{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T16:37:11Z","timestamp":1756312631322,"version":"3.40.3"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030695347"},{"type":"electronic","value":"9783030695354"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-69535-4_17","type":"book-chapter","created":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T15:13:11Z","timestamp":1614179591000},"page":"273-288","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Efficient Large-Scale Semantic Visual Localization in 2D Maps"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7324-5883","authenticated-orcid":false,"given":"Tomas","family":"Vojir","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4278-198X","authenticated-orcid":false,"given":"Ignas","family":"Budvytis","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8999-2151","authenticated-orcid":false,"given":"Roberto","family":"Cipolla","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,2,25]]},"reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Torii, A., Arandjelovi\u0107, R., Sivic, J., Okutomi, M., Pajdla, T.: 24\/7 place recognition by view synthesis. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298790"},{"key":"17_CR2","unstructured":"Budvytis, I., Sauer, P., Cipolla, R.: Semantic localisation via globally unique instance segmentation. In: BMVC (2018)"},{"key":"17_CR3","unstructured":"Abonce, O.S., Zhou, M., Calway, A.: You are here: geolocation by embedding maps and images. arXiv:1911.08797 (2019)"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Arandjelovi\u0107, R., Gronat, P., Torii, A., Pajdla, T., Sivic, J.: NetVLAD: CNN architecture for weakly supervised place recognition. IEEE TPAMI 40, 1437\u20131451 (2018)","DOI":"10.1109\/TPAMI.2017.2711011"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J., Pollefeys, M., Geiger, A., Sattler, T.: Semantic visual localization. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00721"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Sattler, T., Havlena, M., Radenovic, F., Schindler, K., Pollefeys, M.: Hyperpoints and fine vocabularies for large-scale location recognition. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.243"},{"key":"17_CR7","unstructured":"Budvytis, I., Teichmann, M., Vojir, T., Cipolla, R.: Large scale joint semantic re-localisation and scene understanding via globally unique instance coordinate regression. In: BMVC (2019)"},{"key":"17_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1007\/978-3-319-16817-3_13","volume-title":"Computer Vision \u2013 ACCV 2014","author":"R Arandjelovi\u0107","year":"2015","unstructured":"Arandjelovi\u0107, R., Zisserman, A.: DisLocation: scalable descriptor distinctiveness for location recognition. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9006, pp. 188\u2013204. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-16817-3_13"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Stenborg, E., Toft, C., Hammarstrand, L.: Long-term visual localization using semantically segmented images. In: ICRA (2018)","DOI":"10.1109\/ICRA.2018.8463150"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Kendall, A., Cipolla, R.: Geometric loss functions for camera pose regression with deep learning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.694"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Brachmann, E., Rother, C.: Learning less is more - 6D camera localization via 3D surface regression. In: CVPR (2017)","DOI":"10.1109\/CVPR.2018.00489"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Object retrieval with large vocabularies and fast spatial matching. In: CVPR (2007)","DOI":"10.1109\/CVPR.2007.383172"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Perronnin, F., Liu, Y., S\u00e1nchez, J., Poirier, H.: Large-scale image retrieval with compressed Fisher vectors. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540009"},{"key":"17_CR14","unstructured":"Coast, S.: OpenStreetMap (2004)"},{"key":"17_CR15","unstructured":"Massa, F., Girshick, R.: MaskRCNN-benchmark: fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch (2018). https:\/\/github.com\/facebookresearch\/maskrcnn-benchmark"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Zhu, Y., et al.: Improving semantic segmentation via video propagation and label relaxation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00906"},{"key":"17_CR17","unstructured":"Yakubovskiy, P.: Segmentation models (2019). https:\/\/github.com\/qubvel\/segmentation_models"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Panphattarasap, P., Calway, A.: Automated map reading: image based localisation in 2-D maps using binary semantic descriptors. In: IROS (2018)","DOI":"10.1109\/IROS.2018.8594253"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Yan, F., Vysotska, O., Stachniss, C.: Global localization on OpenStreetMap using 4-bit semantic descriptors. In: ECMR (2019)","DOI":"10.1109\/ECMR.2019.8870918"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Chen, D.M., et al.: City-scale landmark identification on mobile devices. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995610"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Schindler, G., Brown, M., Szeliski, R.: City-scale location recognition. In: CVPR (2007)","DOI":"10.1109\/CVPR.2007.383150"},{"key":"17_CR22","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60, 91\u2013110 (2004). https:\/\/doi.org\/10.1023\/B:VISI.0000029664.99615.94","journal-title":"IJCV"},{"key":"17_CR23","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1109\/TPAMI.2010.57","volume":"33","author":"H Jegou","year":"2011","unstructured":"Jegou, H., Douze, M., Schmid, C.: Product quantization for nearest neighbor search. IEEE TPAMI 33, 117\u2013128 (2011)","journal-title":"IEEE TPAMI"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Sattler, T., Leibe, B., Kobbelt, L.: Fast image-based localization using direct 2D-to-3D matching. