{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T17:26:44Z","timestamp":1772731604413,"version":"3.50.1"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031442094","type":"print"},{"value":"9783031442100","type":"electronic"}],"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-44210-0_35","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T08:02:34Z","timestamp":1695283354000},"page":"434-445","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["MCAPR: Multi-modality Cross Attention for\u00a0Camera Absolute Pose Regression"],"prefix":"10.1007","author":[{"given":"Qiqi","family":"Shu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoliang","family":"luan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Poslad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marie-Luce","family":"Bourguet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"key":"35_CR1","doi-asserted-by":"crossref","unstructured":"Balntas, V., Li, S., Prisacariu, V.: Relocnet: continuous metric learning relocalisation using neural nets. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 751\u2013767 (2018)","DOI":"10.1007\/978-3-030-01264-9_46"},{"key":"35_CR2","doi-asserted-by":"crossref","unstructured":"Brachmann, E., et al.: Dsac-differentiable ransac for camera localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6684\u20136692 (2017)","DOI":"10.1109\/CVPR.2017.267"},{"key":"35_CR3","doi-asserted-by":"crossref","unstructured":"Brachmann, E., Rother, C.: 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 (2018)","DOI":"10.1109\/CVPR.2018.00489"},{"key":"35_CR4","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"35_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"35_CR6","doi-asserted-by":"crossref","unstructured":"Glocker, B., Izadi, S., Shotton, J., Criminisi, A.: Real-time rgb-d camera relocalization. In: 2013 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), pp. 173\u2013179. IEEE (2013)","DOI":"10.1109\/ISMAR.2013.6671777"},{"key":"35_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"35_CR8","doi-asserted-by":"crossref","unstructured":"Kendall, A., Cipolla, R.: 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 (2017)","DOI":"10.1109\/CVPR.2017.694"},{"key":"35_CR9","doi-asserted-by":"crossref","unstructured":"Kendall, A., Grimes, M., Cipolla, R.: Posenet: A convolutional network for real-time 6-dof camera relocalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2938\u20132946 (2015)","DOI":"10.1109\/ICCV.2015.336"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Laskar, Z., Melekhov, I., Kalia, S., Kannala, J.: Camera relocalization by computing pairwise relative poses using convolutional neural network. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 929\u2013938 (2017)","DOI":"10.1109\/ICCVW.2017.113"},{"key":"35_CR11","doi-asserted-by":"crossref","unstructured":"Melekhov, I., Ylioinas, J., Kannala, J., Rahtu, E.: Image-based localization using hourglass networks. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 879\u2013886 (2017)","DOI":"10.1109\/ICCVW.2017.107"},{"key":"35_CR12","doi-asserted-by":"crossref","unstructured":"Naseer, T., Burgard, W.: Deep regression for monocular camera-based 6-dof global localization in outdoor environments. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1525\u20131530. IEEE (2017)","DOI":"10.1109\/IROS.2017.8205957"},{"key":"35_CR13","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32, pp. 8024\u20138035. Curran Associates, Inc. (2019). http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf"},{"key":"35_CR14","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652\u2013660 (2017)"},{"key":"35_CR15","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., Cadena, C., Siegwart, R., Dymczyk, M.: From coarse to fine: robust hierarchical localization at large scale. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12716\u201312725 (2019)","DOI":"10.1109\/CVPR.2019.01300"},{"key":"35_CR16","doi-asserted-by":"crossref","unstructured":"Shavit, Y., Ferens, R.: Do we really need scene-specific pose encoders? In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 3186\u20133192. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9412225"},{"key":"35_CR17","doi-asserted-by":"crossref","unstructured":"Shavit, Y., Ferens, R., Keller, Y.: Learning multi-scene absolute pose regression with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2733\u20132742 (2021)","DOI":"10.1109\/ICCV48922.2021.00273"},{"key":"35_CR18","unstructured":"Su, W., et al.: Vl-bert: pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530 (2019)"},{"key":"35_CR19","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"Walch, F., Hazirbas, C., Leal-Taixe, L., Sattler, T., Hilsenbeck, S., Cremers, D.: Image-based localization using lstms for structured feature correlation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 627\u2013637 (2017)","DOI":"10.1109\/ICCV.2017.75"},{"key":"35_CR21","doi-asserted-by":"crossref","unstructured":"Wang, B., Chen, C., Lu, C.X., Zhao, P., Trigoni, N., Markham, A.: Atloc: attention guided camera localization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 10393\u201310401 (2020)","DOI":"10.1609\/aaai.v34i06.6608"},{"key":"35_CR22","doi-asserted-by":"crossref","unstructured":"Wu, J., Ma, L., Hu, X.: Delving deeper into convolutional neural networks for camera relocalization. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 5644\u20135651. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989663"},{"key":"35_CR23","unstructured":"Xu, M., et al.: A critical analysis of image-based camera pose estimation techniques. arXiv preprint arXiv:2201.05816 (2022)"},{"key":"35_CR24","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44210-0_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T08:08:29Z","timestamp":1695283709000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44210-0_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031442094","9783031442100"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44210-0_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Heraklion","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"947","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"426","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"22","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"45% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"type of other papers accepted  : 9 Abstract","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}