{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T16:15:54Z","timestamp":1788970554781,"version":"build-2803163510"},"reference-count":49,"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":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Vision and Image Understanding"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.cviu.2026.104895","type":"journal-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T16:31:37Z","timestamp":1786033897000},"page":"104895","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["CoAtXNet: A dual-stream hybrid transformer based on relative cross-attention for end-to-end camera localization from RGB-D images"],"prefix":"10.1016","volume":"271","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8486-0771","authenticated-orcid":false,"given":"Hussein","family":"Hasan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2611-6821","authenticated-orcid":false,"given":"Miguel Angel","family":"Garcia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hatem","family":"Rashwan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Domenec","family":"Puig","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.cviu.2026.104895_b1","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.isprsjprs.2022.04.021","article-title":"FeatLoc: Absolute pose regressor for indoor 2D sparse features with simplistic view synthesizing","volume":"189","author":"Bach","year":"2022","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.cviu.2026.104895_b2","series-title":"Dealing with the Quaternion Antipodal Problem for Advecting Fields","author":"Becker","year":"2017"},{"key":"10.1016\/j.cviu.2026.104895_b3","series-title":"2021 IEEE\/CVF International Conference on Computer Vision","first-page":"6198","article-title":"On the limits of pseudo ground truth in visual camera re-localisation","author":"Brachmann","year":"2021"},{"key":"10.1016\/j.cviu.2026.104895_b4","doi-asserted-by":"crossref","unstructured":"Brachmann,\u00a0E., Krull,\u00a0A., Nowozin,\u00a0S., Shotton,\u00a0J., Michel,\u00a0F., Gumhold,\u00a0S., Rother,\u00a0C., 2017. Dsac-differentiable ransac for camera localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 6684\u20136692.","DOI":"10.1109\/CVPR.2017.267"},{"key":"10.1016\/j.cviu.2026.104895_b5","doi-asserted-by":"crossref","unstructured":"Chen,\u00a0S., Bhalgat,\u00a0Y., Li,\u00a0X., Bian,\u00a0J.-W., Li,\u00a0K., Wang,\u00a0Z., Prisacariu,\u00a0V.A., 2024. Neural Refinement for Absolute Pose Regression with Feature Synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 20987\u201320996.","DOI":"10.1109\/CVPR52733.2024.01983"},{"key":"10.1016\/j.cviu.2026.104895_b6","series-title":"CoAtNet: Marrying convolution and attention for all data sizes","author":"Dai","year":"2021"},{"issue":"6","key":"10.1016\/j.cviu.2026.104895_b7","doi-asserted-by":"crossref","first-page":"3166","DOI":"10.1109\/LRA.2023.3261703","article-title":"Eaainet: An element-wise attention network with global affinity information for accurate indoor visual localization","volume":"8","author":"Dai","year":"2023","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.cviu.2026.104895_b8","series-title":"HyperPose: Camera pose localization using attention hypernetworks","author":"Ferens","year":"2023"},{"key":"10.1016\/j.cviu.2026.104895_b9","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.cviu.2019.04.009","article-title":"Performance analysis of single-query 6-dof camera pose estimation in self-driving setups","volume":"186","author":"Fu","year":"2019","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2026.104895_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.123792","article-title":"Alnet: An adaptive channel attention network with local discrepancy perception for accurate indoor visual localization","volume":"250","author":"Gao","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.cviu.2026.104895_b11","series-title":"2013 IEEE International Symposium on Mixed and Augmented Reality","first-page":"173","article-title":"Real-Time RGB-D Camera Relocalization","author":"Glocker","year":"2013"},{"issue":"7","key":"10.1016\/j.cviu.2026.104895_b12","doi-asserted-by":"crossref","first-page":"1811","DOI":"10.1007\/s11263-022-01615-7","article-title":"Investigating the role of image retrieval for visual localization: An exhaustive benchmark","volume":"130","author":"Humenberger","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.cviu.2026.104895_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2023.104229","article-title":"Efficient multimodel method based on transformers and CoAtNet for alzheimer\u2019s diagnosis","volume":"143","author":"Kadri","year":"2023","journal-title":"Digit. Signal Process."