{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T07:04:22Z","timestamp":1784531062534,"version":"3.55.0"},"reference-count":54,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Image and Vision Computing"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.imavis.2026.106047","type":"journal-article","created":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T05:25:19Z","timestamp":1780118719000},"page":"106047","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Rethinking remote sensing change detection with state space models and self-supervised learning"],"prefix":"10.1016","volume":"173","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9000-9151","authenticated-orcid":false,"given":"Xingyuan","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jijie","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongjie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suli","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"14","key":"10.1016\/j.imavis.2026.106047_b1","doi-asserted-by":"crossref","first-page":"5843","DOI":"10.1109\/JSEN.2019.2904137","article-title":"A machine learning-based approach for land cover change detection using remote sensing and radiometric measurements","volume":"19","author":"Zerrouki","year":"2019","journal-title":"IEEE Sensors J."},{"key":"10.1016\/j.imavis.2026.106047_b2","article-title":"Adaptive multi-sensor fusion for remote sensing change detection using USASE","author":"Shi","year":"2025","journal-title":"IEEE Sensors J."},{"key":"10.1016\/j.imavis.2026.106047_b3","first-page":"1","article-title":"UrbanEvolver: function-aware urban layout regeneration","author":"Qin","year":"2024","journal-title":"Int. J. Comput. Vis."},{"issue":"2","key":"10.1016\/j.imavis.2026.106047_b4","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1007\/s11263-021-01554-9","article-title":"Sensaturban: Learning semantics from urban-scale photogrammetric point clouds","volume":"130","author":"Hu","year":"2022","journal-title":"Int. J. Comput. Vis."},{"issue":"11","key":"10.1016\/j.imavis.2026.106047_b5","doi-asserted-by":"crossref","first-page":"18108","DOI":"10.1109\/JSEN.2024.3390674","article-title":"Remote sensing image change detection combined with saliency","volume":"24","author":"Zhang","year":"2024","journal-title":"IEEE Sensors J."},{"key":"10.1016\/j.imavis.2026.106047_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.rse.2019.111402","article-title":"Remote sensing for agricultural applications: A meta-review","volume":"236","author":"Weiss","year":"2020","journal-title":"Remote Sens. Environ."},{"key":"10.1016\/j.imavis.2026.106047_b7","first-page":"1","article-title":"Single-temporal supervised learning for universal remote sensing change detection","author":"Zheng","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.imavis.2026.106047_b8","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.isprsjprs.2013.03.006","article-title":"Change detection from remotely sensed images: From pixel-based to object-based approaches","volume":"80","author":"Hussain","year":"2013","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.imavis.2026.106047_b9","first-page":"1","article-title":"BiFA: Remote sensing image change detection with bitemporal feature alignment","volume":"62","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"24","key":"10.1016\/j.imavis.2026.106047_b10","doi-asserted-by":"crossref","first-page":"30751","DOI":"10.1109\/JSEN.2023.3328990","article-title":"YOLO-FSD: An improved target detection algorithm on remote-sensing images","volume":"23","author":"Zhao","year":"2023","journal-title":"IEEE Sensors J."},{"issue":"12","key":"10.1016\/j.imavis.2026.106047_b11","doi-asserted-by":"crossref","first-page":"13680","DOI":"10.1109\/JSEN.2023.3271391","article-title":"Cross-attention guided group aggregation network for cropland change detection","volume":"23","author":"Xu","year":"2023","journal-title":"IEEE Sensors J."},{"key":"10.1016\/j.imavis.2026.106047_b12","first-page":"1","article-title":"Ultra-high resolution image segmentation via locality-aware context fusion and alternating local enhancement","author":"Liu","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.imavis.2026.106047_b13","first-page":"1","article-title":"LSKNet: A foundation lightweight backbone for remote sensing","author":"Li","year":"2024","journal-title":"Int. J. Comput. Vis."