{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T21:55:34Z","timestamp":1777758934985,"version":"3.51.4"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Science and Technology Planning Project of Henan Province","award":["242102211003"],"award-info":[{"award-number":["242102211003"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61972157"],"award-info":[{"award-number":["61972157"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s00371-026-04451-9","type":"journal-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T10:27:35Z","timestamp":1775730455000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PSFusion: progressive semantic-guided hierarchical network for infrared and visible image fusion"],"prefix":"10.1007","volume":"42","author":[{"given":"Canlin","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xunpeng","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangfei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lihua","family":"Bi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lizhuang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,9]]},"reference":[{"issue":"8","key":"4451_CR1","doi-asserted-by":"publisher","first-page":"10535","DOI":"10.1109\/TPAMI.2023.3261282","volume":"45","author":"X Zhang","year":"2023","unstructured":"Zhang, X., Demiris, Y.: Visible and infrared image fusion using deep learning. IEEE Trans. Pattern Anal. Mach. Intell. 45(8), 10535\u201310554 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4451_CR2","first-page":"198","volume":"10","author":"P Rajah","year":"2018","unstructured":"Rajah, P., Odindi, J., Mutanga, O.: Feature level image fusion of optical imagery and synthetic aperture radar (sar) for invasive alien plant species detection and mapping. Remote Sens. Appl. Soc. Environ. 10, 198\u2013208 (2018)","journal-title":"Remote Sens. Appl. Soc. Environ."},{"issue":"2","key":"4451_CR3","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1016\/j.infrared.2009.10.007","volume":"53","author":"S Yin","year":"2010","unstructured":"Yin, S., Cao, L., Ling, Y., Jin, G.: One color contrast enhanced infrared and visible image fusion method. Infrared Phys. Technol. 53(2), 146\u2013150 (2010)","journal-title":"Infrared Phys. Technol."},{"key":"4451_CR4","volume":"112","author":"J Li","year":"2022","unstructured":"Li, J., Hong, D., Gao, L., Yao, J., Zheng, K., Zhang, B., Chanussot, J.: Deep learning in multimodal remote sensing data fusion: A comprehensive review. Int. J. Appl. Earth Obs. Geoinf. 112, 102926 (2022)","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"4451_CR5","doi-asserted-by":"crossref","unstructured":"Li, H., Wu, X.-J., Kittler, J.: Infrared and visible image fusion using a deep learning framework. In: Proceedings of the 24th International conference on pattern recognition (ICPR), Beijing, China, pp. 2705\u20132710 (2018)","DOI":"10.1109\/ICPR.2018.8546006"},{"issue":"7","key":"4451_CR6","first-page":"3159","volume":"33","author":"W Tang","year":"2022","unstructured":"Tang, W., He, F., Liu, Y.: Ydtr: Infrared and visible image fusion via y-shape dynamic transformer. IEEE Trans. Multimedia 33(7), 3159\u20133172 (2022)","journal-title":"IEEE Trans. Multimedia"},{"key":"4451_CR7","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. Inf. Fusion 48, 11\u201326 (2019)","journal-title":"Inf. Fusion"},{"key":"4451_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102841","volume":"117","author":"Q Wang","year":"2025","unstructured":"Wang, Q., et al.: Smae-fusion: Integrating saliency-aware masked autoencoder with hybrid attention transformer for infrared-visible image fusion. Inf. Fusion 117, 102841 (2025)","journal-title":"Inf. Fusion"},{"key":"4451_CR9","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.inffus.2022.03.007","volume":"83\u201384","author":"L Tang","year":"2022","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":"Inf. Fusion"},{"key":"4451_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102147","volume":"103","author":"H Li","year":"2024","unstructured":"Li, H., Wu, X.