{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T06:05:41Z","timestamp":1789538741907,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":94,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032376237","type":"print"},{"value":"9783032376244","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37624-4_15","type":"book-chapter","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T05:46:06Z","timestamp":1789537566000},"page":"247-266","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["UniPR-3D: Towards Universal Visual Place Recognition with\u00a0Visual Geometry Grounded Transformer"],"prefix":"10.1007","author":[{"given":"Tianchen","family":"Deng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziming","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongming","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuhao","family":"Zhai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danwei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Javier","family":"Civera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hesheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,17]]},"reference":[{"key":"15_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., Giguere, P.: Gsv-cities: Toward appropriate supervised visual place recognition. Neurocomputing 513, 194\u2013203 (2022)","journal-title":"Neurocomputing"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Ali-Bey, A., Chaib-Draa, B., Giguere, P.: Mixvpr: feature mixing for visual place recognition. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2998\u20133007 (2023)","DOI":"10.1109\/WACV56688.2023.00301"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Ali-Bey, A., Chaib-Draa, B., Giguere, P.: Boq: a place is worth a bag of learnable queries. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17794\u201317803 (2024)","DOI":"10.1109\/CVPR52733.2024.01685"},{"key":"15_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"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Arroyo, R., Alcantarilla, P.F., Bergasa, L.M., Romera, E.: Towards life-long visual localization using an efficient matching of binary sequences from images. In: 2015 IEEE International Conference on Robotics and Automation (ICRA), pp. 6328\u20136335. IEEE (2015)","DOI":"10.1109\/ICRA.2015.7140088"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Barbarani, G., et al.: Are local features all you need for cross-domain visual place recognition? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6155\u20136165 (2023)","DOI":"10.1109\/CVPRW59228.2023.00655"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Berton, G., Masone, C.: Megaloc: one retrieval to place them all. In: Proceedings of the Computer Vision and Pattern Recognition Conference Workshops, pp. 2861\u20132867 (2025)","DOI":"10.1109\/CVPRW67362.2025.00269"},{"key":"15_CR8","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":"15_CR9","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, pp. 11080\u201311090 (2023)","DOI":"10.1109\/ICCV51070.2023.01017"},{"issue":"2","key":"15_CR10","doi-asserted-by":"publisher","first-page":"1310","DOI":"10.1109\/LRA.2023.3339058","volume":"9","author":"G Berton","year":"2023","unstructured":"Berton, G., Trivigno, G., Caputo, B., Masone, C.: Jist: joint image and sequence training for sequential visual place recognition. IEEE Rob. Autom. Lett. 9(2), 1310\u20131317 (2023)","journal-title":"IEEE Rob. Autom. Lett."},{"key":"15_CR11","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1111\/cgf.14778","volume":"42","author":"N Bonneel","year":"2023","unstructured":"Bonneel, N., Digne, J.: A survey of optimal transport for computer graphics and computer vision. Comput. Graph. Forum 42, 439\u2013460 (2023)","journal-title":"Comput. Graph. Forum"},{"issue":"6","key":"15_CR12","doi-asserted-by":"publisher","first-page":"1874","DOI":"10.1109\/TRO.2021.3075644","volume":"37","author":"C Campos","year":"2021","unstructured":"Campos, C., Elvira, R., Rodr\u00edguez, J.J.G., Montiel, J.M., Tard\u00f3s, J.D.: Orb-slam3: an accurate open-source library for visual, visual-inertial, and multimap slam. IEEE Trans. Rob. 37(6), 1874\u20131890 (2021)","journal-title":"IEEE Trans. Rob."