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126302"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Sattler, T., et al.: Are large-scale 3D models really necessary for accurate visual localization? In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.654"},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"Agarwal, S., et al.: Building Rome in a day. In: ICCV (2009)","DOI":"10.1109\/ICCV.2009.5459148"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Crandall, D., Owens, A., Snavely, N., Huttenlocher, D.: Discrete-continuous optimization for large-scale structure from motion. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995626"},{"key":"17_CR28","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J.L., Radenovi\u0107, F., Chum, O., Frahm, J.: From single image query to detailed 3D reconstruction. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299148"},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J.L., Frahm, J.: Structure-from-motion revisited. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"17_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1007\/978-3-319-10590-1_9","volume-title":"Computer Vision \u2013 ECCV 2014","author":"L Kneip","year":"2014","unstructured":"Kneip, L., Li, H., Seo, Y.: UPnP: an optimal O(n) solution to the absolute pose problem with universal applicability. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 127\u2013142. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_9"},{"key":"17_CR31","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/s11263-008-0152-6","volume":"81","author":"V Lepetit","year":"2009","unstructured":"Lepetit, V., Moreno-Noguer, F., Fua, P.: EPnP: an accurate O(N) solution to the PnP problem. IJCV 81, 155 (2009)","journal-title":"IJCV"},{"key":"17_CR32","doi-asserted-by":"crossref","unstructured":"Camposeco, F., Cohen, A., Pollefeys, M., Sattler, T.: Hybrid scene compression for visual localization. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00784"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Sattler, T., Havlena, M., Schindler, K., Pollefeys, M.: Large-scale location recognition and the geometric burstiness problem. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.175"},{"key":"17_CR34","doi-asserted-by":"crossref","unstructured":"Kendall, A., Grimes, M., Cipolla, R.: PoseNet: a convolutional network for real-time 6-DOF camera relocalization. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.336"},{"key":"17_CR35","doi-asserted-by":"crossref","unstructured":"Walch, F., Hazirbas, C., Leal-Taix\u00e9, L., Sattler, T., Hilsenbeck, S., Cremers, D.: Image-based localization using LSTMs for structured feature correlation. In: ICCV (2016)","DOI":"10.1109\/ICCV.2017.75"},{"key":"17_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/978-3-319-46484-8_3","volume-title":"Computer Vision \u2013 ECCV 2016","author":"T Weyand","year":"2016","unstructured":"Weyand, T., Kostrikov, I., Philbin, J.: PlaNet - photo geolocation with convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 37\u201355. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_3"},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"Sattler, T., Zhou, Q., Pollefeys, M., Leal-Taix\u00e9, L.: Understanding the limitations of CNN-based absolute camera pose regression. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00342"},{"key":"17_CR38","doi-asserted-by":"crossref","unstructured":"Brachmann, E., et al.: DSAC - differentiable RANSAC for camera localization. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.267"},{"key":"17_CR39","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2015.2453975","volume":"38","author":"MA Brubaker","year":"2016","unstructured":"Brubaker, M.A., Geiger, A., Urtasun, R.: Map-based probabilistic visual self-localization. IEEE TPAMI 38, 652\u2013665 (2016)","journal-title":"IEEE TPAMI"},{"key":"17_CR40","unstructured":"Nister, D., Naroditsky, O., Bergen, J.: Visual odometry. In: CVPR (2004)"},{"key":"17_CR41","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)"},{"key":"17_CR42","unstructured":"Hermans, A., Beyer, L., Leibe, B.. In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017)"},{"key":"17_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1007\/978-3-319-46448-0_30","volume-title":"Computer Vision \u2013 ECCV 2016","author":"NN Vo","year":"2016","unstructured":"Vo, N.N., Hays, J.: Localizing and orienting street views using overhead imagery. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 494\u2013509. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_30"},{"key":"17_CR44","doi-asserted-by":"publisher","first-page":"2993","DOI":"10.1016\/j.patcog.2015.04.005","volume":"48","author":"S Ding","year":"2015","unstructured":"Ding, S., Lin, L., Wang, G., Chao, H.: Deep feature learning with relative distance comparison for person re-identification. Pattern Recogn. 48, 2993\u20133003 (2015)","journal-title":"Pattern Recogn."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69535-4_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T15:41:48Z","timestamp":1614181308000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69535-4_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030695347","9783030695354"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69535-4_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"25 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"768","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":"254","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":"0","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":"33% - 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":"3","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":"3","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually.","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)"}}]}}