{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T02:59:41Z","timestamp":1790823581657,"version":"4.1.0"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171327"],"award-info":[{"award-number":["62171327"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072350"],"award-info":[{"award-number":["62072350"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171328"],"award-info":[{"award-number":["62171328"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Digital Signal Processing"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.dsp.2026.106392","type":"journal-article","created":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T08:48:40Z","timestamp":1784537320000},"page":"106392","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["MSSFuse: Multimodal image fusion with mixed spatial and sequential modeling"],"prefix":"10.1016","volume":"184","author":[{"given":"Taoyang","family":"Ma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tongwei","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Min","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9517-3181","authenticated-orcid":false,"given":"Ye","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.dsp.2026.106392_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2025.105593","article-title":"Infrared and visible image fusion based on one-dimensional guided filtering and cross-modal weight perception","volume":"168","author":"Li","year":"2026","journal-title":"Digit. Signal Process."},{"key":"10.1016\/j.dsp.2026.106392_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2025.105586","article-title":"FRFusion: flare removal for nighttime infrared and visible image fusion","volume":"168","author":"Wang","year":"2026","journal-title":"Digit. Signal Process."},{"key":"10.1016\/j.dsp.2026.106392_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2025.105473","article-title":"Cross-modal information interaction of binocular predictive networks for RGBT tracking","volume":"168","author":"Chen","year":"2026","journal-title":"Digit. Signal Process."},{"key":"10.1016\/j.dsp.2026.106392_bib0004","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2025.105526","article-title":"Visible-infrared person re-identification via adaptive frequency mining and embedding","volume":"168","author":"Sun","year":"2026","journal-title":"Digit. Signal Process."},{"issue":"10","key":"10.1016\/j.dsp.2026.106392_bib0005","doi-asserted-by":"crossref","first-page":"3089","DOI":"10.1109\/TIP.2006.877507","article-title":"The nonsubsampled contourlet transform: theory, design, and applications","volume":"15","author":"Da Cunha","year":"2006","journal-title":"IEEE Trans. Image Process."},{"issue":"8","key":"10.1016\/j.dsp.2026.106392_bib0006","doi-asserted-by":"crossref","first-page":"7579","DOI":"10.1109\/TCSVT.2025.3544746","article-title":"CrossFuse: learning infrared and visible image fusion by cross-sensor top-K vision alignment and beyond","volume":"35","author":"Shi","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.dsp.2026.106392_bib0007","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"},{"key":"10.1016\/j.dsp.2026.106392_bib0008","series-title":"Proceedings of the 2008 International Conference on Content-Based Image and Video Retrieval","first-page":"127","article-title":"Multiple feature fusion by subspace learning","author":"Fu","year":"2008"},{"key":"10.1016\/j.dsp.2026.106392_bib0009","series-title":"2019 International Conference on Image and Video Processing, and Artificial Intelligence","first-page":"181","article-title":"Infrared and visible image fusion using joint convolution sparse coding","volume":"vol. 21","author":"Zhang","year":"2019"},{"key":"10.1016\/j.dsp.2026.106392_bib0010","first-page":"1","article-title":"UFA-FUSE: a novel deep supervised and hybrid model for multifocus image fusion","volume":"70","author":"Zang","year":"2021","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.dsp.2026.106392_bib0011","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.dsp.2026.106392_bib0012","first-page":"1","article-title":"CGTF: convolution-guided transformer for infrared and visible image fusion","volume":"71","author":"Li","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.dsp.2026.106392_bib0013","first-page":"1","article-title":"SwinFuse: a residual swin transformer fusion network for infrared and visible images","volume":"71","author":"Wang","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.dsp.2026.106392_bib0014","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1016\/j.inffus.2022.09.030","article-title":"SGFusion: a saliency guided deep-learning framework for pixel-level image fusion","volume":"91","author":"Liu","year":"2023","journal-title":"Inf. Fusion"},{"issue":"1","key":"10.1016\/j.dsp.2026.106392_bib0015","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":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.dsp.2026.106392_bib0016","doi-asserted-by":"crossref","DOI":"10.1016\/j.infrared.2021.103839","article-title":"Infrared and visible image fusion based on variational auto-encoder and infrared feature compensation","volume":"117","author":"Ren","year":"2021","journal-title":"Infrared Phys. Technol."