{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:50:43Z","timestamp":1777567843699,"version":"3.51.4"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733895","type":"print"},{"value":"9783031733901","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-73390-1_5","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T16:24:01Z","timestamp":1730305441000},"page":"76-92","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["AddressCLIP: Empowering Vision-Language Models for\u00a0City-Wide Image Address Localization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5607-4626","authenticated-orcid":false,"given":"Shixiong","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6515-1633","authenticated-orcid":false,"given":"Chenghao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9606-947X","authenticated-orcid":false,"given":"Lubin","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7103-6321","authenticated-orcid":false,"given":"Gaofeng","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2089-9733","authenticated-orcid":false,"given":"Shiming","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8662-5818","authenticated-orcid":false,"given":"Jieping","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"5_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"5_CR2","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":"5_CR3","doi-asserted-by":"crossref","unstructured":"Ali-Bey, A., Chaib-Draa, B., Giguere, P.: MixVPR: feature mixing for visual place recognition. In: WACV, pp. 2998\u20133007 (2023)","DOI":"10.1109\/WACV56688.2023.00301"},{"key":"5_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: CVPR, pp. 5297\u20135307 (2016)","DOI":"10.1109\/CVPR.2016.572"},{"key":"5_CR5","unstructured":"Bai, J., et al.: Qwen-VL: a frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)"},{"issue":"3","key":"5_CR6","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":"5_CR7","doi-asserted-by":"crossref","unstructured":"Berton, G., Masone, C., Caputo, B.: Rethinking visual geo-localization for large-scale applications. In: CVPR, pp. 4878\u20134888 (2022)","DOI":"10.1109\/CVPR52688.2022.00483"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Berton, G., Trivigno, G., Caputo, B., Masone, C.: EigenPlaces: training viewpoint robust models for visual place recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11080\u201311090, October 2023","DOI":"10.1109\/ICCV51070.2023.01017"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Berton, G.M., Paolicelli, V., Masone, C., Caputo, B.: Adaptive-attentive geolocalization from few queries: a hybrid approach. In: WACV, pp. 2918\u20132927 (2021)","DOI":"10.3389\/fcomp.2022.841817"},{"key":"5_CR10","unstructured":"Cepeda, V.V., Nayak, G.K., Shah, M.: GeoCLIP: clip-inspired alignment between locations and images for effective worldwide geo-localization. arXiv preprint arXiv:2309.16020 (2023)"},{"key":"5_CR11","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML, pp. 1597\u20131607 (2020)"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Clark, B., Kerrigan, A., Kulkarni, P.P., Cepeda, V.V., Shah, M.: Where we are and what we\u2019re looking at: query based worldwide image geo-localization using hierarchies and scenes. In: CVPR, pp. 23182\u201323190 (2023)","DOI":"10.1109\/CVPR52729.2023.02220"},{"key":"5_CR13","unstructured":"Csurka, G., Dance, C., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: ECCV Workshop, vol.\u00a01, pp.\u00a01\u20132 (2004)"},{"key":"5_CR14","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"5_CR15","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/s11263-023-01891-x","volume":"132","author":"P Gao","year":"2023","unstructured":"Gao, P., et al.: Clip-adapter: better vision-language models with feature adapters. Int. J. Comput. Vis. 132, 581\u2013595 (2023)","journal-title":"Int. J. Comput. Vis."},{"key":"5_CR16","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"},{"issue":"2","key":"5_CR17","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1007\/s11263-017-1016-8","volume":"124","author":"A Gordo","year":"2017","unstructured":"Gordo, A., Almazan, J., Revaud, J., Larlus, D.: End-to-end learning of deep visual representations for image retrieval. Int. J. Comput. Vision 124(2), 237\u2013254 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"5_CR18","unstructured":"Haas, L., Alberti, S., Skreta, M.: Learning generalized zero-shot learners for open-domain image geolocalization. arXiv preprint arXiv:2302.00275 (2023)"},{"key":"5_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: CVPR, pp. 14141\u201314152 (2021)","DOI":"10.1109\/CVPR46437.2021.01392"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Izquierdo, S., Civera, J.: Optimal transport aggregation for visual place recognition. arXiv preprint arXiv:2311.15937 (2023)","DOI":"10.1109\/CVPR52733.2024.01672"},{"key":"5_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1007\/978-3-540-88682-2_24","volume-title":"Computer Vision \u2013 ECCV 2008","author":"H Jegou","year":"2008","unstructured":"Jegou, H., Douze, M., Schmid, C.: Hamming embedding and weak geometric consistency for large scale image search. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5302, pp. 304\u2013317. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-88682-2_24"},{"issue":"9","key":"5_CR24","doi-asserted-by":"publisher","first-page":"1704","DOI":"10.1109\/TPAMI.2011.235","volume":"34","author":"H J\u00e9gou","year":"2011","unstructured":"J\u00e9gou, H., Perronnin, F., Douze, M., S\u00e1nchez, J., P\u00e9rez, P., Schmid, C.: Aggregating local image descriptors into compact codes. IEEE Trans. Pattern Anal. Mach. Intell. 