},{"issue":"12","key":"10.1016\/j.imavis.2026.106047_b14","doi-asserted-by":"crossref","first-page":"3226","DOI":"10.1007\/s11263-023-01840-8","article-title":"STP-SOM: Scale-transfer learning for pansharpening via estimating spectral observation model","volume":"131","author":"Zhang","year":"2023","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.imavis.2026.106047_b15","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2024.105294","article-title":"MATNet: Multilevel attention-based transformers for change detection in remote sensing images","volume":"151","author":"Zhang","year":"2024","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.imavis.2026.106047_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2024.105150","article-title":"OFACD: An end-to-end change detection network for small UAVs remote sensing with viewpoint differences","volume":"148","author":"Dong","year":"2024","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.imavis.2026.106047_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2025.105651","article-title":"Multi-scale pyramid convolution transformer for remote-sensing object detection","volume":"161","author":"Huagang","year":"2025","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.imavis.2026.106047_b18","series-title":"2018 25th IEEE International Conference on Image Processing","first-page":"4063","article-title":"Fully convolutional siamese networks for change detection","author":"Daudt","year":"2018"},{"key":"10.1016\/j.imavis.2026.106047_b19","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/j.isprsjprs.2020.06.003","article-title":"A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sensing images","volume":"166","author":"Zhang","year":"2020","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.imavis.2026.106047_b20","first-page":"1","article-title":"SNUNet-CD: A densely connected siamese network for change detection of VHR images","volume":"19","author":"Fang","year":"2021","journal-title":"IEEE Geosci. Remote. Sens. Lett."},{"key":"10.1016\/j.imavis.2026.106047_b21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2020.3034752","article-title":"Remote sensing image change detection with transformers","volume":"60","author":"Chen","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.imavis.2026.106047_b22","first-page":"1","article-title":"Building change detection for VHR remote sensing images via local\u2013global pyramid network and cross-task transfer learning strategy","volume":"60","author":"Liu","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.imavis.2026.106047_b23","first-page":"1","article-title":"SwinSUNet: Pure transformer network for remote sensing image change detection","volume":"60","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.imavis.2026.106047_b24","first-page":"1","article-title":"A densely attentive refinement network for change detection based on very-high-resolution bitemporal remote sensing images","volume":"60","author":"Li","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.imavis.2026.106047_b25","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/JSTARS.2022.3224081","article-title":"Axial cross attention meets CNN: Bibranch fusion network for change detection","volume":"16","author":"Song","year":"2022","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens."},{"key":"10.1016\/j.imavis.2026.106047_b26","series-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"10.1016\/j.imavis.2026.106047_b27","series-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024"},{"key":"10.1016\/j.imavis.2026.106047_b28","series-title":"Mamba-unet: Unet-like pure visual mamba for medical image segmentation","author":"Wang","year":"2024"},{"key":"10.1016\/j.imavis.2026.106047_b29","series-title":"Medmamba: Vision mamba for medical image classification","author":"Yue","year":"2024"},{"key":"10.1016\/j.imavis.2026.106047_b30","series-title":"Mambadfuse: A mamba-based dual-phase model for multi-modality image fusion","author":"Li","year":"2024"},{"key":"10.1016\/j.imavis.2026.106047_b31","series-title":"Mambair: A simple baseline for image restoration with state-space model","author":"Guo","year":"2024"},{"key":"10.1016\/j.imavis.2026.106047_b32","series-title":"CDMamba: Remote sensing image change detection with mamba","author":"Zhang","year":"2024"},{"key":"10.1016\/j.imavis.2026.106047_b33","series-title":"Changemamba: Remote sensing change detection with spatio-temporal state space model","author":"Chen","year":"2024"},{"key":"10.1016\/j.imavis.2026.106047_b34","series-title":"Mixup: Beyond empirical risk minimization","author":"Zhang","year":"2017"},{"key":"10.1016\/j.imavis.2026.106047_b35","doi-asserted-by":"crossref","unstructured":"S. Yun, D. Han, S.J. Oh, S. Chun, J. Choe, Y. Yoo, Cutmix: Regularization strategy to train strong classifiers with localizable features, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 6023\u20136032.","DOI":"10.1109\/ICCV.2019.00612"},{"key":"10.1016\/j.imavis.2026.106047_b36","series-title":"Vision superalignment: Weak-to-strong generalization for vision foundation models","author":"Guo","year":"2024"},{"key":"10.1016\/j.imavis.2026.106047_b37","article-title":"Frequency domain feature interaction combined with multi-scale attention for remote sensing change detection","author":"Xie","year":"2025","journal-title":"IEEE Sensors J."