{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T14:15:26Z","timestamp":1788185726654,"version":"build-2803163510"},"reference-count":42,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100003009","name":"Science and Technology Development Fund","doi-asserted-by":"publisher","award":["2025ZY01045"],"award-info":[{"award-number":["2025ZY01045"]}],"id":[{"id":"10.13039\/501100003009","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017630","name":"Humanities and Social Sciences Youth Foundation, Ministry of Education","doi-asserted-by":"publisher","award":["23YJCZH083"],"award-info":[{"award-number":["23YJCZH083"]}],"id":[{"id":"10.13039\/501100017630","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LQN26F030024"],"award-info":[{"award-number":["LQN26F030024"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62301322"],"award-info":[{"award-number":["62301322"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114471","type":"journal-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T15:35:42Z","timestamp":1784216142000},"page":"114471","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PE","title":["Unsupervised multimodal remote sensing image registration via two-stream causal sequential inference"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7825-0902","authenticated-orcid":false,"given":"Han","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baoheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Risheng","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0113-6968","authenticated-orcid":false,"given":"Wanzeng","family":"Kong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114471_b1","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1016\/j.isprsjprs.2025.08.028","article-title":"Feature-based multimodal remote sensing image matching: Benchmark and state-of-the-art","volume":"229","author":"Geng","year":"2025","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114471_b2","doi-asserted-by":"crossref","first-page":"14965","DOI":"10.1109\/JSTARS.2024.3411706","article-title":"Multimodal remote sensing image registration based on adaptive spectrum congruency","volume":"17","author":"Huang","year":"2024","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens."},{"key":"10.1016\/j.patcog.2026.114471_b3","article-title":"Robust registration of multi-modal remote sensing images based on multi-dimensional oriented self-similarity features","volume":"127","author":"Zhang","year":"2024","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"10.1016\/j.patcog.2026.114471_b4","article-title":"Refining multi-modal remote sensing image matching with repetitive feature optimization","volume":"134","author":"Liao","year":"2024","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"10.1016\/j.patcog.2026.114471_b5","doi-asserted-by":"crossref","first-page":"14615","DOI":"10.1109\/JSTARS.2025.3576233","article-title":"WinMRSI: Feature matching with window attention for multimodal remote sensing image","volume":"18","author":"Di","year":"2025","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens."},{"issue":"2","key":"10.1016\/j.patcog.2026.114471_b6","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1023\/A:1007958904918","article-title":"Alignment by maximization of mutual information","volume":"24","author":"Viola","year":"1997","journal-title":"Int. J. Comput. Vis."},{"issue":"2","key":"10.1016\/j.patcog.2026.114471_b7","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1109\/TIP.2014.2387019","article-title":"Multimodal registration via mutual information incorporating geometric and spatial context","volume":"24","author":"Woo","year":"2015","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114471_b8","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","article-title":"Distinctive image features from scale-invariant keypoints","volume":"60","author":"Lowe","year":"2004","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.114471_b9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2022.3157870","article-title":"Robust feature matching for remote sensing image registration via guided hyperplane fitting","volume":"60","author":"Xiao","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114471_b10","first-page":"1","article-title":"R2FD2: Fast and robust matching of multimodal remote sensing images via repeatable feature detector and rotation-invariant feature descriptor","volume":"61","author":"Zhu","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114471_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112469","article-title":"Matrix formula for subpixel image registration","volume":"172","author":"Geng","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114471_b12","first-page":"1","article-title":"Self-distillation feature learning network for optical and SAR image registration","volume":"60","author":"Quan","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114471_b13","first-page":"1","article-title":"Optical and SAR image registration based on feature decoupling network","volume":"60","author":"Xiang","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114471_b14","doi-asserted-by":"crossref","first-page":"4739","DOI":"10.1109\/JSTARS.2023.3276409","article-title":"Efficient and robust: A cross-modal registration deep wavelet learning method for remote sensing images","volume":"16","author":"Quan","year":"2023","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens."},{"key":"10.1016\/j.patcog.2026.114471_b15","first-page":"1","article-title":"F3Net: Adaptive frequency feature filtering network for multimodal remote sensing image registration","volume":"62","author":"Quan","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114471_b16","first-page":"1","article-title":"Learning modality-invariant feature for multimodal image matching via knowledge distillation","volume":"63","author":"Liu","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114471_b17","first-page":"1","article-title":"Robust optical and SAR image matching using attention-enhanced structural features","volume":"62","author":"Ye","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"1","key":"10.1016\/j.patcog.2026.114471_b18","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1109\/TMI.2023.3288136","article-title":"TransMatch: A transformer-based multilevel dual-stream feature matching network for unsupervised deformable image registration","volume":"43","author":"Chen","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.patcog.2026.114471_b19","doi-asserted-by":"crossref","unstructured":"\u00d6. Tuzcuo\u011flu, A. K\u00f6ksal, B. Sofu, S. Kalkan, A.A. Alatan, XoFTR: Cross-Modal Feature Matching Transformer, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2024, pp. 4275\u20134285.","DOI":"10.1109\/CVPRW63382.2024.00431"},{"key":"10.1016\/j.patcog.2026.114471_b20","first-page":"1","article-title":"SwinMatcher: Universal cross-modal remote sensing image matching with interactive Swin Transformer","volume":"63","author":"Li","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114471_b21","doi-asserted-by":"crossref","unstructured":"J. Ren, X. Jiang, Z. Li, D. Liang, X. Zhou, X. Bai, MINIMA: Modality Invariant Image Matching, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2025, pp. 23059\u201323068.","DOI":"10.1109\/CVPR52734.2025.02147"},{"key":"10.1016\/j.patcog.2026.114471_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111120","article-title":"TransMatch: Transformer-based correspondence pruning via local and global consensus","volume":"159","author":"Liu","year":"2025","journal-title":"Pattern Recognit."