{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T02:46:28Z","timestamp":1790995588457,"version":"4.1.0"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730290","type":"print"},{"value":"9783031730306","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"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\/978-3-031-73030-6_26","type":"book-chapter","created":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T11:58:03Z","timestamp":1732535883000},"page":"466-483","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["GAReT: Cross-View Video Geolocalization with\u00a0Adapters and\u00a0Auto-Regressive Transformers"],"prefix":"10.1007","author":[{"given":"Manu S.","family":"Pillai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mamshad Nayeem","family":"Rizve","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mubarak","family":"Shah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,24]]},"reference":[{"key":"26_CR1","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"issue":"12","key":"26_CR2","doi-asserted-by":"publisher","DOI":"10.1088\/0957-0233\/22\/12\/124003","volume":"22","author":"SA Berrabah","year":"2011","unstructured":"Berrabah, S.A., Sahli, H., Baudoin, Y.: Visual-based simultaneous localization and mapping and global positioning system correction for geo-localization of a mobile robot. Meas. Sci. Technol. 22(12), 124003 (2011)","journal-title":"Meas. Sci. Technol."},{"key":"26_CR3","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: ICML, vol.\u00a02, p.\u00a04 (2021)"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Berton, G., Masone, C., Caputo, B.: Rethinking visual geo-localization for large-scale applications. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4878\u20134888 (2022)","DOI":"10.1109\/CVPR52688.2022.00483"},{"key":"26_CR5","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1007\/s10044-017-0611-1","volume":"20","author":"J Brejcha","year":"2017","unstructured":"Brejcha, J., \u010cad\u00edk, M.: State-of-the-art in visual geo-localization. Pattern Anal. Appl. 20, 613\u2013637 (2017)","journal-title":"Pattern Anal. Appl."},{"key":"26_CR6","unstructured":"Bresson, X., Laurent, T.: The transformer network for the traveling salesman problem. arXiv preprint arXiv:2103.03012 (2021)"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Brosh, E., et al.: Accurate visual localization for automotive applications. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00170"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Cho, K., Van\u00a0Merri\u00ebnboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"26_CR10","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\,\\times \\,$$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Fervers, F., Bullinger, S., Bodensteiner, C., Arens, M., Stiefelhagen, R.: Uncertainty-aware vision-based metric cross-view geolocalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21621\u201321631 (2023)","DOI":"10.1109\/CVPR52729.2023.02071"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Hu, S., Feng, M., Nguyen, R.M., Lee, G.H.: CVM-Net: cross-view matching network for image-based ground-to-aerial geo-localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7258\u20137267 (2018)","DOI":"10.1109\/CVPR.2018.00758"},{"key":"26_CR13","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448\u2013456. PMLR (2015)"},{"key":"26_CR14","unstructured":"Kay, W., et\u00a0al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"26_CR15","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Lentsch, T., Xia, Z., Caesar, H., Kooij, J.F.: SliceMatch: geometry-guided aggregation for cross-view pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17225\u201317234 (2023)","DOI":"10.1109\/CVPR52729.2023.01652"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Liu, L., Li, H.: Lending orientation to neural networks for cross-view geo-localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5624\u20135633 (2019)","DOI":"10.1109\/CVPR.2019.00577"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Video swin transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3202\u20133211 (2022)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"26_CR19","doi-asserted-by":"publisher","unstructured":"Noon, C., Bean, J.: An efficient transformation of the generalized traveling salesman problem. INFOR. Inf. Syst. Oper. Res. 31 (1993). https:\/\/doi.org\/10.1080\/03155986.1993.11732212","DOI":"10.1080\/03155986.1993.11732212"},{"key":"26_CR20","first-page":"26462","volume":"35","author":"J Pan","year":"2022","unstructured":"Pan, J., Lin, Z., Zhu, X., Shao, J., Li, H.: ST-Adapter: parameter-efficient image-to-video transfer learning. Adv. Neural. Inf. Process. Syst. 35, 26462\u201326477 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"26_CR21","unstructured":"Paszke, A., et\u00a0al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"26_CR22","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Regmi, K., Shah, M.: Video geo-localization employing geo-temporal feature learning and GPS trajectory smoothing. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12126\u201312135 (2021)","DOI":"10.1109\/ICCV48922.2021.01191"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Shi, Y., Li, H.: Beyond cross-view image retrieval: highly accurate vehicle localization using satellite image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17010\u201317020 (2022)","DOI":"10.1109\/CVPR52688.2022.01650"},{"key":"26_CR25","unstructured":"Shi, Y., Liu, L., Yu, X., Li, H.: Spatial-aware feature aggregation for image based cross-view geo-localization. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Shi, Y., Yu, X., Campbell, D., Li, H.: Where am i looking at? Joint location and orientation estimation by cross-view matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4064\u20134072 (2020)","DOI":"10.1109\/CVPR42600.2020.00412"},{"issue":"3","key":"26_CR27","first-page":"2682","volume":"45","author":"Y Shi","year":"2022","unstructured":"Shi, Y., Yu, X., Liu, L., Campbell, D., Koniusz, P., Li, H.: Accurate 3-DoF camera geo-localization via ground-to-satellite image matching. IEEE Trans. Pattern Anal. Mach. Intell. 