},{"key":"10.1016\/j.imavis.2026.106047_b38","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.imavis.2026.106047_b39","doi-asserted-by":"crossref","unstructured":"W. Wang, E. Xie, X. Li, D.-P. Fan, K. Song, D. Liang, T. Lu, P. Luo, L. Shao, Pyramid vision transformer: A versatile backbone for dense prediction without convolutions, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 568\u2013578.","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"10.1016\/j.imavis.2026.106047_b40","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10.1016\/j.imavis.2026.106047_b41","series-title":"CDXFormer: Boosting remote sensing change detection with extended long short-term memory","author":"Wu","year":"2024"},{"key":"10.1016\/j.imavis.2026.106047_b42","series-title":"IGARSS 2024-2024 IEEE International Geoscience and Remote Sensing Symposium","first-page":"8581","article-title":"Time travelling pixels: Bitemporal features integration with foundation model for remote sensing image change detection","author":"Chen","year":"2024"},{"key":"10.1016\/j.imavis.2026.106047_b43","doi-asserted-by":"crossref","unstructured":"Z. Zheng, S. Tian, A. Ma, L. Zhang, Y. Zhong, Scalable multi-temporal remote sensing change data generation via simulating stochastic change process, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 21818\u201321827.","DOI":"10.1109\/ICCV51070.2023.01994"},{"key":"10.1016\/j.imavis.2026.106047_b44","series-title":"A survey on vision mamba: Models, applications and challenges","author":"Xu","year":"2024"},{"key":"10.1016\/j.imavis.2026.106047_b45","series-title":"VMamba: Visual state space model","author":"Liu","year":"2024"},{"key":"10.1016\/j.imavis.2026.106047_b46","first-page":"1","article-title":"Rsmamba: Remote sensing image classification with state space model","volume":"21","author":"Chen","year":"2024","journal-title":"IEEE Geosci. Remote. Sens. Lett."},{"key":"10.1016\/j.imavis.2026.106047_b47","article-title":"Change detection mamba with boundary-specific supervision","author":"Wang","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.imavis.2026.106047_b48","series-title":"Weak-to-strong generalization: Eliciting strong capabilities with weak supervision","author":"Burns","year":"2023"},{"key":"10.1016\/j.imavis.2026.106047_b49","series-title":"Improving weak-to-strong generalization with reliability-aware alignment","author":"Guo","year":"2024"},{"key":"10.1016\/j.imavis.2026.106047_b50","series-title":"Co-supervised learning: Improving weak-to-strong generalization with hierarchical mixture of experts","author":"Liu","year":"2024"},{"key":"10.1016\/j.imavis.2026.106047_b51","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"10705","article-title":"Negvsr: Augmenting negatives for generalized noise modeling in real-world video super-resolution","volume":"vol. 38","author":"Song","year":"2024"},{"issue":"10","key":"10.1016\/j.imavis.2026.106047_b52","doi-asserted-by":"crossref","first-page":"1662","DOI":"10.3390\/rs12101662","article-title":"A spatial-temporal attention-based method and a new dataset for remote sensing image change detection","volume":"12","author":"Chen","year":"2020","journal-title":"Remote. Sens."},{"key":"10.1016\/j.imavis.2026.106047_b53","first-page":"1","article-title":"A deeply supervised attention metric-based network and an open aerial image dataset for remote sensing change detection","volume":"60","author":"Shi","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"1","key":"10.1016\/j.imavis.2026.106047_b54","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1109\/TGRS.2018.2858817","article-title":"Fully convolutional networks for multisource building extraction from an open aerial and satellite imagery data set","volume":"57","author":"Ji","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."}],"container-title":["Image and Vision Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S026288562600154X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S026288562600154X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T06:27:30Z","timestamp":1784528850000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S026288562600154X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":54,"alternative-id":["S026288562600154X"],"URL":"https:\/\/doi.org\/10.1016\/j.imavis.2026.106047","relation":{},"ISSN":["0262-8856"],"issn-type":[{"value":"0262-8856","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Rethinking remote sensing change detection with state space models and self-supervised learning","name":"articletitle","label":"Article Title"},{"value":"Image and Vision Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.imavis.2026.106047","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":"106047"}}