{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:19:13Z","timestamp":1781536753642,"version":"3.54.5"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031064296","type":"print"},{"value":"9783031064302","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-06430-2_38","type":"book-chapter","created":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T08:03:16Z","timestamp":1652688196000},"page":"454-466","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Learning Semantics for\u00a0Visual Place Recognition Through Multi-scale Attention"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6109-0471","authenticated-orcid":false,"given":"Valerio","family":"Paolicelli","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9013-4007","authenticated-orcid":false,"given":"Antonio","family":"Tavera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1609-9338","authenticated-orcid":false,"given":"Carlo","family":"Masone","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0128-0396","authenticated-orcid":false,"given":"Gabriele","family":"Berton","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7169-0158","authenticated-orcid":false,"given":"Barbara","family":"Caputo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,5,17]]},"reference":[{"issue":"4","key":"38_CR1","doi-asserted-by":"publisher","first-page":"5526","DOI":"10.1109\/LRA.2020.3009075","volume":"5","author":"E Alberti","year":"2020","unstructured":"Alberti, E., Tavera, A., Masone, C., Caputo, B.: IDDA: a large-scale multi-domain dataset for autonomous driving. IEEE Robot. Autom. Lett. 5(4), 5526\u20135533 (2020). https:\/\/doi.org\/10.1109\/LRA.2020.3009075","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"6","key":"38_CR2","doi-asserted-by":"publisher","first-page":"1437","DOI":"10.1109\/TPAMI.2017.2711011","volume":"40","author":"R Arandjelovi\u0107","year":"2018","unstructured":"Arandjelovi\u0107, R., Gronat, P., Torii, A., Pajdla, T., Sivic, J.: NetVLAD: CNN architecture for weakly supervised place recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1437\u20131451 (2018). https:\/\/doi.org\/10.1109\/TPAMI.2017.2711011","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"38_CR3","doi-asserted-by":"crossref","unstructured":"Berton, G.M., Paolicelli, V., Masone, C., Caputo, B.: Adaptive-attentive geolocalization from few queries: a hybrid approach. In: IEEE Winter Conference on Applications of Computer Vision, pp. 2918\u20132927, January 2021","DOI":"10.3389\/fcomp.2022.841817"},{"key":"38_CR4","unstructured":"Cabon, Y., Murray, N., Humenberger, M.: Virtual KITTI 2 (2020)"},{"key":"38_CR5","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2018","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40, 834\u2013848 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"38_CR6","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"38_CR7","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., Koltun, V.: CARLA: an open urban driving simulator. In: Levine, S., Vanhoucke, V., Goldberg, K. (eds.) Proceedings of the 1st Annual Conference on Robot Learning. Proceedings of Machine Learning Research, vol. 78, pp. 1\u201316. PMLR, 13\u201315 November 2017. http:\/\/proceedings.mlr.press\/v78\/dosovitskiy17a.html"},{"key":"38_CR8","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: IEEE Conference on Computer Vision and Pattern Recognition (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"38_CR9","unstructured":"Geyer, J., et al.: A2D2: audi autonomous driving dataset (2020). https:\/\/www.a2d2.audi"},{"key":"38_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"38_CR11","doi-asserted-by":"publisher","unstructured":"Hu, H., Qiao, Z., Cheng, M., Liu, Z., Wang, H.: DASGIL: domain adaptation for semantic and geometric-aware image-based localization. IEEE Trans. Image Process. 30, 1342\u20131353 (2021). https:\/\/doi.org\/10.1109\/TIP.2020.3043875","DOI":"10.1109\/TIP.2020.3043875"},{"key":"38_CR12","doi-asserted-by":"crossref","unstructured":"Huang, X., et al.: The apolloscape dataset for autonomous driving. In: IEEE Conference on Computer Vision and Pattern Recognition, June 2018","DOI":"10.1109\/CVPRW.2018.00141"},{"key":"38_CR13","doi-asserted-by":"crossref","unstructured":"Jenicek, T., Chum, O.: No fear of the dark: image retrieval under varying illumination conditions. In: International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00979"},{"key":"38_CR14","doi-asserted-by":"publisher","unstructured":"Kim, H.J., Dunn, E., Frahm, J.: Learned contextual feature reweighting for image geo-localization. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3251\u20133260 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.346","DOI":"10.1109\/CVPR.2017.346"},{"key":"38_CR15","doi-asserted-by":"crossref","unstructured":"Larsson, M., Stenborg, E., Toft, C., Hammarstrand, L., Sattler, T., Kahl, F.: Fine-grained segmentation networks: self-supervised segmentation for improved long-term visual localization. In: International Conference on Computer Vision, October 2019","DOI":"10.1109\/ICCV.2019.00012"},{"issue":"1","key":"38_CR16","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1177\/0278364916679498","volume":"36","author":"W Maddern","year":"2017","unstructured":"Maddern, W., Pascoe, G., Linegar, C., Newman, P.: 1 year, 1000km: the Oxford RobotCar dataset. Int. J. Robot. Res. 36(1), 3\u201315 (2017). https:\/\/doi.org\/10.1177\/0278364916679498","journal-title":"Int. J. Robot. Res."},{"key":"38_CR17","doi-asserted-by":"publisher","first-page":"19516","DOI":"10.1109\/ACCESS.2021.3054937","volume":"9","author":"C Masone","year":"2021","unstructured":"Masone, C., Caputo, B.: A survey on deep visual place recognition. IEEE Access 9, 19516\u201319547 (2021). https:\/\/doi.org\/10.1109\/ACCESS.2021.3054937","journal-title":"IEEE Access"},{"key":"38_CR18","doi-asserted-by":"publisher","unstructured":"Mousavian, A., Ko\u0161eck\u00e1, J., Lien, J.