},{"key":"10.1016\/j.dsp.2026.106392_bib0017","first-page":"1","article-title":"MrFDDGAN: multireceptive field feature transfer and dual discriminator-driven generative adversarial network for infrared and color visible image fusion","volume":"72","author":"Li","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.dsp.2026.106392_bib0018","doi-asserted-by":"crossref","unstructured":"T. Zhang, Y. Zhu, J. Zhao, G. Cui, Y. Zheng, Exploring state space model in wavelet domain: an infrared and visible image fusion network via wavelet transform and state space model, 2025, arXiv: 2503.18378 [cs.CV].","DOI":"10.1109\/ICME59968.2025.11209539"},{"key":"10.1016\/j.dsp.2026.106392_bib0019","series-title":"International Joint Conference on Artificial Intelligence (IJCAI)","first-page":"970","article-title":"DIDFuse: deep image decomposition for infrared and visible image fusion","author":"Zhao","year":"2020"},{"key":"10.1016\/j.dsp.2026.106392_bib0020","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"2126","article-title":"TransMEF: a transformer-based multi-exposure image fusion framework using self-supervised multi-task learning","volume":"vol. 36","author":"Qu","year":"2022"},{"key":"10.1016\/j.dsp.2026.106392_bib0021","series-title":"2022 IEEE International Conference on Image Processing (ICIP)","first-page":"3566","article-title":"Image fusion transformer","author":"Vs","year":"2022"},{"key":"10.1016\/j.dsp.2026.106392_bib0022","unstructured":"Y. Fu, T. Xu, X. Wu, J. Kittler, PPT fusion: pyramid patch transformer for a case study in image fusion, 2021, arXiv: 2107.13967 [cs.CV]."},{"key":"10.1016\/j.dsp.2026.106392_bib0023","doi-asserted-by":"crossref","first-page":"4816","DOI":"10.1109\/TIP.2020.2976190","article-title":"DRPL: deep regression pair learning for multi-focus image fusion","volume":"29","author":"Li","year":"2020","journal-title":"IEEE Trans. Image Process."},{"issue":"6","key":"10.1016\/j.dsp.2026.106392_bib0024","doi-asserted-by":"crossref","DOI":"10.1007\/s11760-025-04131-6","article-title":"Infrared and visible image fusion network based on low-light image enhancement and attention mechanism","volume":"19","author":"Lu","year":"2025","journal-title":"Signal Image Video Process."},{"key":"10.1016\/j.dsp.2026.106392_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.111728","article-title":"Multi-scale frequency attention fusion network for infrared and visible image fusion","volume":"159","author":"Wang","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.dsp.2026.106392_bib0026","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, et al., An image is worth 16x16 words: transformers for image recognition at scale, 2020, arXiv: 2010.11929 [cs.CV]."},{"key":"10.1016\/j.dsp.2026.106392_bib0027","series-title":"2021 International Conference on Information Technology and Biomedical Engineering (ICITBE)","first-page":"71","article-title":"DNDT: infrared and visible image fusion via densenet and dual-transformer","author":"Zhao","year":"2021"},{"key":"10.1016\/j.dsp.2026.106392_bib0028","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2024.104916","article-title":"ETBIFusion: an infrared and visible image fusion network with edge-texture enhancement and bidirectional interaction","volume":"157","author":"Li","year":"2025","journal-title":"Digit. Signal Process."},{"key":"10.1016\/j.dsp.2026.106392_bib0029","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2025.104996","article-title":"MCAFNet: multiscale cross-modality adaptive fusion network for multispectral object detection","volume":"159","author":"Zheng","year":"2025","journal-title":"Digit. Signal Process."},{"key":"10.1016\/j.dsp.2026.106392_bib0030","unstructured":"W. Li, X. Lu, J. Lu, X. Zhang, J. Jia, On efficient transformer and image pre-training for low-level vision, 2021, arXiv: 2112.10175 [cs.CV]."},{"key":"10.1016\/j.dsp.2026.106392_bib0031","doi-asserted-by":"crossref","first-page":"1340","DOI":"10.1109\/TIP.2025.3541562","article-title":"MaeFuse: transferring omni features with pretrained masked autoencoders for infrared and visible image fusion via guided training","volume":"34","author":"Li","year":"2025","journal-title":"IEEE Trans. Image Process."},{"issue":"6","key":"10.1016\/j.dsp.2026.106392_bib0032","doi-asserted-by":"crossref","first-page":"5518","DOI":"10.1109\/TCSVT.2024.3520252","article-title":"An infrared and visible image fusion method based on semantic-sensitive mask selection and bidirectional-collaboration region fusion","volume":"35","author":"Li","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"8","key":"10.1016\/j.dsp.2026.106392_bib0033","article-title":"Infrared and visible image fusion based on cross-modal feature interaction and multi-scale reconstruction","volume":"54","author":"Yao","year":"2025","journal-title":"Infrared Laser Eng."