{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T15:23:37Z","timestamp":1787412217988,"version":"build-2736575974"},"reference-count":54,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100017587","name":"Hebei University of Engineering","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100017587","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Image and Vision Computing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.imavis.2026.106149","type":"journal-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T06:33:39Z","timestamp":1786084419000},"page":"106149","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["SETFusion: Dual-domain feature learning with Spectral-Enhanced Transformer for infrared and visible image fusion"],"prefix":"10.1016","volume":"174","author":[{"given":"Liang","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongcheng","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jijun","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.imavis.2026.106149_b1","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.inffus.2014.09.008","article-title":"Multisensor video fusion based on higher order singular value decomposition","volume":"24","author":"Zhang","year":"2015","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.imavis.2026.106149_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2019.106977","article-title":"RGB-T object tracking: Benchmark and baseline","volume":"96","author":"Li","year":"2019","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.imavis.2026.106149_b3","series-title":"Proceedings of the 27th ACM International Conference on Multimedia","first-page":"465","article-title":"Dense feature aggregation and pruning for RGBT tracking","author":"Zhu","year":"2019"},{"issue":"3","key":"10.1016\/j.imavis.2026.106149_b4","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1109\/LSP.2019.2895749","article-title":"Medical image fusion via convolutional sparsity based morphological component analysis","volume":"26","author":"Liu","year":"2019","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.imavis.2026.106149_b5","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.neucom.2015.07.160","article-title":"An overview of multi-modal medical image fusion","volume":"215","author":"Du","year":"2016","journal-title":"Neurocomputing"},{"key":"10.1016\/j.imavis.2026.106149_b6","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1016\/j.inffus.2020.04.006","article-title":"Pan-GAN: An unsupervised pan-sharpening method for remote sensing image fusion","volume":"62","author":"Ma","year":"2020","journal-title":"Inf. Fusion"},{"issue":"9","key":"10.1016\/j.imavis.2026.106149_b7","doi-asserted-by":"crossref","first-page":"3367","DOI":"10.1109\/TIM.2018.2877285","article-title":"Image fusion using adjustable non-subsampled shearlet transform","volume":"68","author":"Vishwakarma","year":"2019","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.imavis.2026.106149_b8","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/j.inffus.2014.09.004","article-title":"A general framework for image fusion based on multi-scale transform and sparse representation","volume":"24","author":"Liu","year":"2015","journal-title":"Inf. Fusion"},{"issue":"4","key":"10.1016\/j.imavis.2026.106149_b9","doi-asserted-by":"crossref","first-page":"884","DOI":"10.1109\/TIM.2009.2026612","article-title":"Multifocus image fusion and restoration with sparse representation","volume":"59","author":"Yang","year":"2010","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.imavis.2026.106149_b10","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.neucom.2012.12.015","article-title":"Fast saliency-aware multi-modality image fusion","volume":"111","author":"Han","year":"2013","journal-title":"Neurocomputing"},{"issue":"10","key":"10.1016\/j.imavis.2026.106149_b11","doi-asserted-by":"crossref","first-page":"2761","DOI":"10.1007\/s11263-021-01501-8","article-title":"SDNet: A versatile squeeze-and-decomposition network for real-time image fusion","volume":"129","author":"Zhang","year":"2021","journal-title":"Int. J. Comput. Vis."},{"issue":"4","key":"10.1016\/j.imavis.2026.106149_b12","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1049\/iet-ipr.2014.0245","article-title":"Infrared-visible video fusion based on motion-compensated wavelet transforms","volume":"9","author":"Xu","year":"2015","journal-title":"IET Image Process."