS)"},{"key":"2594_CR32","doi-asserted-by":"crossref","unstructured":"Liu, L., Liu, J., Yuan, S., Slabaugh, G., Leonardis, A., Zhou, W., Tian, Q.: Wavelet-based dual-branch network for image demoir\u00e9ing. In: European Conference on Computer Vision, pp. 86\u2013102 (2020). Springer","DOI":"10.1007\/978-3-030-58601-0_6"},{"key":"2594_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.114908","volume":"332","author":"S Ma","year":"2025","unstructured":"Ma, S., He, J., Gao, Y., Li, Z.: Spectral context-aware frequency alignment for few-shot hyperspectral image classification. Knowl.-Based Syst. 332, 114908 (2025)","journal-title":"Knowl.-Based Syst."},{"key":"2594_CR34","unstructured":"Xie, J., Li, W., Zhan, X., Liu, Z., Ong, Y.S., Loy, C.C.: Masked frequency modeling for self-supervised visual pre-training. In: Proceedings of the International Conference on Learning Representations (2023) https:\/\/arxiv.org\/abs\/2206.07706"},{"key":"2594_CR35","doi-asserted-by":"publisher","first-page":"59239","DOI":"10.52202\/075280-2586","volume":"36","author":"Z Lin","year":"2023","unstructured":"Lin, Z., Gao, Y., Yang, Y., Sang, J.: Revisiting visual model robustness: a frequency long-tailed distribution view. Adv. Neural. Inf. Process. Syst. 36, 59239\u201359251 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"12","key":"2594_CR36","doi-asserted-by":"publisher","first-page":"2379","DOI":"10.1364\/JOSAA.4.002379","volume":"4","author":"DJ Field","year":"1987","unstructured":"Field, D.J.: Relations between the statistics of natural images and the response properties of cortical cells. J. Opt. Soc. Am. A 4(12), 2379\u20132394 (1987)","journal-title":"J. Opt. Soc. Am. A"},{"key":"2594_CR37","doi-asserted-by":"publisher","DOI":"10.1016\/j.infrared.2024.105344","volume":"140","author":"J Xiong","year":"2024","unstructured":"Xiong, J., Liu, G., Tang, H., Gu, X., Bavirisetti, D.P.: Segfusion: a semantic saliency guided infrared and visible image fusion method. Infrared Phys. Technol. 140, 105344 (2024)","journal-title":"Infrared Phys. Technol."},{"key":"2594_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.infrared.2025.106270","volume":"152","author":"W Xing","year":"2026","unstructured":"Xing, W., Guo, C., Guo, Y., Kou, J., Sun, S.: An image fusion network using salient object mask-guided diffusion model. Infrared Phys. Technol. 152, 106270 (2026)","journal-title":"Infrared Phys. Technol."},{"key":"2594_CR39","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101828","volume":"98","author":"D Wang","year":"2023","unstructured":"Wang, D., Liu, J., Liu, R., Fan, X.: An interactively reinforced paradigm for joint infrared-visible image fusion and saliency object detection. Informat. Fusion 98, 101828 (2023)","journal-title":"Informat. Fusion"},{"key":"2594_CR40","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, pp. 7132\u20137141 (2018) https:\/\/arxiv.org\/abs\/1709.015075","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2594_CR41","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: Segformer: simple and efficient design for semantic segmentation with transformers. Adv. Neural. Inf. Process. Syst. 34, 12077\u201312090 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2594_CR42","doi-asserted-by":"crossref","unstructured":"Ha, Q., Watanabe, K., Karasawa, T., Ushiku, Y., Harada, T.: Mfnet: Towards real-time semantic segmentation for autonomous vehicles with multi-spectral scenes. In: Proceedings of the IEEE International Conference on Intelligent Robots and Systems, pp. 5108\u20135115 (2017)","DOI":"10.1109\/IROS.2017.8206396"},{"key":"2594_CR43","doi-asserted-by":"crossref","unstructured":"Shivakumar, S.S., Rodrigues, N., Zhou, A., Miller, I.D., Kumar, V., Taylor, C.J.: Pst900: Rgb-thermal calibration, dataset and segmentation network. In: Proceedings of the IEEE International Conference on Robotics and Automation, pp. 9441\u20139447. (2020)","DOI":"10.1109\/ICRA40945.2020.9196831"},{"key":"2594_CR44","doi-asserted-by":"crossref","unstructured":"Liu, J., Liu, Z., Wu, G., Ma, L., Liu, R., Zhong, W., Luo, Z., Fan, X.: Multi-interactive feature learning and a full-time multi-modality benchmark for image fusion and segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 8115\u20138124 (2023)","DOI":"10.1109\/ICCV51070.2023.00745"},{"key":"2594_CR45","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. Informat. Fusion 82, 28\u201342 (2022). https:\/\/doi.org\/10.1016\/j.inffus.2021.12.004","journal-title":"Informat. Fusion"},{"key":"2594_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, W., Dong, S., Xu, C., Qian, Y.: Edge-aware guidance fusion network for rgb-thermal scene parsing. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 3571\u20133579. (2022)","DOI":"10.1609\/aaai.v36i3.20269"},{"issue":"3","key":"2594_CR47","doi-asserted-by":"publisher","first-page":"1223","DOI":"10.1109\/TCSVT.2022.3208833","volume":"33","author":"G Li","year":"2023","unstructured":"Li, G., Wang, Y., Liu, Z., Zhang, X., Zeng, D.: Rgb-t semantic segmentation with location, activation, and sharpening. Proc. IEEE Trans. Circ. Syst. Video Technol. 33(3), 1223\u20131235 (2023)","journal-title":"Proc. IEEE Trans. Circ. Syst. Video Technol."},{"key":"2594_CR48","doi-asserted-by":"publisher","unstructured":"Zhao, S., Liu, Y., Jiao, Q., Zhang, Q., Han, J.: Mitigating modality discrepancies for RGB-T semantic segmentation. IEEE Trans. Neural Netw. Learn. Syst. 35(7), 9380\u20139394 (2024) https:\/\/doi.org\/10.1109\/TNNLS.2022.3233089","DOI":"10.1109\/TNNLS.2022.3233089"},{"key":"2594_CR49","doi-asserted-by":"publisher","unstructured":"Wang, Y., Li, G., Liu, Z.: Sgfnet: Semantic-guided fusion network for rgb-thermal semantic segmentation. IEEE Trans. Circuits Syst. Video Technol. 33(12), 7737\u20137748 (2023) https:\/\/doi.org\/10.1109\/TCSVT.2023.3281419","DOI":"10.1109\/TCSVT.2023.3281419"},{"issue":"7","key":"2594_CR50","doi-asserted-by":"publisher","first-page":"4060","DOI":"10.1109\/LRA.2023.3272269","volume":"8","author":"M Liang","year":"2023","unstructured":"Liang, M., Hu, J., Bao, C., Feng, H., Deng, F., Lam, T.L.: Explicit attention-enhanced fusion for rgb-thermal perception tasks. IEEE Robot. Automat. Lett. 8(7), 4060\u20134067 (2023)","journal-title":"IEEE Robot. Automat. Lett."},{"key":"2594_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, H., Zuo, X., Jiang, J., Guo, C., Ma, J.: Mrfs: Mutually reinforcing image fusion and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 26974\u201326983. (2024)","DOI":"10.1109\/CVPR52733.2024.02547"},{"key":"2594_CR52","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Howes, A., Zhang, X.: Multitaskvif: Segmentation-oriented visible and infrared image fusion via multi-task learning, (2025). arXiv preprint arXiv:2505.06665","DOI":"10.1109\/TIP.2026.3710490"},{"key":"2594_CR53","doi-asserted-by":"crossref","unstructured":"Wu, G., Liu, H., Fu, H., Peng, Y., Liu, J., Fan, X., Liu, R.: Every SAM drop counts: Embracing semantic priors for multi-modality image fusion and beyond. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 17882\u201317891 (2025)","DOI":"10.1109\/CVPR52734.2025.01666"},{"issue":"17","key":"2594_CR54","doi-asserted-by":"publisher","first-page":"3408","DOI":"10.3390\/electronics14173408","volume":"14","author":"JY Hwang","year":"2025","unstructured":"Hwang, J.Y., Lee, Y.J., Jung, H.G., Suhr, J.K.: Pruning-friendly rgb-t semantic segmentation for real-time processing on edge devices. Electronics 14(17), 3408 (2025). https:\/\/doi.org\/10.3390\/electronics14173408","journal-title":"Electronics"},{"key":"2594_CR55","unstructured":"Guo, X., Liu, T., Li, Y., Lin, Z., Deng, Z.: TUNI: Real-time RGB-T Semantic Segmentation with Unified Multi-Modal Feature Extraction and Cross-Modal Feature Fusion. arXiv preprint arXiv:2509.10005 (2025)"},{"key":"2594_CR56","doi-asserted-by":"publisher","unstructured":"Guo, X., Lin, Z., Hu, L., Deng, Z., Liu, T., Zhou, W.: Cross-modal state space modeling for real-time rgb-thermal wild scene semantic segmentation. In: 2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5938\u20135945 (2025). https:\/\/doi.org\/10.1109\/iros60139.2025.11247008","DOI":"10.1109\/iros60139.2025.11247008"},{"issue":"3","key":"2594_CR57","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/s11554-026-01903-2","volume":"23","author":"H Li","year":"2026","unstructured":"Li, H., Liu, T., Wu, S., Song, Z., Dong, H., Du, J., Wang, X.: Real-time rgb-t semantic segmentation via hierarchical semantic guidance and detail-preserving pidnet. J. Real-Time Image Proc. 23(3), 108 (2026). https:\/\/doi.org\/10.1007\/s11554-026-01903-2","journal-title":"J. Real-Time Image Proc."},{"key":"2594_CR58","unstructured":"Canitez, I.E., Erkent, O.: Frequency-guided fusion for rgb-thermal semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 7018\u20137026. (2026)"},{"issue":"7","key":"2594_CR59","doi-asserted-by":"publisher","first-page":"3159","DOI":"10.1109\/TCSVT.2023.3234340","volume":"33","author":"W Tang","year":"2023","unstructured":"Tang, W., He, F., Liu, Y., Duan, Y., Si, T.: Datfuse: Infrared and visible image fusion via dual attention transformer. IEEE Trans. Circuits Syst. Video Technol. 33(7), 3159\u20133172 (2023) https:\/\/doi.org\/10.1109\/TCSVT.2023.3234340","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2594_CR60","doi-asserted-by":"publisher","DOI":"10.1016\/j.infrared.2024.105548","author":"G Lu","year":"2024","unstructured":"Lu, G., Fang, Z., Tian, J., Huang, H., Xu, Y., Han, Z., Kang, Y., Feng, C., Zhao, Z.: Gan-ha: a generative adversarial network with a novel heterogeneous dual-discriminator network and a new attention-based fusion strategy for infrared and visible image fusion. Infrared Phys. Technol. (2024). https:\/\/doi.org\/10.1016\/j.infrared.2024.105548","journal-title":"Infrared Phys. Technol."},{"issue":"10","key":"2594_CR61","doi-asserted-by":"publisher","first-page":"2774","DOI":"10.1049\/ipr2.13134","volume":"18","author":"S Shen","year":"2024","unstructured":"Shen, S., Zhang, T., Dong, H., Yuan, S., Li, M., Xiao, R., Zhang, X.: Adf-net: attention-guided deep feature decomposition network for infrared and visible image fusion. IET Image Proc. 18(10), 2774\u20132787 (2024). https:\/\/doi.org\/10.1049\/ipr2.13134","journal-title":"IET Image Proc."},{"issue":"1","key":"2594_CR62","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1109\/TPAMI.2020.3012548","volume":"44","author":"H Xu","year":"2022","unstructured":"Xu, H., Ma, J., Le, Z., et al.: U2Fusion: a Unified Unsupervised Image Fusion Network. Proc. IEEE Trans. Pattern Anal. Mach. Intell. 44(1), 502\u2013518 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2020.3012548","journal-title":"Proc. IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2594_CR63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3273451","author":"D Rao","year":"2023","unstructured":"Rao, D., Xu, T., Wu, X.