45(3), 2682\u20132697 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"26_CR28","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/978-3-031-26319-4_8","volume-title":"Computer Vision \u2013 ACCV 2022: 16th Asian Conference on Computer Vision, Macao, China, December 4\u20138, 2022, Proceedings, Part I","author":"Y Shi","year":"2023","unstructured":"Shi, Y., Yu, X., Wang, S., Li, H.: CVLNet: cross-view semantic correspondence learning for\u00a0video-based camera localization. In: Wang, L., Gall, J., Chin, T.-J., Sato, I., Chellappa, R. (eds.) Computer Vision \u2013 ACCV 2022: 16th Asian Conference on Computer Vision, Macao, China, December 4\u20138, 2022, Proceedings, Part I, pp. 123\u2013141. Springer Nature Switzerland, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-26319-4_8"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Tian, Y., Chen, C., Shah, M.: Cross-view image matching for geo-localization in urban environments. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3608\u20133616 (2017)","DOI":"10.1109\/CVPR.2017.216"},{"key":"26_CR30","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., Jegou, H.: Training data-efficient image transformers and distillation through attention. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 10347\u201310357. PMLR (18\u201324 Jul 2021). https:\/\/proceedings.mlr.press\/v139\/touvron21a.html"},{"key":"26_CR31","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"26_CR32","doi-asserted-by":"publisher","first-page":"440","DOI":"10.1007\/978-3-031-19836-6_25","volume-title":"Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXVII","author":"S Vyas","year":"2022","unstructured":"Vyas, S., Chen, C., Shah, M.: GAMa: cross-view video geo-localization. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXVII, pp. 440\u2013456. Springer Nature Switzerland, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19836-6_25"},{"key":"26_CR33","unstructured":"Xia, Z., Booij, O., Kooij, J.F.: Convolutional cross-view pose estimation. arXiv preprint arXiv:2303.05915 (2023)"},{"key":"26_CR34","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1007\/978-3-031-19842-7_6","volume-title":"Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXIX","author":"Z Xia","year":"2022","unstructured":"Xia, Z., Booij, O., Manfredi, M., Kooij, J.F.P.: Visual cross-view metric localization with\u00a0dense uncertainty estimates. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXIX, pp. 90\u2013106. Springer Nature Switzerland, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19842-7_6"},{"key":"26_CR35","first-page":"29009","volume":"34","author":"H Yang","year":"2021","unstructured":"Yang, H., Lu, X., Zhu, Y.: Cross-view geo-localization with layer-to-layer transformer. Adv. Neural. Inf. Process. Syst. 34, 29009\u201329020 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"26_CR36","unstructured":"Yang, T., Zhu, Y., Xie, Y., Zhang, A., Chen, C., Li, M.: AIM: adapting image models for efficient video action recognition. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"26_CR37","doi-asserted-by":"crossref","unstructured":"Yu, F., et al.: Bdd100k: a diverse driving dataset for heterogeneous multitask learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2636\u20132645 (2020)","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"26_CR38","unstructured":"Zamir, A.R.: Visual geo-localization and location-aware image understanding (2014)"},{"issue":"8","key":"26_CR39","doi-asserted-by":"publisher","first-page":"1546","DOI":"10.1109\/TPAMI.2014.2299799","volume":"36","author":"AR Zamir","year":"2014","unstructured":"Zamir, A.R., Shah, M.: Image geo-localization based on multiplenearest neighbor feature matching usinggeneralized graphs. IEEE Trans. Pattern Anal. Mach. Intell. 36(8), 1546\u20131558 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, X., Li, X., Sultani, W., Chen, C., Wshah, S.: GeoDTR+: toward generic cross-view geolocalization via geometric disentanglement. arXiv preprint arXiv:2308.09624 (2023)","DOI":"10.1109\/TPAMI.2024.3443652"},{"key":"26_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, X., Li, X., Sultani, W., Zhou, Y., Wshah, S.: Cross-view geo-localization via learning disentangled geometric layout correspondence. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 3480\u20133488 (2023)","DOI":"10.1609\/aaai.v37i3.25457"},{"key":"26_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, X., Li, X., Sultani, W., Zhou, Y., Wshah, S.: Cross-view geo-localization via learning disentangled geometric layout correspondence. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 3480\u20133488 (2023)","DOI":"10.1609\/aaai.v37i3.25457"},{"key":"26_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, X., Sultani, W., Wshah, S.: Cross-view image sequence geo-localization. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2914\u20132923 (2023)","DOI":"10.1109\/WACV56688.2023.00293"},{"key":"26_CR44","doi-asserted-by":"crossref","unstructured":"Zhu, S., Shah, M., Chen, C.: TransGeo: transformer is all you need for cross-view image geo-localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1162\u20131171 (2022)","DOI":"10.1109\/CVPR52688.2022.00123"},{"key":"26_CR45","doi-asserted-by":"crossref","unstructured":"Zhu, S., Yang, T., Chen, C.: Revisiting street-to-aerial view image geo-localization and orientation estimation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 756\u2013765 (2021)","DOI":"10.1109\/WACV48630.2021.00080"},{"key":"26_CR46","doi-asserted-by":"crossref","unstructured":"Zhu, S., Yang, T., Chen, C.: VIGOR: cross-view image geo-localization beyond one-to-one retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3640\u20133649 (2021)","DOI":"10.1109\/CVPR46437.2021.00364"}],"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\/978-3-031-73030-6_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T12:19:25Z","timestamp":1732537165000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73030-6_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,24]]},"ISBN":["9783031730290","9783031730306"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73030-6_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,24]]},"assertion":[{"value":"24 November 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"}}]}}