},{"issue":"5","key":"10.1016\/j.imavis.2026.106149_b13","doi-asserted-by":"crossref","first-page":"2614","DOI":"10.1109\/TIP.2018.2887342","article-title":"DenseFuse: A fusion approach to infrared and visible images","volume":"28","author":"Li","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.imavis.2026.106149_b14","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.inffus.2019.07.011","article-title":"IFCNN: A general image fusion framework based on convolutional neural network","volume":"54","author":"Zhang","year":"2020","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.imavis.2026.106149_b15","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/j.inffus.2021.06.002","article-title":"Self-supervised feature adaption for infrared and visible image fusion","volume":"76","author":"Zhao","year":"2021","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.imavis.2026.106149_b16","doi-asserted-by":"crossref","first-page":"4980","DOI":"10.1109\/TIP.2020.2977573","article-title":"DDcGAN: A dual-discriminator conditional generative adversarial network for multi-resolution image fusion","volume":"29","author":"Ma","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.imavis.2026.106149_b17","doi-asserted-by":"crossref","first-page":"7203","DOI":"10.1109\/TIP.2020.2999855","article-title":"MEF-GAN: multi-exposure image fusion via generative adversarial networks","volume":"29","author":"Xu","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.imavis.2026.106149_b18","doi-asserted-by":"crossref","first-page":"55145","DOI":"10.1109\/ACCESS.2020.2982016","article-title":"Mgmdcgan: Medical image fusion using multi-generator multi-discriminator conditional generative adversarial network","volume":"8","author":"Huang","year":"2020","journal-title":"IEEE Access"},{"issue":"7","key":"10.1016\/j.imavis.2026.106149_b19","doi-asserted-by":"crossref","first-page":"1200","DOI":"10.1109\/JAS.2022.105686","article-title":"SwinFusion: Cross-domain long-range learning for general image fusion via swin transformer","volume":"9","author":"Ma","year":"2022","journal-title":"IEEE CAA J. Autom. Sin."},{"key":"10.1016\/j.imavis.2026.106149_b20","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1016\/j.inffus.2021.06.008","article-title":"Image fusion meets deep learning: A survey and perspective","volume":"76","author":"Zhang","year":"2021","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.imavis.2026.106149_b21","series-title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","first-page":"970","article-title":"DIDFuse: Deep image decomposition for infrared and visible image fusion","author":"Zhao","year":"2020"},{"key":"10.1016\/j.imavis.2026.106149_b22","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1016\/j.inffus.2017.10.007","article-title":"Deep learning for pixel-level image fusion: Recent advances and future prospects","volume":"42","author":"Liu","year":"2018","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.imavis.2026.106149_b23","doi-asserted-by":"crossref","unstructured":"L. Qu, S. Liu, M. Wang, Z. Song, TransMEF: A Transformer-Based Multi-Exposure Image Fusion Framework Using Self-Supervised Multi-Task Learning, in: Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022, 2022, pp. 2126\u20132134.","DOI":"10.1609\/aaai.v36i2.20109"},{"key":"10.1016\/j.imavis.2026.106149_b24","doi-asserted-by":"crossref","unstructured":"V. VS, J.M.J. Valanarasu, P. Oza, V.M. Patel, Image Fusion Transformer, in: 2022 IEEE International Conference on Image Processing, ICIP 2022, 2022, pp. 3566\u20133570.","DOI":"10.1109\/ICIP46576.2022.9897280"},{"key":"10.1016\/j.imavis.2026.106149_b25","series-title":"TGFuse: An infrared and visible image fusion approach based on transformer and generative adversarial network","author":"Rao","year":"2022"},{"key":"10.1016\/j.imavis.2026.106149_b26","doi-asserted-by":"crossref","unstructured":"Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, B. Guo, Swin Transformer: Hierarchical Vision Transformer using Shifted Windows, in: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, 2021, pp. 9992\u201310002.