},{"issue":"8","key":"10.1016\/j.patcog.2026.114471_b23","doi-asserted-by":"crossref","first-page":"1788","DOI":"10.1109\/TMI.2019.2897538","article-title":"VoxelMorph: A learning framework for deformable medical image registration","volume":"38","author":"Balakrishnan","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.patcog.2026.114471_b24","first-page":"1","article-title":"A multiscale framework with unsupervised learning for remote sensing image registration","volume":"60","author":"Ye","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114471_b25","first-page":"1","article-title":"Multimodal image fusion framework for end-to-end remote sensing image registration","volume":"61","author":"Li","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114471_b26","first-page":"1","article-title":"Unsupervised multimodal remote sensing image registration via domain adaptation","volume":"61","author":"Shi","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114471_b27","first-page":"1","article-title":"Multimodal remote sensing image registration via modality perception and self-supervised position estimation","volume":"63","author":"Xiao","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114471_b28","first-page":"1","article-title":"Adaptive self-supervised SAR image registration with modifications of alignment transformation","volume":"61","author":"Mao","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114471_b29","first-page":"1","article-title":"A global-to-local algorithm for high-resolution optical and SAR image registration","volume":"61","author":"Xiang","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114471_b30","first-page":"1","article-title":"FRIM: A framework for satellite-Borne remote sensing image matching","volume":"63","author":"Geng","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"1","key":"10.1016\/j.patcog.2026.114471_b31","doi-asserted-by":"crossref","first-page":"12941","DOI":"10.1038\/s41598-023-39863-3","article-title":"General cross-modality registration framework for visible and infrared UAV target image registration","volume":"13","author":"Luo","year":"2023","journal-title":"Sci. Rep."},{"key":"10.1016\/j.patcog.2026.114471_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2022.102615","article-title":"TransMorph: Transformer for unsupervised medical image registration","volume":"82","author":"Chen","year":"2022","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.patcog.2026.114471_b33","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022","first-page":"217","article-title":"XMorpher: Full transformer for deformable medical image registration via cross attention","author":"Shi","year":"2022"},{"key":"10.1016\/j.patcog.2026.114471_b34","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112955","article-title":"PCRNet: A multiscale cross-attention network for large deformation medical image registration","volume":"174","author":"Deng","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114471_b35","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112925","article-title":"LDM-Morph: Latent diffusion model guided deformable image registration","volume":"174","author":"Wu","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114471_b36","doi-asserted-by":"crossref","unstructured":"M. Brown, S. S\u00fcsstrunk, Multi-spectral SIFT for Scene Category Recognition, in: 2011 IEEE Conference on Computer Vision and Pattern Recognition, 2011, pp. 177\u2013184.","DOI":"10.1109\/CVPR.2011.5995637"},{"key":"10.1016\/j.patcog.2026.114471_b37","first-page":"141","article-title":"The SEN1-2 dataset for deep learning in SAR-optical data fusion","volume":"IV-1","author":"Schmitt","year":"2018","journal-title":"ISPRS Ann. Photogramm. Remote. Sens. Spat. Inf. Sci."},{"key":"10.1016\/j.patcog.2026.114471_b38","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1109\/TIP.2022.3231135","article-title":"ReDFeat: Recoupling detection and description for multimodal feature learning","volume":"32","author":"Deng","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114471_b39","series-title":"Advances in Neural Information Processing Systems","first-page":"61306","article-title":"Unsupervised homography estimation on multimodal image pair via alternating optimization","author":"Song","year":"2024"},{"issue":"Part C","key":"10.1016\/j.patcog.2026.114471_b40","article-title":"Cross-scale infrared and visible image registration based on phase consistency feature for UAV scenario","volume":"258","author":"Li","year":"2026","journal-title":"Measurement"},{"key":"10.1016\/j.patcog.2026.114471_b41","first-page":"1","article-title":"Multimodal remote sensing image robust matching based on second-order tensor orientation feature transformation","volume":"63","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114471_b42","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.102027","article-title":"POS-GIFT: A geometric and intensity-invariant feature transformation for multimodal images","volume":"102","author":"Hou","year":"2024","journal-title":"Inf. Fusion"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326014354?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326014354?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T13:32:10Z","timestamp":1788183130000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326014354"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":42,"alternative-id":["S0031320326014354"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114471","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Unsupervised multimodal remote sensing image registration via two-stream causal sequential inference","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114471","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"114471"}}