-J.: Crossfuse: a novel cross attention mechanism based infrared and visible image fusion approach. Inf. Fusion 103, 102147 (2024)","journal-title":"Inf. Fusion"},{"key":"4451_CR11","doi-asserted-by":"publisher","first-page":"57","DOI":"10.3966\/199115592017042802005","volume":"28","author":"L Zhan","year":"2017","unstructured":"Zhan, L., Zhuang, Y., Huang, L.: Infrared and visible images fusion method based on discrete wavelet transform. J. Comput. 28, 57\u201371 (2017). https:\/\/doi.org\/10.3966\/199115592017042802005","journal-title":"J. Comput."},{"key":"4451_CR12","doi-asserted-by":"publisher","unstructured":"Zheng, Y., Essock, E., Hansen, B.: An advanced image fusion algorithm based on wavelet transform - incorporation with pca and morphological processing. In: Proceedings of SPIE\u2014The International Society for Optical Engineering, vol. 5298 (2004). https:\/\/doi.org\/10.1117\/12.523966","DOI":"10.1117\/12.523966"},{"issue":"1","key":"4451_CR13","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., Jiang, J., Guo, X., Ling, H.: U2Fusion: a unified unsupervised image fusion network. IEEE Trans. Pattern Anal. Mach. Intell. 44(1), 502\u2013518 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2020.3012548","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4451_CR14","doi-asserted-by":"publisher","unstructured":"Dai, Y., Gieseke, F., Oehmcke, S., Wu, Y., Barnard, K.: Attentional feature fusion. In: 2021 IEEE winter conference on applications of computer vision (WACV), pp. 3559\u20133568 (2021). https:\/\/doi.org\/10.1109\/WACV48630.2021.00360","DOI":"10.1109\/WACV48630.2021.00360"},{"key":"4451_CR15","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Salt Lake City, UT, USA, pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"4451_CR16","doi-asserted-by":"publisher","first-page":"4980","DOI":"10.1109\/TIP.2020.2977573","volume":"29","author":"J Ma","year":"2020","unstructured":"Ma, J., Xu, H., Jiang, J., Mei, X., Zhang, X.P.: DDcGAN: a dual-discriminator conditional generative adversarial network for multi-resolution image fusion. IEEE Trans. Image Process. 29, 4980\u20134995 (2020). https:\/\/doi.org\/10.1109\/TIP.2020.2977573","journal-title":"IEEE Trans. Image Process."},{"key":"4451_CR17","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Xu, S., Zhang, C., Liu, J., Li, P., Zhang, J.: DIDFuse: Deep image decomposition for infrared and visible image fusion. arXiv preprint arXiv:2003.09210 (2020)","DOI":"10.24963\/ijcai.2020\/135"},{"issue":"2","key":"4451_CR18","first-page":"892","volume":"27","author":"Q Xiao","year":"2025","unstructured":"Xiao, Q., Jin, H., Su, H., et al.: Spdfusion: a semantic prior knowledge-driven method for infrared and visible image fusion. IEEE Trans. Multimedia 27(2), 892\u2013905 (2025)","journal-title":"IEEE Trans. Multimedia"},{"issue":"1","key":"4451_CR19","first-page":"412","volume":"34","author":"J Li","year":"2025","unstructured":"Li, J., Wang, Y., Zhang, L., et al.: Mafs: knowledge distillation-enhanced progressive heterogeneous fusion for cross-modal segmentation. IEEE Trans. Image Process. 34(1), 412\u2013425 (2025)","journal-title":"IEEE Trans. Image Process."},{"key":"4451_CR20","unstructured":"Chen, W., Liu, Z., Li, M., et al.: Text-guided channel perturbation and pretrained knowledge integration for unified multi-modality image fusion. arXiv:2511.12432v1 (2025)"},{"key":"4451_CR21","doi-asserted-by":"publisher","unstructured":"Yang, C., Luo, X., Zhang, Z., Chen, Z., Wu, X.