34(9), 1704\u20131716 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"5_CR25","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML, pp. 4904\u20134916 (2021)"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"Jin\u00a0Kim, H., Dunn, E., Frahm, J.M.: Learned contextual feature reweighting for image geo-localization. In: CVPR, pp. 2136\u20132145 (2017)","DOI":"10.1109\/CVPR.2017.346"},{"key":"5_CR27","doi-asserted-by":"publisher","first-page":"1286","DOI":"10.1109\/LRA.2023.3343602","volume":"9","author":"N Keetha","year":"2023","unstructured":"Keetha, N., et al.: AnyLoc: towards universal visual place recognition. IEEE Robot. Autom. Lett. 9, 1286\u20131293 (2023)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Rasheed, H., Maaz, M., Khan, S., Khan, F.S.: Maple: multi-modal prompt learning. In: CVPR, pp. 19113\u201319122 (2023)","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"5_CR29","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML, pp. 12888\u201312900 (2022)"},{"key":"5_CR30","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744 (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Liu, L., Li, H., Dai, Y.: Stochastic attraction-repulsion embedding for large scale image localization. In: ICCV, pp. 2570\u20132579 (2019)","DOI":"10.1109\/ICCV.2019.00266"},{"key":"5_CR32","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, 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vision"},{"key":"5_CR33","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/S0079-6123(06)55002-2","volume":"155","author":"A Oliva","year":"2006","unstructured":"Oliva, A., Torralba, A.: Building the gist of a scene: the role of global image features in recognition. Prog. Brain Res. 155, 23\u201336 (2006)","journal-title":"Prog. Brain Res."},{"key":"5_CR34","unstructured":"Oquab, M., et\u00a0al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"5_CR35","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1007\/978-3-031-19839-7_12","volume-title":"ECCV 2022","author":"S Pramanick","year":"2022","unstructured":"Pramanick, S., Nowara, E.M., Gleason, J., Castillo, C.D., Chellappa, R.: Where in the world is this image? Transformer-based geo-localization in the wild. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13698, pp. 196\u2013215. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19839-7_12"},{"issue":"7","key":"5_CR36","doi-asserted-by":"publisher","first-page":"1655","DOI":"10.1109\/TPAMI.2018.2846566","volume":"41","author":"F Radenovi\u0107","year":"2018","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 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"5_CR37","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Schindler, G., Brown, M., Szeliski, R.: City-scale location recognition. In: CVPR, pp.\u00a01\u20137. IEEE (2007)","DOI":"10.1109\/CVPR.2007.383150"},{"key":"5_CR39","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. ArXiv abs\/2210.08402 (2022). https:\/\/api.semanticscholar.org\/CorpusID:252917726"},{"key":"5_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1007\/978-3-030-01249-6_33","volume-title":"Computer Vision \u2013 ECCV 2018","author":"PH Seo","year":"2018","unstructured":"Seo, P.H., Weyand, T., Sim, J., Han, B.: CPlaNet: enhancing image geolocalization by combinatorial partitioning of maps. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 544\u2013560. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_33"},{"key":"5_CR41","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"5_CR42","unstructured":"Team, G., et\u00a0al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"5_CR43","doi-asserted-by":"crossref","unstructured":"Torii, A., Sivic, J., Pajdla, T., Okutomi, M.: Visual place recognition with repetitive structures. In: CVPR, pp. 883\u2013890 (2013)","DOI":"10.1109\/CVPR.2013.119"},{"key":"5_CR44","doi-asserted-by":"crossref","unstructured":"Trivigno, G., Berton, G., Aragon, J., Caputo, B., Masone, C.: Divide &classify: fine-grained classification for city-wide visual geo-localization. In: ICCV, pp. 11142\u201311152 (2023)","DOI":"10.1109\/ICCV51070.2023.01023"},{"key":"5_CR45","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS, vol. 30 (2017)"},{"key":"5_CR46","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: CVPR, pp. 13648\u201313657 (2022)","DOI":"10.1109\/CVPR52688.2022.01328"},{"key":"5_CR47","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":"5_CR48","doi-asserted-by":"publisher","first-page":"1350","DOI":"10.1007\/s11263-023-01942-3","volume":"132","author":"D Wilson","year":"2023","unstructured":"Wilson, D., Zhang, X., Sultani, W., Wshah, S.: Image and object geo-localization. Int. J. Comput. Vision 132, 1350\u20131392 (2023)","journal-title":"Int. J. Comput. Vision"},{"key":"5_CR49","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: CVPR, pp. 16816\u201316825 (2022)","DOI":"10.1109\/CVPR52688.2022.01631"},{"issue":"9","key":"5_CR50","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Int. J. Comput. Vision 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"5_CR51","doi-asserted-by":"crossref","unstructured":"Zhu, S., Yang, L., Chen, C., Shah, M., Shen, X., Wang, H.: R2former: unified retrieval and reranking transformer for place recognition. In: CVPR, pp. 19370\u201319380 (2023)","DOI":"10.1109\/CVPR52729.2023.01856"},{"key":"5_CR52","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Wang, J., Xie, L., Zheng, L.: Attention-based pyramid aggregation network for visual place recognition. In: ACM MM, pp. 99\u2013107 (2018)","DOI":"10.1145\/3240508.3240525"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73390-1_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T16:29:00Z","timestamp":1730305740000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73390-1_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031733895","9783031733901"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73390-1_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}