},{"key":"15_CR13","unstructured":"Chen, K., et al.: Out of sight but not out of mind: hybrid memory for dynamic video world models. arXiv preprint arXiv:2603.25716 (2026)"},{"issue":"4","key":"15_CR14","doi-asserted-by":"publisher","first-page":"4015","DOI":"10.1109\/LRA.2018.2859916","volume":"3","author":"Z Chen","year":"2018","unstructured":"Chen, Z., Liu, L., Sa, I., Ge, Z., Chli, M.: Learning context flexible attention model for long-term visual place recognition. IEEE Rob. Autom. Lett. 3(4), 4015\u20134022 (2018)","journal-title":"IEEE Rob. Autom. Lett."},{"key":"15_CR15","unstructured":"Cheng, Z., Zhang, X., Di, D., Wei, C., Li, H., Yang, X.: Moca: modeling object consistency for 3d camera control in video generation. In: The Fourteenth International Conference on Learning Representations (2026)"},{"key":"15_CR16","unstructured":"Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transport. Adv. Neural. Inf. Process. Syst. 26 (2013)"},{"key":"15_CR17","unstructured":"Dao, T.: Flashattention-2: faster attention with better parallelism and work partitioning. arXiv preprint arXiv:2307.08691 (2023)"},{"key":"15_CR18","unstructured":"Deng, T., Liu, S., Wang, X., Liu, Y., Wang, D., Chen, W.: Prosgnerf: progressive dynamic neural scene graph with frequency modulated auto-encoder in urban scenes. arXiv preprint arXiv:2312.09076 (2023)"},{"key":"15_CR19","unstructured":"Deng, T., et al.: What is the best 3d scene representation for robotics? From geometric to foundation models. arXiv preprint arXiv:2512.03422 (2025)"},{"key":"15_CR20","unstructured":"Deng, T., et al.: Mcn-slam: multi-agent collaborative neural slam with hybrid implicit neural scene representation. arXiv preprint arXiv:2506.18678 (2025)"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Deng, T., et al.: Plgslam: progressive neural scene represenation with local to global bundle adjustment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19657\u201319666 (2024)","DOI":"10.1109\/CVPR52733.2024.01859"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Deng, T., et\u00a0al.: Mne-slam: multi-agent neural slam for mobile robots. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 1485\u20131494 (2025)","DOI":"10.1109\/CVPR52734.2025.00146"},{"key":"15_CR23","doi-asserted-by":"publisher","unstructured":"Deng, T., et al.: Neslam: neural implicit mapping and self-supervised feature tracking with depth completion and denoising. IEEE Trans. Autom. Sci. Eng.\u00a0(2025). https:\/\/doi.org\/10.1109\/TASE.2025.3541064","DOI":"10.1109\/TASE.2025.3541064"},{"issue":"1","key":"15_CR24","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1109\/MRA.2022.3228492","volume":"30","author":"T Deng","year":"2023","unstructured":"Deng, T., Xie, H., Wang, J., Chen, W.: Long-term visual simultaneous localization and mapping: using a bayesian persistence filter-based global map prediction. IEEE Rob. Autom. Maga. 30(1), 36\u201349 (2023)","journal-title":"IEEE Rob. Autom. Maga."},{"key":"15_CR25","unstructured":"Facil, J.M., Olid, D., Montesano, L., Civera, J.: Condition-invariant multi-view place recognition. arXiv preprint arXiv:1902.09516 (2019)"},{"key":"15_CR26","unstructured":"Fang, X., et al.: Dens3r: a foundation model for 3d geometry prediction. arXiv preprint arXiv:2507.16290 (2025)"},{"issue":"5","key":"15_CR27","doi-asserted-by":"publisher","first-page":"1188","DOI":"10.1109\/TRO.2012.2197158","volume":"28","author":"D G\u00e1lvez-L\u00f3pez","year":"2012","unstructured":"G\u00e1lvez-L\u00f3pez, D., Tardos, J.D.: Bags of binary words for fast place recognition in image sequences. IEEE Trans. Rob. 28(5), 1188\u20131197 (2012)","journal-title":"IEEE Trans. Rob."},{"key":"15_CR28","unstructured":"Gao, J., et al.: More: 3d visual geometry reconstruction meets mixture-of-experts. arXiv preprint arXiv:2510.27234 (2025)"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Garg, S., Fischer, T., Milford, M.: Where is your place, visual place recognition? arXiv preprint arXiv:2103.06443 (2021)","DOI":"10.24963\/ijcai.2021\/603"},{"issue":"4","key":"15_CR30","doi-asserted-by":"publisher","first-page":"5120","DOI":"10.1109\/LRA.2020.3005627","volume":"5","author":"S Garg","year":"2020","unstructured":"Garg, S., Harwood, B., Anand, G., Milford, M.: Delta descriptors: change-based place representation for robust visual localization. IEEE Rob. Autom. Lett. 5(4), 5120\u20135127 (2020)","journal-title":"IEEE Rob. Autom. Lett."