-j.: KDFuse: A high-level vision task-driven infrared and visible image fusion method based on cross-domain knowledge distillation. Inf. Fusion. (2025) https:\/\/doi.org\/10.1016\/j.inffus.2025.102944","DOI":"10.1016\/j.inffus.2025.102944"},{"issue":"10","key":"4451_CR22","doi-asserted-by":"publisher","first-page":"8756","DOI":"10.1109\/TPAMI.2025.3581162","volume":"47","author":"Z Shao","year":"2025","unstructured":"Shao, Z., Cheng, Y., Li, F., Zhou, Y., Lu, X., Xie, Y., Ma, L.: Mol: Joint estimation of micro-expressions, optical flow and feature points based on transformer-graph convolution. IEEE Trans. Pattern Anal. Mach. Intell. 47(10), 8756\u20138768 (2025). https:\/\/doi.org\/10.1109\/TPAMI.2025.3581162","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"4451_CR23","doi-asserted-by":"publisher","first-page":"1711","DOI":"10.1007\/s11263-024-02258-6","volume":"133","author":"Z Shao","year":"2025","unstructured":"Shao, Z., Zhu, H., Zhou, Y., Xiang, X., Liu, B., Yao, R., Ma, L.: Facial action unit detection via adaptively constrained self-attention and causally deconfounded samples. Int. J. Comput. Vision 133(4), 1711\u20131726 (2025). https:\/\/doi.org\/10.1007\/s11263-024-02258-6","journal-title":"Int. J. Comput. Vision"},{"key":"4451_CR24","doi-asserted-by":"publisher","unstructured":"Sun, Y., Cao, B., Zhu, P., Hu, Q.: DetFusion: A detection-driven infrared and visible image fusion network. In: Proceedings of the 30th acm international conference on multimedia, Lisboa, Portugal (2022). https:\/\/doi.org\/10.1145\/3503161.3547902","DOI":"10.1145\/3503161.3547902"},{"key":"4451_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.109192","volume":"137","author":"C Wang","year":"2024","unstructured":"Wang, C., Pu, Y., Zhao, Z., Nie, R., Cao, J., Xu, D.: FCLFusion: A frequency-aware and collaborative learning for infrared and visible image fusion. Eng. Appl. Artif. Intell. 137, 109192 (2024). https:\/\/doi.org\/10.1016\/j.engappai.2024.109192","journal-title":"Eng. Appl. Artif. Intell."},{"key":"4451_CR26","doi-asserted-by":"publisher","first-page":"3354","DOI":"10.1109\/TIP.2023.3277794","volume":"32","author":"Z Shao","year":"2023","unstructured":"Shao, Z., Zhou, Y., Cai, J., Zhu, H., Yao, R.: Facial action unit detection based on adaptive attention and correlation. IEEE Trans. Image Process. 32, 3354\u20133366 (2023). https:\/\/doi.org\/10.1109\/TIP.2023.3277794","journal-title":"IEEE Trans. Image Process."},{"issue":"2","key":"4451_CR27","doi-asserted-by":"publisher","first-page":"1513","DOI":"10.1109\/TETCI.2024.3352490","volume":"8","author":"Q Liu","year":"2024","unstructured":"Liu, Q., Pi, J., Gao, P., Yuan, D.: STFNet: Self-supervised transformer for infrared and visible image fusion. IEEE Trans. Emerg. Top. Comput. Intell. 8(2), 1513\u20131526 (2024). https:\/\/doi.org\/10.1109\/TETCI.2024.3352490","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"4451_CR28","doi-asserted-by":"crossref","unstructured":"Zhu, H., Shao, Z., Zhou, Y., Wang, G., Chen, P., Li, L.: Personalized image aesthetic assessment via attribute-guided fine-grained feature representation. In: Proceedings of the ACM international conference on multimedia (MM), pp. 6794\u20136802 (2023)","DOI":"10.1145\/3581783.3611942"},{"key":"4451_CR29","doi-asserted-by":"crossref","unstructured":"Tong, T.C., He, S., Shao, Z., Yeung, D.-Y.: G-veval: A general evaluation metric for image and video captioning based on gpt-4o. In: Proceedings of the AAAI conference on artificial intelligence. pp. 7419\u20137427 (2025)","DOI":"10.1609\/aaai.v39i7.32798"},{"key":"4451_CR30","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Essock, E.A., Hansen, B.C.: An advanced image fusion algorithm based on wavelet transform: incorporation with pca and morphological processing. In: Proceedings of SPIE, pp. 177\u2013187 (2004)","DOI":"10.1117\/12.523966"},{"key":"4451_CR31","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on computer vision and pattern recognition (CVPR), Salt Lake City, UT, USA, pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"4451_CR32","doi-asserted-by":"publisher","first-page":"4980","DOI":"10.1109\/TIP.2020.2977573","volume":"29","author":"J Ma","year":"2020","unstructured":"Ma, J., Xu, H., Jiang, J., Mei, X., Zhang, X.