{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T18:49:09Z","timestamp":1732042149442},"reference-count":45,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100003565","name":"Ministry of Land, Infrastructure and Transport","doi-asserted-by":"publisher","award":["21AATD-C163269-01"],"id":[{"id":"10.13039\/501100003565","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002701","name":"Ministry of Education","doi-asserted-by":"publisher","award":["2020R1I1A3074639"],"id":[{"id":"10.13039\/501100002701","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007694","name":"Korea Agency for Infrastructure Technology Advancement","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007694","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003052","name":"Ministry of Trade, Industry and Energy","doi-asserted-by":"publisher","award":["20011875"],"id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1016\/j.neunet.2022.11.014","type":"journal-article","created":{"date-parts":[[2022,11,19]],"date-time":"2022-11-19T07:13:07Z","timestamp":1668841987000},"page":"369-383","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":11,"special_numbering":"C","title":["CT-Loc: Cross-domain visual localization with a channel-wise transformer"],"prefix":"10.1016","volume":"158","author":[{"ORCID":"http:\/\/orcid.org\/0000-0003-2921-3168","authenticated-orcid":false,"given":"Daeho","family":"Kim","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-9799-1773","authenticated-orcid":false,"given":"Jaeil","family":"Kim","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2022.11.014_b1","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.isprsjprs.2019.02.020","article-title":"BIM-PoseNet: Indoor camera localisation using a 3D indoor model and deep learning from synthetic images","volume":"150","author":"Acharya","year":"2019","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"issue":"19","key":"10.1016\/j.neunet.2022.11.014_b2","doi-asserted-by":"crossref","first-page":"5492","DOI":"10.3390\/s20195492","article-title":"A recurrent deep network for estimating the pose of real indoor images from synthetic image sequences","volume":"20","author":"Acharya","year":"2020","journal-title":"Sensors"},{"key":"10.1016\/j.neunet.2022.11.014_b3","series-title":"Modelling uncertainty of single image indoor localisation using a 3D model and deep learning","author":"Acharya","year":"2019"},{"key":"10.1016\/j.neunet.2022.11.014_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.autcon.2022.104152","article-title":"Single-image localisation using 3D models: Combining hierarchical edge maps and semantic segmentation for domain adaptation","volume":"136","author":"Acharya","year":"2022","journal-title":"Automation in Construction"},{"key":"10.1016\/j.neunet.2022.11.014_b5","series-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"10.1016\/j.neunet.2022.11.014_b6","doi-asserted-by":"crossref","unstructured":"Brachmann,\u00a0E., Krull,\u00a0A., Nowozin,\u00a0S., Shotton,\u00a0J., Michel,\u00a0F., Gumhold,\u00a0S., et al. (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.neunet.2022.11.014_b7","doi-asserted-by":"crossref","unstructured":"Brachmann,\u00a0E., & Rother,\u00a0C. (2018). Learning less is more-6d camera localization via 3d surface regression. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4654\u20134662).","DOI":"10.1109\/CVPR.2018.00489"},{"key":"10.1016\/j.neunet.2022.11.014_b8","doi-asserted-by":"crossref","unstructured":"Brahmbhatt,\u00a0S., Gu,\u00a0J., Kim,\u00a0K., Hays,\u00a0J., & Kautz,\u00a0J. (2018). Geometry-aware learning of maps for camera localization. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2616\u20132625).","DOI":"10.1109\/CVPR.2018.00277"},{"key":"10.1016\/j.neunet.2022.11.014_b9","series-title":"Virtual kitti 2","author":"Cabon","year":"2020"},{"key":"10.1016\/j.neunet.2022.11.014_b10","doi-asserted-by":"crossref","unstructured":"Clark,\u00a0R., Wang,\u00a0S., Markham,\u00a0A., Trigoni,\u00a0N., & Wen,\u00a0H. (2017). Vidloc: A deep spatio-temporal model for 6-dof video-clip relocalization. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 6856\u20136864).","DOI":"10.1109\/CVPR.2017.284"},{"key":"10.1016\/j.neunet.2022.11.014_b11","series-title":"2009 IEEE conference on computer vision and pattern recognition","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.neunet.2022.11.014_b12","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"issue":"1635","key":"10.1016\/j.neunet.2022.11.014_b13","article-title":"Neural systems for landmark-based wayfinding in humans","volume":"369","author":"Epstein","year":"2014","journal-title":"Philosophical Transactions of the Royal Society, Series B (Biological Sciences)"},{"key":"10.1016\/j.neunet.2022.11.014_b14","series-title":"2012 IEEE conference on computer vision and pattern