},{"issue":"3","key":"15_CR31","doi-asserted-by":"publisher","first-page":"4305","DOI":"10.1109\/LRA.2021.3067633","volume":"6","author":"S Garg","year":"2021","unstructured":"Garg, S., Milford, M.: Seqnet: learning descriptors for sequence-based hierarchical place recognition. IEEE Rob. Autom. Lett. 6(3), 4305\u20134312 (2021)","journal-title":"IEEE Rob. Autom. Lett."},{"key":"15_CR32","unstructured":"Garg, S., Vankadari, M., Milford, M.: Seqmatchnet: contrastive learning with sequence matching for place recognition & relocalization. In: Conference on Robot Learning, pp. 429\u2013443. PMLR (2022)"},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"Gong, Z., et al.: Dino-slam: dino-informed rgb-d slam for neural implicit and explicit representations. arXiv preprint arXiv:2507.19474 (2025)","DOI":"10.1007\/978-3-032-37041-9_9"},{"key":"15_CR34","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14141\u201314152 (2021)","DOI":"10.1109\/CVPR46437.2021.01392"},{"key":"15_CR35","doi-asserted-by":"crossref","unstructured":"Hussaini, S., Fischer, T., Milford, M.: Improving visual place recognition with sequence-matching receptiveness prediction. arXiv preprint arXiv:2503.06840 (2025)","DOI":"10.1109\/IROS60139.2025.11247581"},{"key":"15_CR36","doi-asserted-by":"publisher","unstructured":"Izquierdo, S., Civera, J.: Close, but not there: boosting geographic distance sensitivity in visual place recognition. In: European Conference on Computer Vision, pp. 240\u2013257. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-73464-9_15","DOI":"10.1007\/978-3-031-73464-9_15"},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Izquierdo, S., Civera, J.: Optimal transport aggregation for visual place recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17658\u201317668 (2024)","DOI":"10.1109\/CVPR52733.2024.01672"},{"key":"15_CR38","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Douze, M., Schmid, C., P\u00e9rez, P.: Aggregating local descriptors into a compact image representation. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 3304\u20133311. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5540039"},{"issue":"2","key":"15_CR39","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 Rob. Autom. Lett. 9(2), 1286\u20131293 (2023)","journal-title":"IEEE Rob. Autom. Lett."},{"key":"15_CR40","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"15_CR41","doi-asserted-by":"crossref","unstructured":"Li, H., Peng, G., Zhang, J., Wen, M., Ma, Y., Wang, D.: Casevpr: correlation-aware sequential embedding for sequence-to-frame visual place recognition. IEEE Rob. Autom. Lett. (2025)","DOI":"10.1109\/LRA.2025.3541452"},{"key":"15_CR42","unstructured":"Liu, M., et al.: Streamvlo: streaming visual-lidar odometry with cumulative drift compensation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 39086\u201339097 (2026)"},{"key":"15_CR43","doi-asserted-by":"crossref","unstructured":"Liu, M., et al.: Driveva: video action models are zero-shot drivers. arXiv preprint arXiv:2604.04198 (2026)","DOI":"10.1007\/978-3-032-37718-0_19"},{"issue":"6","key":"15_CR44","doi-asserted-by":"publisher","first-page":"8907","DOI":"10.1109\/TII.2024.3378829","volume":"20","author":"Q Liu","year":"2024","unstructured":"Liu, Q., Chen, N., Liu, Z., Wang, H.: Toward learning-based visuomotor navigation with neural radiance fields. IEEE Trans. Ind. Inf. 20(6), 8907\u20138916 (2024). https:\/\/doi.org\/10.1109\/TII.2024.3378829","journal-title":"IEEE Trans. Ind. Inf."},{"issue":"12","key":"15_CR45","doi-asserted-by":"publisher","first-page":"11200","DOI":"10.1109\/TPAMI.2024.3455252","volume":"46","author":"Q Liu","year":"2024","unstructured":"Liu, Q., Xin, H., Liu, Z., Wang, H.: Integrating neural radiance fields end-to-end for cognitive visuomotor navigation. IEEE Trans. Pattern Anal. Mach. Intell. 