},{"issue":"18","key":"10.1016\/j.cviu.2026.104895_b14","doi-asserted-by":"crossref","DOI":"10.3390\/s22186971","article-title":"Absolute camera pose regression using an RGB-d dual-stream network and handcrafted base poses","volume":"22","author":"Kao","year":"2022","journal-title":"Sensors"},{"key":"10.1016\/j.cviu.2026.104895_b15","series-title":"2016 IEEE International Conference on Robotics and Automation","first-page":"4762","article-title":"Modelling uncertainty in deep learning for camera relocalization","author":"Kendall","year":"2016"},{"key":"10.1016\/j.cviu.2026.104895_b16","series-title":"2015 IEEE International Conference on Computer Vision","first-page":"2938","article-title":"PoseNet: A convolutional network for real-time 6-DOF camera relocalization","author":"Kendall","year":"2015"},{"key":"10.1016\/j.cviu.2026.104895_b17","series-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"10.1016\/j.cviu.2026.104895_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.122561","article-title":"Multisensory integration for topological indoor localization of mobile robots in complex symmetrical environments","volume":"241","author":"Lafuente-Arroyo","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.cviu.2026.104895_b19","series-title":"2017 IEEE International Conference on Computer Vision Workshops","first-page":"920","article-title":"Camera relocalization by computing pairwise relative poses using convolutional neural network","author":"Laskar","year":"2017"},{"key":"10.1016\/j.cviu.2026.104895_b20","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/j.isprsjprs.2023.05.034","article-title":"Structure-guided camera localization for indoor environments","volume":"202","author":"Li","year":"2023","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.cviu.2026.104895_b21","series-title":"TransCamP: Graph transformer for 6-dof camera pose estimation","author":"Li","year":"2021"},{"key":"10.1016\/j.cviu.2026.104895_b22","series-title":"2022 IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"1848","article-title":"CoordiNet: uncertainty-aware pose regressor for reliable vehicle localization","author":"Moreau","year":"2021"},{"key":"10.1016\/j.cviu.2026.104895_b23","series-title":"2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"1525","article-title":"Deep regression for monocular camera-based 6-dof global localization in outdoor environments","author":"Naseer","year":"2017"},{"issue":"5","key":"10.1016\/j.cviu.2026.104895_b24","doi-asserted-by":"crossref","DOI":"10.3390\/s23052381","article-title":"Effective techniques for multimodal data fusion: A comparative analysis","volume":"23","author":"Paw\u0142\u00a0owski","year":"2023","journal-title":"Sensors"},{"key":"10.1016\/j.cviu.2026.104895_b25","doi-asserted-by":"crossref","unstructured":"Pietrantoni,\u00a0M., Humenberger,\u00a0M., Sattler,\u00a0T., Csurka,\u00a0G., 2023. SegLoc: Learning Segmentation-Based Representations for Privacy-Preserving Visual Localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 15380\u201315391.","DOI":"10.1109\/CVPR52729.2023.01476"},{"issue":"8","key":"10.1016\/j.cviu.2026.104895_b26","doi-asserted-by":"crossref","first-page":"4633","DOI":"10.1109\/LRA.2023.3286123","article-title":"TransAPR: Absolute camera pose regression with spatial and temporal attention","volume":"8","author":"Qiao","year":"2023","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"6","key":"10.1016\/j.cviu.2026.104895_b27","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0286916","article-title":"Coat-mixer: Self-attention deep learning framework for left ventricular hypertrophy using electrocardiography","volume":"18","author":"Ryu","year":"2023","journal-title":"PLoS One"},{"key":"10.1016\/j.cviu.2026.104895_b28","series-title":"British Machine Vision Conference","article-title":"Improved visual relocalization by discovering anchor points","author":"Saha","year":"2018"},{"issue":"9","key":"10.1016\/j.cviu.2026.104895_b29","doi-asserted-by":"crossref","first-page":"1744","DOI":"10.1109\/TPAMI.2016.2611662","article-title":"Efficient and effective prioritized matching for large-scale image-based localization","volume":"39","author":"Sattler","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2026.104895_b30","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3297","article-title":"Understanding the limitations of CNN-based absolute camera pose regression","author":"Sattler","year":"2019"},{"key":"10.1016\/j.cviu.2026.104895_b31","series-title":"Introduction to camera pose estimation with deep learning","author":"Shavit","year":"2019"},{"key":"10.1016\/j.cviu.2026.104895_b32","series-title":"Paying attention to activation maps in camera pose regression","author":"Shavit","year":"2021"},{"key":"10.1016\/j.cviu.2026.104895_b33","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2024.103982","article-title":"Learning single and multi-scene camera pose regression with transformer encoders","volume":"243","author":"Shavit","year":"2024","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2026.104895_b34","series-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2023","first-page":"434","article-title":"MCAPR: Multi-modality cross attention for camera absolute pose regression","author":"Shu","year":"2023"},{"key":"10.1016\/j.cviu.2026.104895_b35","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109975","article-title":"TransBoNet: Learning camera localization with transformer bottleneck and attention","volume":"146","author":"Song","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.cviu.2026.104895_b36","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1016\/j.isprsjprs.2023.12.006","article-title":"TransCNNLoc: End-to-end pixel-level learning for 2D-to-3D pose estimation in dynamic indoor scenes","volume":"207","author":"Tang","year":"2024","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.cviu.2026.104895_b37","series-title":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"9558","article-title":"Early or late fusion matters: Efficient rgb-d fusion in vision transformers for 3d object recognition","author":"Tziafas","year":"2023"},{"key":"10.1016\/j.cviu.2026.104895_b38","series-title":"2016 Fourth International Conference on 3D Vision (3DV)","first-page":"323","article-title":"Learning to navigate the energy landscape","author":"Valentin","year":"2016"},{"key":"10.1016\/j.cviu.2026.104895_b39","series-title":"Neural Information Processing Systems","first-page":"6000","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.cviu.2026.104895_b40","series-title":"2017 IEEE International Conference on Computer Vision","first-page":"627","article-title":"Image-based localization using LSTMs for structured feature correlation","author":"Walch","year":"2017"},{"key":"10.1016\/j.cviu.2026.104895_b41","doi-asserted-by":"crossref","unstructured":"Wang,\u00a0B., Chen,\u00a0C., Lu,\u00a0C.X., Zhao,\u00a0P., Trigoni,\u00a0N., Markham,\u00a0A., 2020. AtLoc: Attention Guided Camera Localization. In: Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence.","DOI":"10.1609\/aaai.v34i06.6608"},{"key":"10.1016\/j.cviu.2026.104895_b42","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.122755","article-title":"Efrnet-VL: An end-to-end feature refinement network for monocular visual localization in dynamic environments","volume":"243","author":"Wang","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.cviu.2026.104895_b43","series-title":"2017 IEEE International Conference on Robotics and Automation","first-page":"5644","article-title":"Delving deeper into convolutional neural networks for camera relocalization","author":"Wu","year":"2017"},{"issue":"1","key":"10.1016\/j.cviu.2026.104895_b44","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1186\/s42492-018-0008-z","article-title":"Image-based camera localization: an overview","volume":"1","author":"Wu","year":"2018","journal-title":"Vis. Comput. Ind. Biomed. Art"},{"key":"10.1016\/j.cviu.2026.104895_b45","series-title":"2024 IEEE International Conference on Robotics and Automation","first-page":"8529","article-title":"EffLoc: Lightweight vision transformer for efficient 6-DOF camera relocalization","author":"Xiao","year":"2024"},{"key":"10.1016\/j.cviu.2026.104895_b46","series-title":"2023 IEEE\/CVF International Conference on Computer Vision","first-page":"5493","article-title":"OFVL-MS: Once for visual localization across multiple indoor scenes","author":"Xie","year":"2023"},{"key":"10.1016\/j.cviu.2026.104895_b47","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.127125","article-title":"A critical analysis of image-based camera pose estimation techniques","volume":"570","author":"Xu","year":"2024","journal-title":"Neurocomputing"},{"issue":"7","key":"10.1016\/j.cviu.2026.104895_b48","first-page":"6165","article-title":"VMLoc: Variational fusion for learning-based multimodal camera localization","volume":"35","author":"Zhou","year":"2021","journal-title":"Proc. the AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.cviu.2026.104895_b49","series-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"32","article-title":"Fusing the old with the new: Learning relative camera pose with geometry-guided uncertainty","author":"Zhuang","year":"2021"}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226002626?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226002626?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T15:47:13Z","timestamp":1788968833000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1077314226002626"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":49,"alternative-id":["S1077314226002626"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104895","relation":{},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"CoAtXNet: A dual-stream hybrid transformer based on relative cross-attention for end-to-end camera localization from RGB-D images","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104895","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"104895"}}