recognition","first-page":"3354","article-title":"Are we ready for autonomous driving? the kitti vision benchmark suite","author":"Geiger","year":"2012"},{"key":"10.1016\/j.neunet.2022.11.014_b15","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/j.buildenv.2018.05.026","article-title":"Image retrieval using BIM and features from pretrained VGG network for indoor localization","volume":"140","author":"Ha","year":"2018","journal-title":"Building and Environment"},{"key":"10.1016\/j.neunet.2022.11.014_b16","doi-asserted-by":"crossref","unstructured":"He,\u00a0K., Zhang,\u00a0X., Ren,\u00a0S., & Sun,\u00a0J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.neunet.2022.11.014_b17","doi-asserted-by":"crossref","unstructured":"Huang,\u00a0Z., Xu,\u00a0Y., Shi,\u00a0J., Zhou,\u00a0X., Bao,\u00a0H., & Zhang,\u00a0G. (2019). Prior guided dropout for robust visual localization in dynamic environments. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 2791\u20132800).","DOI":"10.1109\/ICCV.2019.00288"},{"key":"10.1016\/j.neunet.2022.11.014_b18","series-title":"2016 IEEE international conference on robotics and automation (ICRA)","first-page":"4762","article-title":"Modelling uncertainty in deep learning for camera relocalization","author":"Kendall","year":"2016"},{"key":"10.1016\/j.neunet.2022.11.014_b19","doi-asserted-by":"crossref","unstructured":"Kendall,\u00a0A., & Cipolla,\u00a0R. (2017). Geometric loss functions for camera pose regression with deep learning. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5974\u20135983).","DOI":"10.1109\/CVPR.2017.694"},{"key":"10.1016\/j.neunet.2022.11.014_b20","doi-asserted-by":"crossref","unstructured":"Kendall,\u00a0A., Grimes,\u00a0M., & Cipolla,\u00a0R. (2015). Posenet: A convolutional network for real-time 6-dof camera relocalization. In Proceedings of the IEEE international conference on computer vision (pp. 2938\u20132946).","DOI":"10.1109\/ICCV.2015.336"},{"key":"10.1016\/j.neunet.2022.11.014_b21","series-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"10.1016\/j.neunet.2022.11.014_b22","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1016\/j.isprsjprs.2021.10.005","article-title":"Improving synthetic 3D model-aided indoor image localization via domain adaptation","volume":"183","author":"Li","year":"2022","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"10.1016\/j.neunet.2022.11.014_b23","series-title":"European conference on computer vision","first-page":"791","article-title":"Location recognition using prioritized feature matching","author":"Li","year":"2010"},{"key":"10.1016\/j.neunet.2022.11.014_b24","doi-asserted-by":"crossref","unstructured":"Melekhov,\u00a0I., Ylioinas,\u00a0J., Kannala,\u00a0J., & Rahtu,\u00a0E. (2017). Image-based localization using hourglass networks. In Proceedings of the IEEE international conference on computer vision workshops (pp. 879\u2013886).","DOI":"10.1109\/ICCVW.2017.107"},{"key":"10.1016\/j.neunet.2022.11.014_b25","doi-asserted-by":"crossref","unstructured":"Moulon,\u00a0P., Monasse,\u00a0P., & Marlet,\u00a0R. (2013). Global fusion of relative motions for robust, accurate and scalable structure from motion. In Proceedings of the IEEE international conference on computer vision (pp. 3248\u20133255).","DOI":"10.1109\/ICCV.2013.403"},{"key":"10.1016\/j.neunet.2022.11.014_b26","series-title":"2017 IEEE\/RSJ international conference on intelligent robots and systems (IROS)","first-page":"1525","article-title":"Deep regression for monocular camera-based 6-dof global localization in outdoor environments","author":"Naseer","year":"2017"},{"key":"10.1016\/j.neunet.2022.11.014_b27","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.patcog.2017.09.013","article-title":"A survey on visual-based localization: On the benefit of heterogeneous data","volume":"74","author":"Piasco","year":"2018","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2022.11.014_b28","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1016\/j.autcon.2012.12.004","article-title":"Building information modeling (BIM) partnering framework for public construction projects","volume":"31","author":"Porwal","year":"2013","journal-title":"Automation in Construction"},{"issue":"9","key":"10.1016\/j.neunet.2022.11.014_b29","doi-asserted-by":"crossref","first-page":"1744","DOI":"10.1109\/TPAMI.2016.2611662","article-title":"Efficient & effective prioritized matching for large-scale image-based localization","volume":"39","author":"Sattler","year":"2016","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2022.11.014_b30","doi-asserted-by":"crossref","unstructured":"Sattler,\u00a0T., Zhou,\u00a0Q., Pollefeys,\u00a0M., & Leal-Taixe,\u00a0L. (2019). Understanding the limitations of cnn-based absolute camera pose regression. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 3302\u20133312).","DOI":"10.1109\/CVPR.2019.00342"},{"key":"10.1016\/j.neunet.2022.11.014_b31","series-title":"2007 IEEE conference on computer vision and pattern recognition","first-page":"1","article-title":"City-scale location recognition","author":"Schindler","year":"2007"},{"key":"10.1016\/j.neunet.2022.11.014_b32","doi-asserted-by":"crossref","unstructured":"Seifi,\u00a0S., & Tuytelaars,\u00a0T. (2019). How to improve CNN-based 6-DoF camera pose estimation. In Proceedings of the IEEE\/CVF international conference on computer vision workshops.","DOI":"10.1109\/ICCVW.2019.00471"},{"key":"10.1016\/j.neunet.2022.11.014_b33","series-title":"2020 25th international conference on pattern recognition (ICPR)","first-page":"3186","article-title":"Do we really need scene-specific pose encoders?","author":"Shavit","year":"2021"},{"key":"10.1016\/j.neunet.2022.11.014_b34","doi-asserted-by":"crossref","unstructured":"Shavit,\u00a0Y., Ferens,\u00a0R., & Keller,\u00a0Y. (2021). Learning multi-scene absolute pose regression with transformers. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 2733\u20132742).","DOI":"10.1109\/ICCV48922.2021.00273"},{"key":"10.1016\/j.neunet.2022.11.014_b35","series-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"Simonyan","year":"2013"},{"key":"10.1016\/j.neunet.2022.11.014_b36","series-title":"Striving for simplicity: The all convolutional net","author":"Springenberg","year":"2014"},{"key":"10.1016\/j.neunet.2022.11.014_b37","doi-asserted-by":"crossref","unstructured":"Szegedy,\u00a0C., Liu,\u00a0W., Jia,\u00a0Y., Sermanet,\u00a0P., Reed,\u00a0S., Anguelov,\u00a0D., et al. (2015). Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1\u20139).","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"10.1016\/j.neunet.2022.11.014_b38","series-title":"2011 IEEE international conference on computer vision workshops (ICCV workshops)","first-page":"102","article-title":"Visual localization by linear combination of image descriptors","author":"Torii","year":"2011"},{"key":"10.1016\/j.neunet.2022.11.014_b39","doi-asserted-by":"crossref","unstructured":"Torii,\u00a0A., Sivic,\u00a0J., Pajdla,\u00a0T., & Okutomi,\u00a0M. (2013). Visual place recognition with repetitive structures. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 883\u2013890).","DOI":"10.1109\/CVPR.2013.119"},{"key":"10.1016\/j.neunet.2022.11.014_b40","doi-asserted-by":"crossref","unstructured":"Valentin,\u00a0J., Nie\u00dfner,\u00a0M., Shotton,\u00a0J., Fitzgibbon,\u00a0A., Izadi,\u00a0S., & Torr,\u00a0P. H. (2015). Exploiting uncertainty in regression forests for accurate camera relocalization. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4400\u20134408).","DOI":"10.1109\/CVPR.2015.7299069"},{"key":"10.1016\/j.neunet.2022.11.014_b41","series-title":"Advances in neural information processing systems","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.neunet.2022.11.014_b42","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.autcon.2013.10.023","article-title":"Building information modeling (BIM) for existing buildings\u2014Literature review and future needs","volume":"38","author":"Volk","year":"2014","journal-title":"Automation in Construction"},{"key":"10.1016\/j.neunet.2022.11.014_b43","doi-asserted-by":"crossref","unstructured":"Walch,\u00a0F., Hazirbas,\u00a0C., Leal-Taixe,\u00a0L., Sattler,\u00a0T., Hilsenbeck,\u00a0S., & Cremers,\u00a0D. (2017). Image-based localization using lstms for structured feature correlation. In Proceedings of the IEEE international conference on computer vision (pp. 627\u2013637).","DOI":"10.1109\/ICCV.2017.75"},{"key":"10.1016\/j.neunet.2022.11.014_b44","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 AAAI conference on artificial intelligence, Vol. 34 (pp. 10393\u201310401).","DOI":"10.1609\/aaai.v34i06.6608"},{"key":"10.1016\/j.neunet.2022.11.014_b45","series-title":"2017 IEEE international conference on robotics and automation (ICRA)","first-page":"5644","article-title":"Delving deeper into convolutional neural networks for camera relocalization","author":"Wu","year":"2017"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608022004555?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608022004555?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,4,22]],"date-time":"2024-04-22T14:00:02Z","timestamp":1713794402000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608022004555"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":45,"alternative-id":["S0893608022004555"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2022.11.014","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2023,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"CT-Loc: Cross-domain visual localization with a channel-wise transformer","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2022.11.014","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2022 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}]}}