46(12), 11200\u201311215 (2024). https:\/\/doi.org\/10.1109\/TPAMI.2024.3455252","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR46","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Mg-slam: structure gaussian splatting slam with manhattan world hypothesis. IEEE Trans. Autom. Sci. Eng. (2025)","DOI":"10.1109\/TASE.2025.3575772"},{"issue":"1","key":"15_CR47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TRO.2015.2496823","volume":"32","author":"S Lowry","year":"2015","unstructured":"Lowry, S., et al.: Visual place recognition: a survey. IEEE Trans. Rob. 32(1), 1\u201319 (2015)","journal-title":"IEEE Trans. Rob."},{"issue":"3","key":"15_CR48","doi-asserted-by":"publisher","first-page":"2731","DOI":"10.1109\/TPAMI.2025.3629287","volume":"48","author":"F Lu","year":"2026","unstructured":"Lu, F., et al.: Selavpr++: towards seamless adaptation of foundation models for efficient place recognition. IEEE Trans. Pattern Anal. Mach. Intell. 48(3), 2731\u20132748 (2026)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR49","doi-asserted-by":"crossref","unstructured":"Lu, F., Lan, X., Zhang, L., Jiang, D., Wang, Y., Yuan, C.: Cricavpr: cross-image correlation-aware representation learning for visual place recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16772\u201316782 (2024)","DOI":"10.1109\/CVPR52733.2024.01587"},{"key":"15_CR50","unstructured":"Lu, F., Zhang, L., Lan, X., Dong, S., Wang, Y., Yuan, C.: Towards seamless adaptation of pre-trained models for visual place recognition. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"15_CR51","doi-asserted-by":"crossref","unstructured":"Lv, J., Ju, X., Wang, C.: Neural network-based nonconservative predefined-time backstepping control for uncertain strict-feedback nonlinear systems. IEEE Trans. Neural Netw. Learn. Syst. (2023)","DOI":"10.1109\/TNNLS.2023.3296194"},{"key":"15_CR52","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2025.112625","volume":"183","author":"J Lv","year":"2026","unstructured":"Lv, J., Wang, C., Xie, L.: Adaptive distributed observer design for nonlinear multiagent systems. Automatica 183, 112625 (2026)","journal-title":"Automatica"},{"key":"15_CR53","unstructured":"Ma, Y., et\u00a0al.: Controllable video generation: a survey. arXiv preprint arXiv:2507.16869 (2025)"},{"key":"15_CR54","unstructured":"Ma, Y., et al.: Follow-your-creation: empowering 4d creation through video inpainting. arXiv preprint arXiv:2506.04590 (2025)"},{"key":"15_CR55","doi-asserted-by":"crossref","unstructured":"Ma, Y., et al.: Follow your pose: pose-guided text-to-video generation using pose-free videos. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 4117\u20134125 (2024)","DOI":"10.1609\/aaai.v38i5.28206"},{"issue":"1","key":"15_CR56","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. Rob. Res. 36(1), 3\u201315 (2017)","journal-title":"Int. J. Rob. Res."},{"key":"15_CR57","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)","journal-title":"IEEE Access"},{"issue":"4","key":"15_CR58","doi-asserted-by":"publisher","first-page":"10383","DOI":"10.1109\/LRA.2022.3194310","volume":"7","author":"R Mereu","year":"2022","unstructured":"Mereu, R., Trivigno, G., Berton, G., Masone, C., Caputo, B.: Learning sequential descriptors for sequence-based visual place recognition. IEEE Rob. Autom. Lett. 7(4), 10383\u201310390 (2022)","journal-title":"IEEE Rob. Autom. Lett."},{"key":"15_CR59","doi-asserted-by":"crossref","unstructured":"Milford, M., Fischer, T.: Going places: place recognition in artificial and natural systems. Robot. Auton. Syst. 9 (2025)","DOI":"10.1146\/annurev-control-032724-014418"},{"key":"15_CR60","doi-asserted-by":"crossref","unstructured":"Milford, M.J., Wyeth, G.F.: Seqslam: visual route-based navigation for sunny summer days and stormy winter nights. In: 2012 IEEE International Conference on Robotics and Automation, pp. 1643\u20131649. IEEE (2012)","DOI":"10.1109\/ICRA.2012.6224623"},{"issue":"1","key":"15_CR61","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1109\/TRO.2012.2220211","volume":"29","author":"AC Murillo","year":"2012","unstructured":"Murillo, A.C., Singh, G., Kosecka, J., Guerrero, J.J.: Localization in urban environments using a panoramic gist descriptor. IEEE Trans. Rob. 29(1), 146\u2013160 (2012)","journal-title":"IEEE Trans. Rob."},{"key":"15_CR62","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"issue":"7","key":"15_CR63","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":"15_CR64","doi-asserted-by":"crossref","unstructured":"Revaud, J., Almaz\u00e1n, J., Rezende, R.S., Souza, C.R.D.: Learning with average precision: training image retrieval with a listwise loss. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5107\u20135116 (2019)","DOI":"10.1109\/ICCV.2019.00521"},{"key":"15_CR65","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., Cadena, C., Siegwart, R., Dymczyk, M.: From coarse to fine: robust hierarchical localization at large scale. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12716\u201312725 (2019)","DOI":"10.1109\/CVPR.2019.01300"},{"key":"15_CR66","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., DeTone, D., Malisiewicz, T., Rabinovich, A.: Superglue: learning feature matching with graph neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4938\u20134947 (2020)","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"15_CR67","doi-asserted-by":"crossref","unstructured":"Schubert, S., Neubert, P., Garg, S., Milford, M., Fischer, T.: Visual place recognition: a tutorial. IEEE Rob. Autom. Maga. (2023)","DOI":"10.1109\/MRA.2023.3310859"},{"key":"15_CR68","doi-asserted-by":"crossref","unstructured":"Schubert, S., Neubert, P., Protzel, P.: Fast and memory efficient graph optimization via icm for visual place recognition. Rob. Sci. Syst. 2 (2021)","DOI":"10.15607\/RSS.2021.XVII.091"},{"key":"15_CR69","doi-asserted-by":"crossref","unstructured":"Sferrazza, D., Berton, G., Trivigno, G., Masone, C.: To match or not to match: revisiting image matching for reliable visual place recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 2874\u20132885 (2025)","DOI":"10.1109\/CVPRW67362.2025.00268"},{"key":"15_CR70","unstructured":"Shen, G., et al.: Grs-slam3r: real-time dense slam with gated recurrent state. arXiv preprint arXiv:2509.23737 (2025)"},{"key":"15_CR71","doi-asserted-by":"crossref","unstructured":"Shen, H., et al.: Unilgl: learning uniform place recognition for fov-limited\/panoramic lidar global localization. arXiv preprint arXiv:2507.12194 (2025)","DOI":"10.1109\/TRO.2026.3672514"},{"key":"15_CR72","doi-asserted-by":"crossref","unstructured":"Sivic, Z.: Video google: a text retrieval approach to object matching in videos. In: Proceedings ninth IEEE International Conference on Computer Vision, pp. 1470\u20131477. IEEE (2003)","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"15_CR73","doi-asserted-by":"crossref","unstructured":"Song, W., et al.: Accelerating vision-language-action model integrated with action chunking via parallel decoding. arXiv preprint arXiv:2503.02310 (2025)","DOI":"10.1109\/IROS60139.2025.11247519"},{"key":"15_CR74","doi-asserted-by":"crossref","unstructured":"Song, W., et al.: Reconvla: reconstructive vision-language-action model as effective robot perceiver. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, pp. 18549\u201318557 (2026)","DOI":"10.1609\/aaai.v40i22.38921"},{"key":"15_CR75","unstructured":"S\u00fcnderhauf, N., Neubert, P., Protzel, P.: Are we there yet? Challenging seqslam on a 3000 km journey across all four seasons. In: Proceedings of Workshop on Long-Term Autonomy, IEEE International Conference on Robotics and Automation (ICRA), p. 2013. Citeseer (2013)"},{"key":"15_CR76","doi-asserted-by":"crossref","unstructured":"S\u00fcnderhauf, N., Protzel, P.: Brief-gist-closing the loop by simple means. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 1234\u20131241. IEEE (2011)","DOI":"10.1109\/IROS.2011.6094921"},{"key":"15_CR77","doi-asserted-by":"crossref","unstructured":"Taira, H., et al.: Inloc: indoor visual localization with dense matching and view synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7199\u20137209 (2018)","DOI":"10.1109\/CVPR.2018.00752"},{"key":"15_CR78","doi-asserted-by":"crossref","unstructured":"Torii, A., Arandjelovic, R., Sivic, J., Okutomi, 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":"15_CR79","doi-asserted-by":"crossref","unstructured":"Torii, A., Sivic, J., Pajdla, T., Okutomi, M.: Visual place recognition with repetitive structures. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 883\u2013890 (2013)","DOI":"10.1109\/CVPR.2013.119"},{"key":"15_CR80","doi-asserted-by":"crossref","unstructured":"Tosi, F., et al.: How nerfs and 3d gaussian splatting are reshaping slam: a survey. IEEE Trans. Rob. (2026)","DOI":"10.1109\/TRO.2026.3666139"},{"key":"15_CR81","unstructured":"Tu, S., et al.: The role of world models in shaping autonomous driving: a comprehensive survey. arXiv preprint arXiv:2502.10498 (2025)"},{"key":"15_CR82","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., Novotny, D.: Vggt: visual geometry grounded transformer. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 5294\u20135306 (2025)","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"15_CR83","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13648\u201313657 (2022)","DOI":"10.1109\/CVPR52688.2022.01328"},{"key":"15_CR84","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5022\u20135030 (2019)","DOI":"10.1109\/CVPR.2019.00516"},{"key":"15_CR85","doi-asserted-by":"crossref","unstructured":"Wang, Y., Fang, Z., Zhao, L., Chen, W.: Learning to tune like an expert: interpretable and scene-aware navigation via mllm reasoning and cvae-based adaptation. arXiv preprint arXiv:2507.11001 (2025)","DOI":"10.1109\/TASE.2026.3673004"},{"key":"15_CR86","doi-asserted-by":"publisher","unstructured":"Wang, Y., et al.: Sfpnet: sparse focal point network for semantic segmentation on general lidar point clouds. In: European Conference on Computer Vision, pp. 403\u2013421. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-72652-1_24","DOI":"10.1007\/978-3-031-72652-1_24"},{"key":"15_CR87","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2626\u20132635 (2020)","DOI":"10.1109\/CVPR42600.2020.00270"},{"key":"15_CR88","doi-asserted-by":"crossref","unstructured":"Wu, X., et al.: Generation models know space: unleashing implicit 3d priors for scene understanding. arXiv preprint arXiv:2603.19235 (2026)","DOI":"10.1007\/978-3-032-37235-2_15"},{"issue":"10","key":"15_CR89","doi-asserted-by":"publisher","first-page":"15254","DOI":"10.1109\/TVT.2025.3572622","volume":"74","author":"C Yang","year":"2025","unstructured":"Yang, C., Pan, H., Wang, J.: Stgcnformer: spatio-temporal dual-stream graph convolutional networks and transformers for traffic forecasting. IEEE Trans. Veh. Technol. 74(10), 15254\u201315263 (2025). https:\/\/doi.org\/10.1109\/TVT.2025.3572622","journal-title":"IEEE Trans. Veh. Technol."},{"key":"15_CR90","doi-asserted-by":"publisher","unstructured":"Yang, C., Pan, H., Wang, J., Hong, Y.: Trajdiff: trajectory prediction with diffusion probabilistic models. IEEE Trans. Image Process. 1\u201314 (2025). https:\/\/doi.org\/10.1109\/TIP.2025.3640001","DOI":"10.1109\/TIP.2025.3640001"},{"key":"15_CR91","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107760","volume":"113","author":"X Zhang","year":"2021","unstructured":"Zhang, X., Wang, L., Su, Y.: Visual place recognition: a survey from deep learning perspective. Pattern Recogn. 113, 107760 (2021)","journal-title":"Pattern Recogn."},{"issue":"3","key":"15_CR92","doi-asserted-by":"publisher","first-page":"2351","DOI":"10.1109\/LRA.2024.3354627","volume":"9","author":"J Zhao","year":"2024","unstructured":"Zhao, J., et al.: Learning sequence descriptor based on spatio-temporal attention for visual place recognition. IEEE Rob. Autom. Lett. 9(3), 2351\u20132358 (2024). https:\/\/doi.org\/10.1109\/LRA.2024.3354627","journal-title":"IEEE Rob. Autom. Lett."},{"key":"15_CR93","doi-asserted-by":"publisher","unstructured":"Zhou, Q., Maximov, M., Litany, O., Leal-Taix\u00e9, L.: The nerfect match: exploring nerf features for visual localization. In: European Conference on Computer Vision, pp. 108\u2013127. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-72691-0_7","DOI":"10.1007\/978-3-031-72691-0_7"},{"key":"15_CR94","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19370\u201319380 (2023)","DOI":"10.1109\/CVPR52729.2023.01856"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37624-4_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T05:46:40Z","timestamp":1789537600000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37624-4_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032376237","9783032376244"],"references-count":94,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37624-4_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"17 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}