},{"issue":"17","key":"10.1016\/j.dsp.2026.106392_bib0034","article-title":"Infrared-visible image registration and fusion based on dynamic convolutional dual attention network","volume":"2","author":"Xia","year":"2025","journal-title":"Acta Opt. Sin."},{"key":"10.1016\/j.dsp.2026.106392_bib0035","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2025.3587918","article-title":"CFMW: cross-modality fusion Mamba for robust object detection under adverse weather","author":"Li","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.dsp.2026.106392_bib0036","doi-asserted-by":"crossref","DOI":"10.1109\/TMM.2025.3599020","article-title":"Fusion-Mamba for cross-modality object detection","author":"Dong","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.dsp.2026.106392_bib0037","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/j.inffus.2022.03.007","article-title":"PIAFusion: a progressive infrared and visible image fusion network based on illumination aware","volume":"83-84","author":"Tang","year":"2022","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.dsp.2026.106392_bib0038","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2025.105200","article-title":"SDATFuse: sparse dual aggregation transformer-based network for infrared and visible image fusion","volume":"162","author":"Guo","year":"2025","journal-title":"Digit. Signal Process."},{"key":"10.1016\/j.dsp.2026.106392_bib0039","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2025.105136","article-title":"P3TFusion: progressive two-stage infrared and visible image fusion network focused on enhancing target and texture information","volume":"162","author":"Li","year":"2025","journal-title":"Digit. Signal Process."},{"key":"10.1016\/j.dsp.2026.106392_bib0040","series-title":"AAAI Conference on Artificial Intelligence","first-page":"12484","article-title":"Fusiondn: a unified densely connected network for image fusion","author":"Xu","year":"2020"},{"issue":"1","key":"10.1016\/j.dsp.2026.106392_bib0041","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1117\/1.OE.51.1.010901","article-title":"Progress in color night vision","volume":"51","author":"Toet","year":"2012","journal-title":"Opt. Eng."},{"key":"10.1016\/j.dsp.2026.106392_bib0042","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2025.105203","article-title":"Infrared and visible image fusion based on text-image core-semantic alignment and interaction","volume":"163","author":"Li","year":"2025","journal-title":"Digit. Signal Process."},{"key":"10.1016\/j.dsp.2026.106392_bib0043","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1016\/j.inffus.2018.02.004","article-title":"Infrared and visible image fusion methods and applications: a survey","volume":"45","author":"Ma","year":"2019","journal-title":"Inf. Fusion"},{"issue":"1","key":"10.1016\/j.dsp.2026.106392_bib0044","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.dsp.2026.106392_bib0045","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"},{"key":"10.1016\/j.dsp.2026.106392_bib0046","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.dsp.2026.106392_bib0047","unstructured":"A. Toet, TNO Image Fusion Dataset, figshare, 2014, 10.6084\/m9.figshare.1008029."},{"key":"10.1016\/j.dsp.2026.106392_bib0048","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110822","article-title":"ITFuse: an interactive transformer for infrared and visible image fusion","volume":"156","author":"Tang","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.dsp.2026.106392_bib0049","doi-asserted-by":"crossref","DOI":"10.1016\/j.optlaseng.2023.107925","article-title":"BTSFusion: fusion of infrared and visible image via a mechanism of balancing texture and salience","volume":"173","author":"Qian","year":"2024","journal-title":"Opt. Lasers Eng."}],"container-title":["Digital Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1051200426005105?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1051200426005105?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T02:52:35Z","timestamp":1790823155000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1051200426005105"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":49,"alternative-id":["S1051200426005105"],"URL":"https:\/\/doi.org\/10.1016\/j.dsp.2026.106392","relation":{},"ISSN":["1051-2004"],"issn-type":[{"value":"1051-2004","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MSSFuse: Multimodal image fusion with mixed spatial and sequential modeling","name":"articletitle","label":"Article Title"},{"value":"Digital Signal Processing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.dsp.2026.106392","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"106392"}}