-M.: Semantically guided location recognition for outdoors scenes. In: IEEE International Conference on Robotics and Automation, pp. 4882\u20134889 (2015). https:\/\/doi.org\/10.1109\/ICRA.2015.7139877","DOI":"10.1109\/ICRA.2015.7139877"},{"key":"38_CR19","doi-asserted-by":"crossref","unstructured":"Naseer, T., Oliveira, G., Brox, T., Burgard, W.: Semantics-aware visual localization under challenging perceptual conditions. In: IEEE International Conference on Robotics and Automation. IEEE (2017). http:\/\/lmb.informatik.uni-freiburg.de\/Publications\/2017\/OB17","DOI":"10.1109\/ICRA.2017.7989305"},{"key":"38_CR20","doi-asserted-by":"crossref","unstructured":"Pion, N., Humenberger, M., Csurka, G., Cabon, Y., Sattler, T.: Benchmarking image retrieval for visual localization. In: 2020 International Conference on 3D Vision (3DV), pp. 483\u2013494 (2020)","DOI":"10.1109\/3DV50981.2020.00058"},{"issue":"7","key":"38_CR21","doi-asserted-by":"publisher","first-page":"1655","DOI":"10.1109\/TPAMI.2018.2846566","volume":"41","author":"F Radenovi\u0107","year":"2019","unstructured":"Radenovi\u0107, F., Tolias, G., Chum, O.: Fine-tuning CNN image retrieval with no human annotation. IEEE Trans. Pattern Anal. Mach. Intell. 41(7), 1655\u20131668 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"38_CR22","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: Bengio, Y., LeCun, Y. (eds.) The International Conference on Learning Representations (2016). http:\/\/arxiv.org\/abs\/1511.06434"},{"key":"38_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1007\/978-3-319-46475-6_7","volume-title":"Computer Vision \u2013 ECCV 2016","author":"SR Richter","year":"2016","unstructured":"Richter, S.R., Vineet, V., Roth, S., Koltun, V.: Playing for data: ground truth from computer games. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 102\u2013118. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_7"},{"key":"38_CR24","doi-asserted-by":"crossref","unstructured":"Ros, G., Sellart, L., Materzynska, J., Vazquez, D., Lopez, A.M.: The SYNTHIA dataset: a large collection of synthetic images for semantic segmentation of urban scenes. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3234\u20133243, June 2016","DOI":"10.1109\/CVPR.2016.352"},{"key":"38_CR25","unstructured":"Tolias, G., Sicre, R., J\u00e9gou, H.: Particular object retrieval with integral max-pooling of CNN activations. In: The International Conference on Learning Representations, San Juan, Puerto Rico, pp. 1\u201312, May 2016. https:\/\/hal.inria.fr\/hal-01842218"},{"key":"38_CR26","doi-asserted-by":"crossref","unstructured":"Torii, A., Arandjelovi\u0107, R., Sivic, J., Okutomi, M., Pajdla, T.: 24\/7 place recognition by view synthesis. In: IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298790"},{"issue":"11","key":"38_CR27","doi-asserted-by":"publisher","first-page":"2346","DOI":"10.1109\/TPAMI.2015.2409868","volume":"37","author":"A Torii","year":"2015","unstructured":"Torii, A., Sivic, J., Okutomi, M., Pajdla, T.: Visual place recognition with repetitive structures. IEEE Trans. Pattern Anal. Mach. Intell. 37(11), 2346\u20132359 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"38_CR28","doi-asserted-by":"crossref","unstructured":"Warburg, F., Hauberg, S., Lopez-Antequera, M., Gargallo, P., Kuang, Y., Civera, J.: Mapillary street-level sequences: a dataset for lifelong place recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, June 2020","DOI":"10.1109\/CVPR42600.2020.00270"},{"key":"38_CR29","doi-asserted-by":"crossref","unstructured":"Xin, Z., et al.: Localizing discriminative visual landmarks for place recognition. In: IEEE International Conference on Robotics and Automation, pp. 5979\u20135985 (2019)","DOI":"10.1109\/ICRA.2019.8794383"},{"key":"38_CR30","doi-asserted-by":"crossref","unstructured":"Yu, F., et al.: BDD100K: a diverse driving dataset for heterogeneous multitask learning. In: IEEE Conference on Computer Vision and Pattern Recognition, June 2020","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"38_CR31","unstructured":"Zaffar, M., Khaliq, A., Ehsan, S., Milford, M., McDonald-Maier, K.: Levelling the playing field: a comprehensive comparison of visual place recognition approaches under changing condition. In: IEEE International Conference on Robotics and Automation Workshop, pp. 1\u20138 (2019)"},{"key":"38_CR32","doi-asserted-by":"publisher","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6230\u20136239 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.660","DOI":"10.1109\/CVPR.2017.660"},{"key":"38_CR33","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Wang, J., Xie, L., Zheng, L.: Attention-based pyramid aggregation network for visual place recognition. In: ACM International Conference on Multimedia, MM 2018, pp. 99\u2013107. Association for Computing Machinery, New York (2018)","DOI":"10.1145\/3240508.3240525"}],"container-title":["Lecture Notes in Computer Science","Image Analysis and Processing \u2013 ICIAP 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-06430-2_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T13:52:19Z","timestamp":1710337939000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-06430-2_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031064296","9783031064302"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-06430-2_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"17 May 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIAP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image Analysis and Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lecce","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 May 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 May 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iciap2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iciap2021.org\/","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","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"307","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":"168","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":"55% - 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":"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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}