{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T04:20:12Z","timestamp":1783138812108,"version":"3.54.6"},"reference-count":67,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":["62171321"],"award-info":[{"award-number":["62171321"]}],"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":["62471335"],"award-info":[{"award-number":["62471335"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Visual Communication and Image Representation"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.jvcir.2026.104837","type":"journal-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T15:49:29Z","timestamp":1777996169000},"page":"104837","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Text-prompt multi-scale integration and detail-aware enhancement network for homography estimation"],"prefix":"10.1016","volume":"118","author":[{"given":"Xiaoting","family":"Fan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0815-1987","authenticated-orcid":false,"given":"Ronglu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7095-4606","authenticated-orcid":false,"given":"Long","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvcir.2026.104837_b1","series-title":"Proceedings of Machine Learning Research","article-title":"Unsupervised domain adaptation by backpropagation","author":"Ganin","year":"2015"},{"key":"10.1016\/j.jvcir.2026.104837_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2020.102950","article-title":"A view-free image stitching network based on global homography","volume":"73","author":"Nie","year":"2020","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104837_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2023.103835","article-title":"Uav image stitching by estimating orthograph with RGB cameras","volume":"94","author":"Cai","year":"2023","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104837_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2023.103922","article-title":"Efficient online real-time video stabilization with a novel least squares formulation and parallel ac-ransac","volume":"96","author":"Ke","year":"2023","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104837_b5","doi-asserted-by":"crossref","DOI":"10.1109\/34.888718","article-title":"A flexible new technique for camera calibration","volume":"22","author":"Zhang","year":"2000","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.jvcir.2026.104837_b6","doi-asserted-by":"crossref","unstructured":"N. Gelfand, A. Adams, S.H. Park, K. Pulli, Multi-exposure imaging on mobile devices, in: Proceedings of the 18th ACM International Conference on Multimedia, 2010.","DOI":"10.1145\/1873951.1874088"},{"key":"10.1016\/j.jvcir.2026.104837_b7","doi-asserted-by":"crossref","DOI":"10.1109\/TRO.2015.2463671","article-title":"Orb-slam: A versatile and accurate monocular slam system","volume":"31","author":"Mur-Artal","year":"2015","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.jvcir.2026.104837_b8","article-title":"Coslam: Collaborative visual slam in dynamic environments","volume":"35","author":"Zou","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.jvcir.2026.104837_b9","article-title":"Image alignment and stitching: A tutorial","volume":"2","author":"Szeliski","year":"2006","journal-title":"Found. Trends Comput. Graph. Vis."},{"key":"10.1016\/j.jvcir.2026.104837_b10","doi-asserted-by":"crossref","DOI":"10.1109\/LRA.2018.2809549","article-title":"Unsupervised deep homography: A fast and robust homography estimation model","volume":"3","author":"Nguyen","year":"2018","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.jvcir.2026.104837_b11","doi-asserted-by":"crossref","unstructured":"H. Bay, T. Tuytelaars, L.V. Gool, Surf: Speeded up robust features, in: Proceedings of the European Conference on Computer Vision, 2006.","DOI":"10.1007\/11744023_32"},{"key":"10.1016\/j.jvcir.2026.104837_b12","doi-asserted-by":"crossref","DOI":"10.1007\/s11263-018-1117-z","article-title":"Locality preserving matching","volume":"127","author":"Ma","year":"2019","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.jvcir.2026.104837_b13","doi-asserted-by":"crossref","unstructured":"J. Zhang, et al., Content-aware unsupervised deep homography estimation, in: Proceedings of the European Conference on Computer Vision, 2020.","DOI":"10.1007\/978-3-030-58452-8_38"},{"key":"10.1016\/j.jvcir.2026.104837_b14","unstructured":"D. DeTone, T. Malisiewicz, A. Rabinovich, Deep image homography estimation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016."},{"key":"10.1016\/j.jvcir.2026.104837_b15","doi-asserted-by":"crossref","unstructured":"H. Le, F. Liu, S. Zhang, A. Agarwala, Deep homography estimation for dynamic scenes, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020.","DOI":"10.1109\/CVPR42600.2020.00767"},{"key":"10.1016\/j.jvcir.2026.104837_b16","article-title":"Orsi salient object detection via progressive interaction and saliency-guided enhancement","volume":"23","author":"Zhang","year":"2025","journal-title":"IEEE Geosci. Remote. Sens. Lett."