-J.: Tgfuse: an infrared and visible image fusion approach based on transformer and generative adversarial network. IEEE Trans. Image Process. (2023) https:\/\/doi.org\/10.1109\/TIP.2023.3273451","journal-title":"IEEE Trans. Image Process."},{"key":"2594_CR64","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Bai, H., Zhang, J., Zhang, Y., Xu, S., Lin, Z., Timofte, R., Gool, L.V.: 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), pp. 5906\u20135916 (2023) 72","DOI":"10.1109\/CVPR52729.2023.00572"},{"issue":"1","key":"2594_CR65","doi-asserted-by":"publisher","first-page":"1919","DOI":"10.1109\/TIV.2023.3314527","volume":"9","author":"W Zhou","year":"2024","unstructured":"Zhou, W., Dong, S., Fang, M., Yu, L.: CACFNet: cross-modal attention cascaded fusion network for RGB-T urban scene parsing. IEEE Trans. Intell. Vehicle 9(1), 1919\u20131929 (2024). https:\/\/doi.org\/10.1109\/TIV.2023.3314527","journal-title":"IEEE Trans. Intell. Vehicle"},{"key":"2594_CR66","first-page":"1","volume":"72","author":"Y Zhang","year":"2023","unstructured":"Xie R, Jiang S, Bie Y, Xia M.: Illumination-guided with crossmodal transformer fusion for rgb-t object detection.J. Imaging Sci. Technol. 69(2), 1\u201311 (2025)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"2594_CR67","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2024.103918","volume":"130","author":"C J","year":"2024","unstructured":"Jiang, C.; Ren, H.; Yang, H.; Huo, H.; Zhu, P.; Yao, Z.; Li, J.; Sun, M.; Yang, S.: M$$^2$$fnet: multi-modal fusion network for object detection from visible and thermal infrared images. ISPRS J. Appl. Earth Observ. Geoinformat. 130, 103918 (2024) https:\/\/doi.org\/10.1016\/j.jag.2024.103918","journal-title":"ISPRS J. Appl. Earth Observ. Geoinformat."},{"key":"2594_CR68","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102246","volume":"105","author":"X Li","year":"2024","unstructured":"Yuan, L., Shi, W., Wang, Z., Wang, N., Wang, Y., Wei, X.: Improving rgb-infrared object detection with cascade alignment-guided transformer. Informat. Fusion 105, 102246 (2024). https:\/\/doi.org\/10.1016\/j.inffus.2024.102246","journal-title":"Informat. Fusion"},{"key":"2594_CR69","unstructured":"Liu, F., Gao, C., Chen, F., Li, P., Guo, J., Meng, D.: Ivgf: The fusion-guided infrared and visible general framework. arXiv:2409.00973 arXiv:2409.00973(2024) https:\/\/arXiv:2409.00973"},{"key":"2594_CR70","doi-asserted-by":"crossref","unstructured":"Zhang, T., Zhao, J., Zhu, Y., Cui, G., Lyu, Y.: Fsatfusion: Frequency-spatial attention transformer for infrared and visible image fusion. arXiv preprint arXiv:2506.10366 (2025) 10.48550\/arXiv.2506.10366","DOI":"10.1016\/j.cviu.2025.104600"},{"key":"2594_CR71","unstructured":"Jocher, G.: YOLOv5: A Family of Object Detection Architectures and Models Pretrained on the COCO Dataset. Version 6.0. https:\/\/github.com\/ultralytics\/yolov5"},{"issue":"3","key":"2594_CR72","doi-asserted-by":"publisher","first-page":"1712","DOI":"10.1109\/TCSVT.2023.3296745","volume":"34","author":"Y Zhao","year":"2024","unstructured":"Zhao, Y., Zheng, Q., Zhu, P., Zhang, X., Ma, W.: Tufusion: a transformer-based universal fusion algorithm for multimodal images. IEEE Trans. Circuits Syst. Video Technol. 