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10.1016\/j.imavis.2026.106149_b27","series-title":"SpectFormer: Frequency and attention is what you need in a vision transformer","author":"Patro","year":"2023"},{"key":"10.1016\/j.imavis.2026.106149_b28","doi-asserted-by":"crossref","unstructured":"K.R. Prabhakar, V.S. Srikar, R.V. Babu, DeepFuse: A Deep Unsupervised Approach for Exposure Fusion with Extreme Exposure Image Pairs, in: IEEE International Conference on Computer Vision, ICCV 2017, 2017, pp. 4724\u20134732.","DOI":"10.1109\/ICCV.2017.505"},{"key":"10.1016\/j.imavis.2026.106149_b29","series-title":"The Thirty-Fourth AAAI Conference on Artificial Intelligence","first-page":"12797","article-title":"Rethinking the image fusion: A fast unified image fusion network based on proportional maintenance of gradient and intensity","author":"Zhang","year":"2020"},{"issue":"12","key":"10.1016\/j.imavis.2026.106149_b30","doi-asserted-by":"crossref","first-page":"9645","DOI":"10.1109\/TIM.2020.3005230","article-title":"NestFuse: An infrared and visible image fusion architecture based on nest connection and spatial\/channel attention models","volume":"69","author":"Li","year":"2020","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.imavis.2026.106149_b31","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.inffus.2021.02.023","article-title":"RFN-nest: An end-to-end residual fusion network for infrared and visible images","volume":"73","author":"Li","year":"2021","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.imavis.2026.106149_b32","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.inffus.2018.09.004","article-title":"FusionGAN: A generative adversarial network for infrared and visible image fusion","volume":"48","author":"Ma","year":"2019","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.imavis.2026.106149_b33","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.inffus.2019.07.005","article-title":"Infrared and visible image fusion via detail preserving adversarial learning","volume":"54","author":"Ma","year":"2020","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.imavis.2026.106149_b34","doi-asserted-by":"crossref","unstructured":"J. Liu, X. Fan, Z. Huang, G. Wu, R. Liu, W. Zhong, Z. Luo, Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection, in: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, 2022, pp. 5792\u20135801.","DOI":"10.1109\/CVPR52688.2022.00571"},{"key":"10.1016\/j.imavis.2026.106149_b35","doi-asserted-by":"crossref","first-page":"8988","DOI":"10.1109\/TMM.2023.3243659","article-title":"Transformer based conditional GAN for multimodal image fusion","volume":"25","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Multim."},{"issue":"2","key":"10.1016\/j.imavis.2026.106149_b36","doi-asserted-by":"crossref","first-page":"1513","DOI":"10.1109\/TETCI.2024.3352490","article-title":"Stfnet: Self-supervised transformer for infrared and visible image fusion","volume":"8","author":"Liu","year":"2024","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"10.1016\/j.imavis.2026.106149_b37","doi-asserted-by":"crossref","first-page":"3098","DOI":"10.1109\/TIP.2021.3058764","article-title":"Deep coupled feedback network for joint exposure fusion and image super-resolution","volume":"30","author":"Deng","year":"2021","journal-title":"IEEE Trans. Image Process."},{"issue":"12","key":"10.1016\/j.imavis.2026.106149_b38","doi-asserted-by":"crossref","first-page":"2121","DOI":"10.1109\/JAS.2022.106082","article-title":"SuperFusion: A versatile image registration and fusion network with semantic awareness","volume":"9","author":"Tang","year":"2022","journal-title":"IEEE CAA J. Autom. Sin."},{"key":"10.1016\/j.imavis.2026.106149_b39","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1016\/j.inffus.2022.10.034","article-title":"DIVFusion: Darkness-free infrared and visible image fusion","volume":"91","author":"Tang","year":"2023","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.imavis.2026.106149_b40","article-title":"TGFuse: An infrared and visible image fusion approach based on transformer and generative adversarial network","author":"Rao","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.imavis.2026.106149_b41","doi-asserted-by":"crossref","unstructured":"J. Liang, J. Cao, G. Sun, K. Zhang, L.V. Gool, R. Timofte, SwinIR: Image Restoration Using Swin