{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T06:47:47Z","timestamp":1743058067125,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781124"},{"type":"electronic","value":"9783031781131"}],"license":[{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-78113-1_25","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T17:02:39Z","timestamp":1733245359000},"page":"377-392","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Visual Place Recognition with\u00a0Semantic-Guided Attention"],"prefix":"10.1007","author":[{"given":"Wenwen","family":"Ming","sequence":"first","affiliation":[]},{"given":"Xucan","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Zhe","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Ruihao","family":"Li","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Yi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"key":"25_CR1","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1016\/j.neucom.2022.09.127","volume":"513","author":"A Ali-bey","year":"2022","unstructured":"Ali-bey, A., Chaib-draa, B., Gigu\u00e8re, P.: GSV-Cities: toward appropriate supervised visual place recognition. Neurocomputing 513, 194\u2013203 (2022)","journal-title":"Neurocomputing"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Ali-Bey, A., Chaib-Draa, B., Giguere, P.: MixVPR: feature mixing for visual place recognition. In: 2023 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 2997\u20133006. IEEE, Waikoloa, HI, USA (2023)","DOI":"10.1109\/WACV56688.2023.00301"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Arandjelovic, A.T.R., Okutomi, J.S.M., Pajdla, T.: 24\/7 place recognition by view synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1808\u20131817 (2015)","DOI":"10.1109\/CVPR.2015.7298790"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., Sivic, J.: NetVLAD: CNN architecture for weakly supervised place recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5297\u20135307 (2016)","DOI":"10.1109\/CVPR.2016.572"},{"issue":"3","key":"25_CR5","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1016\/j.cviu.2007.09.014","volume":"110","author":"H Bay","year":"2008","unstructured":"Bay, H., Ess, A., Tuytelaars, T., Van Gool, L.: Speeded-up robust features (SURF). Comput. Vis. Image Underst. 110(3), 346\u2013359 (2008)","journal-title":"Comput. Vis. Image Underst."},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Berton, G., Masone, C., Caputo, B.: Rethinking Visual Geo-localization for Large-Scale Applications. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4868\u20134878. IEEE, New Orleans, LA, USA (2022)","DOI":"10.1109\/CVPR52688.2022.00483"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Berton, G.M., Paolicelli, V., Masone, C., Caputo, B.: Adaptive-attentive geolocalization from few queries: a hybrid approach. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2918\u20132927 (2021)","DOI":"10.3389\/fcomp.2022.841817"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Cai, Y., Zhao, J., Cui, J., Zhang, F., Feng, T., Ye, C.: Patch-NetVLAD+: learned patch descriptor and weighted matching strategy for place recognition. In: 2022 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI), pp.\u00a01\u20138 (2022)","DOI":"10.1109\/MFI55806.2022.9913860"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 1280\u20131289. IEEE, New Orleans, LA, USA (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"25_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109645","volume":"141","author":"SM Choi","year":"2023","unstructured":"Choi, S.M., Lee, S.I., Lee, J.Y., Kweon, I.S.: Semantic-guided de-attention with sharpened triplet marginal loss for visual place recognition. Pattern Recogn. 141, 109645 (2023)","journal-title":"Pattern Recogn."},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3213\u20133223. IEEE, Las Vegas, NV, USA (2016)","DOI":"10.1109\/CVPR.2016.350"},{"issue":"6","key":"25_CR12","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1177\/0278364908090961","volume":"27","author":"M Cummins","year":"2008","unstructured":"Cummins, M., Newman, P.: FAB-MAP: probabilistic localization and mapping in the space of appearance. Int. J. Robot. Res. 27(6), 647\u2013665 (2008)","journal-title":"Int. J. Robot. Res."},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905). vol.\u00a01, pp. 886\u2013893 vol. 1 (2005)","DOI":"10.1109\/CVPR.2005.177"},{"key":"25_CR14","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2021)"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. In: Readings in Computer Vision, pp. 726\u2013740. Morgan Kaufmann, San Francisco (CA) (1987)","DOI":"10.1016\/B978-0-08-051581-6.50070-2"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Garg, S., Suenderhauf, N., Milford, M.: LoST? Appearance-invariant place recognition for opposite viewpoints using visual semantics. In: Robotics: Science and Systems XIV. Robotics: Science and Systems Foundation (2018)","DOI":"10.15607\/RSS.2018.XIV.022"},{"issue":"6","key":"25_CR17","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1177\/0278364919839761","volume":"41","author":"S Garg","year":"2022","unstructured":"Garg, S., Suenderhauf, N., Milford, M.: Semantic\u2013geometric visual place recognition: a new perspective for reconciling opposing views. Int. J. Robot. Res. 41(6), 573\u2013598 (2022)","journal-title":"Int. J. Robot. Res."},{"key":"25_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1007\/978-3-030-58548-8_22","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Ge","year":"2020","unstructured":"Ge, Y., Wang, H., Zhu, F., Zhao, R., Li, H.: Self-supervising fine-grained region similarities for large-scale image localization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 369\u2013386. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_22"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Hausler, S., Garg, S., Xu, M., Milford, M., Fischer, T.: Patch-NetVLAD: multi-scale fusion of locally-global descriptors for place recognition. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14136\u201314147. IEEE, Nashville, TN, USA (2021)","DOI":"10.1109\/CVPR46437.2021.01392"},{"key":"25_CR20","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":"25_CR21","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Douze, M., Schmid, C., P\u00e9rez, P.: Aggregating local descriptors into a compact image representation. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 3304\u20133311 (2010)","DOI":"10.1109\/CVPR.2010.5540039"},{"issue":"4","key":"25_CR22","doi-asserted-by":"publisher","first-page":"6969","DOI":"10.1109\/LRA.2021.3096751","volume":"6","author":"NV Keetha","year":"2021","unstructured":"Keetha, N.V., Milford, M., Garg, S.: A hierarchical dual model of environment- and place-specific utility for visual place recognition. IEEE Robot. Autom. Lett. 6(4), 6969\u20136976 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Kim, H.J., Dunn, E., Frahm, J.M.: Learned contextual feature reweighting for image geo-localization. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3251\u20133260. IEEE, Honolulu, HI (2017)","DOI":"10.1109\/CVPR.2017.346"},{"key":"25_CR24","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: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 31\u201341. IEEE, Seoul, Korea (South) (2019)","DOI":"10.1109\/ICCV.2019.00012"},{"issue":"2","key":"25_CR25","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. Int. J. Comput. Vision 60(2), 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vision"},{"issue":"1","key":"25_CR26","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, 1000 km: the oxford RobotCar dataset. Int. J. Robot. Res. 36(1), 3\u201315 (2017)","journal-title":"Int. J. Robot. Res."},{"key":"25_CR27","doi-asserted-by":"crossref","unstructured":"Naseer, T., Oliveira, G.L., Brox, T., Burgard, W.: Semantics-aware visual localization under challenging perceptual conditions. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 2614\u20132620. IEEE, Singapore (2017)","DOI":"10.1109\/ICRA.2017.7989305"},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Oliva, A., Torralba, A.: Building the gist of a scene: the role of global image features in recognition. In: Martinez-Conde, S., Macknik, S.L., Martinez, L.M., Alonso, J.M., Tse, P.U. (eds.) Progress in Brain Research, Visual Perception, vol.\u00a0155, pp. 23\u201336. Elsevier (2006)","DOI":"10.1016\/S0079-6123(06)55002-2"},{"key":"25_CR29","doi-asserted-by":"publisher","unstructured":"Paolicelli, V., Tavera, A., Masone, C., Berton, G., Caputo, B.: Learning semantics for\u00a0visual place recognition through multi-scale attention. In: Sclaroff, S., Distante, C., Leo, M., Farinella, G.M., Tombari, F. (eds.) Image Analysis and Processing \u2013 ICIAP 2022, pp. 454\u2013466. Springer International Publishing, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-06430-2_38","DOI":"10.1007\/978-3-031-06430-2_38"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Peng, G., Yue, Y., Zhang, J., Wu, Z., Tang, X., Wang, D.: Semantic reinforced attention learning for visual place recognition. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 13415\u201313422 (2021)","DOI":"10.1109\/ICRA48506.2021.9561812"},{"key":"25_CR31","doi-asserted-by":"crossref","unstructured":"Revaud, J., Almazan, J., Rezende, R., Souza, C.D.: Learning with average precision: training image retrieval with a listwise loss. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5106\u20135115. IEEE, Seoul, Korea (South) (2019)","DOI":"10.1109\/ICCV.2019.00521"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Shen, Y., Zhou, S., Fu, J., Wang, R., Chen, S., Zheng, N.: StructVPR: distill structural knowledge with weighting samples for visual place recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1217\u201311226 (2023)","DOI":"10.1109\/CVPR52729.2023.01079"},{"key":"25_CR33","doi-asserted-by":"crossref","unstructured":"Sivic, Zisserman: Video Google: a text retrieval approach to object matching in videos. In: Proceedings Ninth IEEE International Conference on Computer Vision, vol. 2, pp. 1470\u20131477 (2003)","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"25_CR34","doi-asserted-by":"crossref","unstructured":"Torii, A., Sivic, J., Pajdla, T., Okutomi, M.: Visual place recognition with repetitive structures. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition, pp. 883\u2013890. IEEE, Portland, OR, USA (2013)","DOI":"10.1109\/CVPR.2013.119"},{"key":"25_CR35","doi-asserted-by":"crossref","unstructured":"Wang, R., Shen, Y., Zuo, W., Zhou, S., Zheng, N.: TransVPR: transformer-based place recognition with multi-level attention aggregation. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13638\u201313647. IEEE, New Orleans, LA, USA (2022)","DOI":"10.1109\/CVPR52688.2022.01328"},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Wang, X., Han, X., Huang, W., Dong, D., Scott, M.R.: Multi-similarity loss with general pair weighting for deep metric learning. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5017\u20135025. IEEE, Long Beach, CA, USA (2019)","DOI":"10.1109\/CVPR.2019.00516"},{"key":"25_CR37","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: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2623\u20132632. IEEE, Seattle, WA, USA (2020)","DOI":"10.1109\/CVPR42600.2020.00270"},{"key":"25_CR38","doi-asserted-by":"crossref","unstructured":"Xue, F., Budvytis, I., Cipolla, R.: SFD2: semantic-guided feature detection and description. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5206\u20135216. IEEE, Vancouver, BC, Canada (2023)","DOI":"10.1109\/CVPR52729.2023.00504"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78113-1_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T17:07:00Z","timestamp":1733245620000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78113-1_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"ISBN":["9783031781124","9783031781131"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78113-1_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,4]]},"assertion":[{"value":"4 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}