},{"key":"10.1016\/j.jvcir.2026.104837_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.111840","article-title":"Video saliency prediction via single feature enhancement and temporal recurrence","volume":"160","author":"Zhang","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.jvcir.2026.104837_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.109806","article-title":"An efficient perceptual video compression scheme based on deep learning-assisted video saliency and just noticeable distortion","volume":"141","author":"Zhang","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.jvcir.2026.104837_b19","article-title":"Adaptive downsampling and scale enhanced detection head for tiny object detection in remote sensing image","volume":"22","author":"Zhang","year":"2025","journal-title":"IEEE Geosci. Remote. Sens. Lett."},{"issue":"1","key":"10.1016\/j.jvcir.2026.104837_b20","doi-asserted-by":"crossref","DOI":"10.1117\/1.JEI.34.1.013005","article-title":"Asymmetric light-aware progressive decoding network for rgb-thermal salient object detection","volume":"34","author":"Zhang","year":"2025","journal-title":"J. Electron. Imaging"},{"key":"10.1016\/j.jvcir.2026.104837_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128564","article-title":"Spatiotemporal dual-branch feature-guided fusion network for driver attention prediction","volume":"292","author":"Zhang","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.jvcir.2026.104837_b22","doi-asserted-by":"crossref","DOI":"10.1023\/B:VISI.0000011205.11775.fd","article-title":"Lucas-kanade 20 years on: A unifying framework","volume":"56","author":"Baker","year":"2004","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.jvcir.2026.104837_b23","article-title":"Distinctive image features from scale-invariant keypoints","volume":"6","author":"Lowe","year":"2004","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.jvcir.2026.104837_b24","doi-asserted-by":"crossref","unstructured":"E. Rublee, V. Rabaud, K. Konolige, G.R. Bradski, Orb: An efficient alternative to sift or surf, in: Proceedings of the IEEE International Conference on Computer Vision, 2011.","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"10.1016\/j.jvcir.2026.104837_b25","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2016.07.002","article-title":"Accurate and robust feature-based homography estimation using half-sift and feature localization error weighting","volume":"40","author":"Zhao","year":"2016","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104837_b26","doi-asserted-by":"crossref","unstructured":"D. DeTone, T. Malisiewicz, A. Rabinovich, Superpoint: Self-supervised interest point detection and description, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"10.1016\/j.jvcir.2026.104837_b27","doi-asserted-by":"crossref","unstructured":"Y. Tian, X. Yu, B. Fan, F. Wu, H. Heijnen, V. Balntas, Sosnet: Second order similarity regularization for local descriptor learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019.","DOI":"10.1109\/CVPR.2019.01127"},{"key":"10.1016\/j.jvcir.2026.104837_b28","unstructured":"K.M. Yi, E. Trulls, V. Lepetit, P. Fua, Lift: Learned invariant feature transform, in: Proceedings of the European Conference on Computer Vision, 2016."},{"key":"10.1016\/j.jvcir.2026.104837_b29","doi-asserted-by":"crossref","unstructured":"J. Zhang, et al., Learning two-view correspondences and geometry using order-aware network, in: Proceedings of the IEEE International Conference on Computer Vision, 2019.","DOI":"10.1109\/ICCV.2019.00594"},{"key":"10.1016\/j.jvcir.2026.104837_b30","doi-asserted-by":"crossref","unstructured":"P.-E. Sarlin, D. DeTone, T. Malisiewicz, A. Rabinovich, Superglue: Learning feature matching with graph neural networks, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020.","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"10.1016\/j.jvcir.2026.104837_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.patrec.2020.04.005","article-title":"Beblid: Boosted efficient binary local image descriptor","volume":"133","author":"Suarez","year":"2020","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.jvcir.2026.104837_b32","doi-asserted-by":"crossref","DOI":"10.1145\/358669.358692","article-title":"Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography","volume":"24","author":"Fischler","year":"1981","journal-title":"Commun. ACM"},{"key":"10.1016\/j.jvcir.2026.104837_b33","article-title":"Unsupervised global and local homography estimation with motion basis learning","volume":"45","author":"Ye","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.jvcir.2026.104837_b34","doi-asserted-by":"crossref","unstructured":"D. Barath, J. Matas, J. Noskova, Magsac: Marginalizing sample consensus, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019.","DOI":"10.1109\/CVPR.2019.01044"},{"key":"10.1016\/j.jvcir.2026.104837_b35","series-title":"Multiple View Geometry in Computer Vision","author":"Hartley","year":"2004"},{"key":"10.1016\/j.jvcir.2026.104837_b36","series-title":"Proceedings of the IEEE International Conference on Multimedia and Expo","article-title":"Deep homography estimation with feature correlation transformer","author":"Zhou","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104837_b37","series-title":"Sefenet: Robust deep homography estimation via semantic-driven feature enhancement","author":"Shi","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104837_b38","doi-asserted-by":"crossref","unstructured":"L. Nie, C. Lin, K. Liao, S. Liu, Y. Zhao, Edge-preserved image stitching from multi-scale deep homography, in: Proceedings of the IEEE International Conference on Image Processing, 2021.","DOI":"10.1016\/j.neucom.2021.12.032"},{"key":"10.1016\/j.jvcir.2026.104837_b39","article-title":"Learning transferable visual models from natural language supervision","volume":"Vol. 139","author":"Radford","year":"2021"},{"key":"10.1016\/j.jvcir.2026.104837_b40","article-title":"A lightweight network enhanced by attention-guided cross-scale interaction for underwater object detection","author":"Zhang","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.jvcir.2026.104837_b41","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2025.113466","article-title":"Unsupervised image stitching based on generative adversarial networks and feature frequency awareness algorithm","author":"Qin","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.jvcir.2026.104837_b42","doi-asserted-by":"crossref","DOI":"10.1007\/s10462-025-11439-9","article-title":"Reinforcement learning for single-agent to multi-agent systems: From basic theory to industrial application progress, a survey","author":"Zhang","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.jvcir.2026.104837_b43","article-title":"An innovative neural network architecture designed for industrial fault diagnosis with hierarchical adaptive attention mechanism","author":"Wu","year":"2025","journal-title":"Process. Saf. Environ. Prot."},{"key":"10.1016\/j.jvcir.2026.104837_b44","doi-asserted-by":"crossref","unstructured":"S.-C. Huang, L. Shen, M.P. Lungren, S. Yeung, Gloria: A multimodal global-local representation learning framework for label-efficient medical image recognition, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021.","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"10.1016\/j.jvcir.2026.104837_b45","unstructured":"Y. Zhang, H. Jiang, Y. Miura, C.D. Manning, C.P. Langlotz, Contrastive learning of medical visual representations from paired images and text, in: Machine Learning for Healthcare Conference, 2022."},{"key":"10.1016\/j.jvcir.2026.104837_b46","doi-asserted-by":"crossref","unstructured":"R. Zhang, Z. Zeng, Z. Guo, Y. Li, Can language understand depth?, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022.","DOI":"10.1145\/3503161.3549201"},{"key":"10.1016\/j.jvcir.2026.104837_b47","doi-asserted-by":"crossref","unstructured":"Y. Lin, et al., CLIP is also an efficient segmenter: A text-driven approach for weakly supervised semantic segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023.","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"10.1016\/j.jvcir.2026.104837_b48","doi-asserted-by":"crossref","unstructured":"D. Liang, J. Xie, Z. Zou, X. Ye, W. Xu, X. Bai, Crowdclip: Unsupervised crowd counting via vision-language model, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023.","DOI":"10.1109\/CVPR52729.2023.00283"},{"key":"10.1016\/j.jvcir.2026.104837_b49","doi-asserted-by":"crossref","unstructured":"M. Tao, B.-K. Bao, H. Tang, C. Xu, Galip: Generative adversarial clips for text-to-image synthesis, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023.","DOI":"10.1109\/CVPR52729.2023.01366"},{"key":"10.1016\/j.jvcir.2026.104837_b50","doi-asserted-by":"crossref","unstructured":"S.T. Wasim, M. Naseer, S. Khan, F.S. Khan, M. Shah, Vitaclip: Video and text adaptive clip via multimodal prompting, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023.","DOI":"10.1109\/CVPR52729.2023.02206"},{"key":"10.1016\/j.jvcir.2026.104837_b51","series-title":"Image super-resolution with text prompt diffusion","author":"Chen","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104837_b52","article-title":"Advancing real-world stereoscopic image super-resolution via vision-language model","volume":"34","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2026.104837_b53","doi-asserted-by":"crossref","DOI":"10.1109\/JBHI.2025.3619343","article-title":"Amlpf-clip: Adaptive prompting and distilled learning for