Transformer, in: IEEE\/CVF International Conference on Computer Vision Workshops, ICCVW 2021, 2021, pp. 1833\u20131844.","DOI":"10.1109\/ICCVW54120.2021.00210"},{"issue":"4","key":"10.1016\/j.imavis.2026.106149_b42","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.imavis.2026.106149_b43","series-title":"Computer Vision - ECCV 2016 - 14th European Conference, Proceedings, Part II","first-page":"694","article-title":"Perceptual losses for real-time style transfer and super-resolution","volume":"vol. 9906","author":"Johnson","year":"2016"},{"key":"10.1016\/j.imavis.2026.106149_b44","series-title":"TNO image fusion dataset","author":"Alexander","year":"2014"},{"key":"10.1016\/j.imavis.2026.106149_b45","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.inffus.2021.12.004","article-title":"Image fusion in the loop of high-level vision tasks: A semantic-aware real-time infrared and visible image fusion network","volume":"82","author":"Tang","year":"2022","journal-title":"Inf. Fusion"},{"issue":"1","key":"10.1016\/j.imavis.2026.106149_b46","doi-asserted-by":"crossref","first-page":"502","DOI":"10.1109\/TPAMI.2020.3012548","article-title":"U2Fusion: A unified unsupervised image fusion network","volume":"44","author":"Xu","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.imavis.2026.106149_b47","series-title":"IEEE\/CVF International Conference on Computer Vision","first-page":"8048","article-title":"DDFM: denoising diffusion model for multi-modality image fusion","author":"Zhao","year":"2023"},{"key":"10.1016\/j.imavis.2026.106149_b48","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.102147","article-title":"CrossFuse: A novel cross attention mechanism based infrared and visible image fusion approach","volume":"103","author":"Li","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.imavis.2026.106149_b49","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"25912","article-title":"Equivariant multi-modality image fusion","author":"Zhao","year":"2024"},{"key":"10.1016\/j.imavis.2026.106149_b50","series-title":"One model for ALL: low-level task interaction is a key to task-agnostic image fusion","author":"Cheng","year":"2025"},{"issue":"5","key":"10.1016\/j.imavis.2026.106149_b51","doi-asserted-by":"crossref","first-page":"744","DOI":"10.1016\/j.compeleceng.2011.07.012","article-title":"A non-reference image fusion metric based on mutual information of image features","volume":"37","author":"Haghighat","year":"2011","journal-title":"Comput. Electr. Eng."},{"key":"10.1016\/j.imavis.2026.106149_b52","doi-asserted-by":"crossref","unstructured":"M. Haghighat, M.A. Razian, Fast-FMI: Non-reference image fusion metric, in: IEEE International Conference on Application of Information & Communication Technologies, 2014, pp. 1\u20133.","DOI":"10.1109\/ICAICT.2014.7036000"},{"issue":"2","key":"10.1016\/j.imavis.2026.106149_b53","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.inffus.2011.08.002","article-title":"A new image fusion performance metric based on visual information fidelity","volume":"14","author":"Han","year":"2013","journal-title":"Inf. Fusion"},{"issue":"4","key":"10.1016\/j.imavis.2026.106149_b54","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1049\/el:20000267","article-title":"Objective image fusion performance measure","volume":"36","author":"Xydeas","year":"2000","journal-title":"Electron. Lett."}],"container-title":["Image and Vision Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885626002568?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885626002568?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T14:43:29Z","timestamp":1787409809000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0262885626002568"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":54,"alternative-id":["S0262885626002568"],"URL":"https:\/\/doi.org\/10.1016\/j.imavis.2026.106149","relation":{},"ISSN":["0262-8856"],"issn-type":[{"value":"0262-8856","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SETFusion: Dual-domain feature learning with Spectral-Enhanced Transformer for infrared and visible image fusion","name":"articletitle","label":"Article Title"},{"value":"Image and Vision Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.imavis.2026.106149","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"106149"}}