-P.: Ddcgan: a dual-discriminator conditional generative adversarial network for multi-resolution image fusion. IEEE Trans. Image Process. 29, 4980\u20134995 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"4451_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110822","volume":"156","author":"W Tang","year":"2024","unstructured":"Tang, W., He, F., Liu, Y.: Itfuse: an interactive transformer for infrared and visible image fusion. Pattern Recogn. 156, 110822 (2024)","journal-title":"Pattern Recogn."},{"key":"4451_CR34","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 multi-modality benchmark to fuse infrared and visible for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 5792\u20135801 (2022)","DOI":"10.1109\/CVPR52688.2022.00571"},{"key":"4451_CR35","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)","DOI":"10.1109\/CVPR52729.2023.00572"},{"key":"4451_CR36","doi-asserted-by":"publisher","unstructured":"Xu, J., He, X.: Daf-net: A dual-branch feature decomposition fusion network with domain adaptive for infrared and visible image fusion. arXiv preprint arXiv:2409.11642 (2024) https:\/\/doi.org\/10.48550\/arXiv.2409.11642","DOI":"10.48550\/arXiv.2409.11642"},{"issue":"03","key":"4451_CR37","doi-asserted-by":"crossref","first-page":"2050015","DOI":"10.1142\/S0219691320500150","volume":"18","author":"Y Liu","year":"2020","unstructured":"Liu, Y., Chen, X., Cheng, J., Peng, H., Wang, Z.: Infrared and visible image fusion with convolutional neural networks. Int. J. Wavelets Multiresolut. Inf. Process. 18(03), 2050015 (2020)","journal-title":"Int. J. Wavelets Multiresolut. Inf. Process."},{"issue":"1","key":"4451_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1117\/1.OE.51.1.010901","volume":"51","author":"A Toet","year":"2012","unstructured":"Toet, A., Hogervorst, M.A.: Progress in color night vision. Opt. Eng. 51(1), 1\u201320 (2012)","journal-title":"Opt. Eng."},{"key":"4451_CR39","doi-asserted-by":"crossref","unstructured":"Xu, H., Ma, J., Le, Z., Jiang, J., Guo, X.: Fusiondn: A unified densely connected network for image fusion. In: Proceedings of the AAAI conference on artificial intelligence (AAAI), pp. 12484\u201312491 (2020)","DOI":"10.1609\/aaai.v34i07.6936"},{"key":"4451_CR40","doi-asserted-by":"crossref","unstructured":"Huang, Z., Liu, J., Fan, X., Liu, R., Zhong, W., Luo, Z.: Reconet: Recurrent correction network for fast and efficient multi-modality image fusion. In: Proceedings of the European conference on computer vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-19797-0_31"},{"key":"4451_CR41","doi-asserted-by":"crossref","unstructured":"Liang, P., Jiang, J., Liu, X., Ma, J.: Fusion from decomposition: a self-supervised decomposition approach for image fusion. In: Proceedings of the European conference on computer vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-19797-0_41"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-026-04451-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-026-04451-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-026-04451-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T13:16:33Z","timestamp":1777468593000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-026-04451-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":41,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["4451"],"URL":"https:\/\/doi.org\/10.1007\/s00371-026-04451-9","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"18 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 April 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 conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This chapter does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"246"}}