imbalanced histopathological image classification","author":"Yao","year":"2025","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.jvcir.2026.104837_b54","series-title":"Proceedings of the IEEE International Symposium on Circuits and Systems","article-title":"Clip-dqa: Blindly evaluating dehazed images from global and local perspectives using clip","author":"Zeng","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104837_b55","doi-asserted-by":"crossref","DOI":"10.1109\/LSP.2025.3615082","article-title":"Clip-dqa v2: Exploring clip for dehazed image quality assessment from a fragment-level perspective","author":"Zeng","year":"2025","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.jvcir.2026.104837_b56","doi-asserted-by":"crossref","DOI":"10.1109\/LSP.2024.3420083","article-title":"Vision-language consistency guided multi-modal prompt learning for blind AI generated image quality assessment","volume":"31","author":"Fu","year":"2024","journal-title":"IEEE Signal Process. Lett."},{"issue":"3","key":"10.1016\/j.jvcir.2026.104837_b57","doi-asserted-by":"crossref","DOI":"10.1109\/TBC.2024.3391060","article-title":"Adaptive mixed-scale feature fusion network for blind AI-generated image quality assessment","volume":"70","author":"Zhou","year":"2024","journal-title":"IEEE Trans. Broadcast."},{"key":"10.1016\/j.jvcir.2026.104837_b58","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2026.3657415","article-title":"Dvlta-vqa: Decoupled vision-language modeling with text-guided adaptation for blind video quality assessment","author":"Yu","year":"2026","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.jvcir.2026.104837_b59","series-title":"Alibaba cloud official website","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104837_b60","doi-asserted-by":"crossref","unstructured":"R. Varghese, M. Sambath, Yolov8: A novel object detection algorithm with enhanced performance and robustness, in: International Conference on Advances in Data Engineering and Intelligent Computing Systems, 2024.","DOI":"10.1109\/ADICS58448.2024.10533619"},{"key":"10.1016\/j.jvcir.2026.104837_b61","doi-asserted-by":"crossref","DOI":"10.1016\/j.patrec.2025.04.027","article-title":"Pyramid-structured multi-scale transformer for efficient semi-supervised video object segmentation with adaptive fusion","volume":"194","author":"Zhang","year":"2025","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.jvcir.2026.104837_b62","doi-asserted-by":"crossref","DOI":"10.1016\/j.patrec.2025.04.015","article-title":"Cross-erasure enhanced network for occluded person re-identification","volume":"193","author":"Zhang","year":"2025","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.jvcir.2026.104837_b63","doi-asserted-by":"crossref","unstructured":"N. Ye, C. Wang, H. Fan, S. Liu, Motion basis learning for unsupervised deep homography estimation with subspace projection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021.","DOI":"10.1109\/ICCV48922.2021.01287"},{"key":"10.1016\/j.jvcir.2026.104837_b64","doi-asserted-by":"crossref","unstructured":"M. Hong, Y. Lu, N. Ye, C. Lin, Q. Zhao, S. Liu, Unsupervised homography estimation with coplanarity-aware gan, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022.","DOI":"10.1109\/CVPR52688.2022.01714"},{"key":"10.1016\/j.jvcir.2026.104837_b65","unstructured":"D.P. Kingma, J. Ba, Adam: A method for stochastic optimization, in: Proceedings of the International Conference on Learning Representations, 2015."},{"key":"10.1016\/j.jvcir.2026.104837_b66","doi-asserted-by":"crossref","DOI":"10.1109\/TIM.2024.3374320","article-title":"Abhe: All attention-based homography estimation","volume":"73","author":"Huo","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.jvcir.2026.104837_b67","unstructured":"M. Jaderberg, K. Simonyan, A. Zisserman, K. Kavukcuoglu, Spatial transformer networks, Proceedings of the Annual Conference on Neural Information Processing Systems, 2015."}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S104732032600132X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S104732032600132X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T03:58:00Z","timestamp":1783137480000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S104732032600132X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":67,"alternative-id":["S104732032600132X"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104837","relation":{},"ISSN":["1047-3203"],"issn-type":[{"value":"1047-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Text-prompt multi-scale integration and detail-aware enhancement network for homography estimation","name":"articletitle","label":"Article Title"},{"value":"Journal of Visual Communication and Image Representation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104837","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":"104837"}}