34(3), 1712\u20131725 (2024). https:\/\/doi.org\/10.1109\/TCSVT.2023.3296745","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2594_CR73","doi-asserted-by":"publisher","first-page":"3542877","DOI":"10.1109\/TIM.2025.3542877","volume":"74","author":"J Liu","year":"2025","unstructured":"Liu, J., Zhang, L., Zeng, X., Liu, W., Zhang, J.: Matcnn: infrared and visible image fusion method based on multi-scale CNN with attention transformer. IEEE Trans. Instrum. Meas. 74, 3542877 (2025). https:\/\/doi.org\/10.1109\/TIM.2025.3542877","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"2594_CR74","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.dib.2017.09.038","volume":"15","author":"A Toet","year":"2017","unstructured":"Toet, A.: The tno multiband image data collection. Data Brief 15, 249\u2013251 (2017) https:\/\/doi.org\/10.1016\/j.dib.2017.09.038","journal-title":"Data Brief"},{"key":"2594_CR75","first-page":"11460","volume":"34","author":"C Li","year":"2020","unstructured":"Tang, L., Yuan, J., Zhang, H., Jiang, X., Ma, J.: PIAFusion: A progressive infrared and visible image fusion network based on illumination aware. Inf. Fusion 83\u201384, 79\u201392 (2022)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"2594_CR76","doi-asserted-by":"publisher","unstructured":"Li, F., Zhang, H., Xu, H., Liu, S., Zhang, L., Ni, L.M., Shum, H.-Y.: Mask dino: Towards a unified transformer-based framework for object detection and segmentation, In: CVPR, pp. 3041\u20133050 (2023) https:\/\/doi.org\/10.1109\/CVPR52729.2023.00297","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"2594_CR77","doi-asserted-by":"crossref","unstructured":"Nan, Z., Li, X., Xiang, T., Dai, J.: DI\u2011MaskDINO: A joint object detection and instance segmentation model. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 60359\u201360381 (2024) arXiv:2405.10082","DOI":"10.52202\/079017-1930"},{"key":"2594_CR78","doi-asserted-by":"publisher","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: Common objects in context. European conference on computer vision, pp. 740\u2013755. (2014) https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"12","key":"2594_CR79","doi-asserted-by":"publisher","first-page":"7096","DOI":"10.1109\/TCSVT.2023.3275314","volume":"33","author":"W Zhou","year":"2023","unstructured":"Zhou, W., Zhang, H., Yan, W., Lin, W.: Mmsmcnet: Modal memory sharing and morphological complementary networks for rgb-t urban scene semantic segmentation. IEEE Trans. Circuits Syst. Video Technol. 33(12), 7096\u20137108 (2023) https:\/\/doi.org\/10.1109\/TCSVT.2023.3275314","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2594_CR80","doi-asserted-by":"publisher","DOI":"10.1016\/j.infrared.2024.105218","volume":"138","author":"H Chi","year":"2024","unstructured":"Chi, H., Luo, D., Wang, S.: Lmdfusion: a lightweight infrared and visible image fusion network for substation equipment based on mask and residual dense connection. Infrared Phys. Technol. 138, 105218 (2024). https:\/\/doi.org\/10.1016\/j.infrared.2024.105218","journal-title":"Infrared Phys. Technol."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02594-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02594-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02594-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T09:16:15Z","timestamp":1789463775000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02594-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,24]]},"references-count":80,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["2594"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02594-2","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,24]]},"assertion":[{"value":"19 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare there is no conflict of interest regarding the publication of this paper.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not Applicable.","order":2,"name":"Ethics","label":"Ethics approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not Applicable.","order":3,"name":"Ethics","label":"Consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not Applicable.","order":4,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"532"}}