{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T21:20:02Z","timestamp":1771708802900,"version":"3.50.1"},"reference-count":89,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,8,28]],"date-time":"2020-08-28T00:00:00Z","timestamp":1598572800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,8,28]],"date-time":"2020-08-28T00:00:00Z","timestamp":1598572800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"ANR project pLaTINUM"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2021,1]]},"DOI":"10.1007\/s11263-020-01363-6","type":"journal-article","created":{"date-parts":[[2020,8,28]],"date-time":"2020-08-28T04:25:17Z","timestamp":1598588717000},"page":"185-202","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Improving Image Description with Auxiliary Modality for Visual Localization in Challenging Conditions"],"prefix":"10.1007","volume":"129","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7952-6643","authenticated-orcid":false,"given":"Nathan","family":"Piasco","sequence":"first","affiliation":[]},{"given":"D\u00e9sir\u00e9","family":"Sidib\u00e9","sequence":"additional","affiliation":[]},{"given":"Val\u00e9rie","family":"Gouet-Brunet","sequence":"additional","affiliation":[]},{"given":"C\u00e9dric","family":"Demonceaux","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,8,28]]},"reference":[{"key":"1363_CR1","doi-asserted-by":"crossref","unstructured":"Anoosheh, A., Agustsson, E., Timofte, R., & Van Gool, L. (2018). Combogan: Unrestrained scalability for image domain translation. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops (pp. 783\u2013790).","DOI":"10.1109\/CVPRW.2018.00122"},{"key":"1363_CR2","doi-asserted-by":"crossref","unstructured":"Anoosheh, A., Sattler, T., Timofte, R., Pollefeys, M., & Van Gool, L. (2019). Night-to-day image translation for retrieval-based localization. In International conference on robotics and automation (ICRA) (pp. 5958\u20135964). IEEE.","DOI":"10.1109\/ICRA.2019.8794387"},{"key":"1363_CR3","doi-asserted-by":"crossref","unstructured":"Arandjelovi\u0107, R., Gronat, P., Torii, A., Pajdla, T., & Sivic, J. (2017). NetVLAD: CNN architecture for weakly supervised place recognition. In IEEE transactions on pattern analysis and machine intelligence (TPAMI) (pp. 5297\u20135307).","DOI":"10.1109\/CVPR.2016.572"},{"key":"1363_CR4","unstructured":"Arandjelovi\u0107, R. & Zisserman, A. (2014). DisLocation : Scalable descriptor. In Asian conference on computer vision (ACCV)."},{"key":"1363_CR5","doi-asserted-by":"crossref","unstructured":"Ardeshir, S., Zamir, A. R., Torroella, A., & Shah, M. (2014). GIS-assisted object detection and geospatial localization. In European conference on computer vision (ECCV), LNCS (Vol. 8694, pp. 602\u2013617).","DOI":"10.1007\/978-3-319-10599-4_39"},{"issue":"2","key":"1363_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2591009","volume":"33","author":"M Aubry","year":"2014","unstructured":"Aubry, M., Russell, B. C., & Sivic, J. (2014). Painting-to-3D model alignment via discriminative visual elements. ACM Transactions on Graphics (ToG), 33(2), 1\u201314.","journal-title":"ACM Transactions on Graphics (ToG)"},{"key":"1363_CR7","doi-asserted-by":"crossref","unstructured":"Azzi, C., Asmar, D., Fakih, A., & Zelek, J. (2016). Filtering 3D keypoints using GIST for accurate image-based localization. In British machine vision conference (BMVC) (Vol. 2, pp. 1\u201312).","DOI":"10.5244\/C.30.127"},{"key":"1363_CR8","doi-asserted-by":"crossref","unstructured":"Balntas, V., Riba, E., Ponsa, D., & Mikolajczyk, K. (2016). Learning local feature descriptors with triplets and shallow convolutional neural networks. In BMVC (Vol. 1, p. 3).","DOI":"10.5244\/C.30.119"},{"key":"1363_CR9","doi-asserted-by":"crossref","unstructured":"Bansal, A., Badino, H., & Huber, D. (2014). Understanding how camera configuration and environmental conditions affect appearance-based localization. InIEEE intelligent vehicles symposium (IV) (pp. 800\u2013807).","DOI":"10.1109\/IVS.2014.6856605"},{"key":"1363_CR10","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.isprsjprs.2017.01.005","volume":"125","author":"M Bevilacqua","year":"2017","unstructured":"Bevilacqua, M., Aujol, J. F., Biasutti, P., Br\u00e9dif, M., & Bugeau, A. (2017). Joint inpainting of depth and reflectance with visibility estimation. ISPRS Journal of Photogrammetry and Remote Sensing, 125, 16\u201332.","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"1363_CR11","doi-asserted-by":"crossref","unstructured":"Bhowmik, N., Weng, L., Gouet-Brunet, V., & Soheilian, B. (2017). Cross-domain image localization by adaptive feature fusion. In Joint urban remote sensing event (JURSE).","DOI":"10.1109\/JURSE.2017.7924572"},{"key":"1363_CR12","doi-asserted-by":"crossref","unstructured":"Brachmann, E. & Rother, C. (2018). Learning less is more\u20146D camera localization via 3D surface regression. In IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00489"},{"key":"1363_CR13","doi-asserted-by":"crossref","unstructured":"Cao, Y., Long, M., Wang, J., Zhu, H., & Wen, Q. (2016). Deep quantization network for efficient image retrieval. In AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v30i1.10455"},{"key":"1363_CR14","doi-asserted-by":"crossref","unstructured":"Cao, Z., Long, M., Wang, J., & Yu, P. S. (2017). Hashnet: Deep learning to hash by continuation. In Proceedings of the IEEE international conference on computer vision (pp. 5608\u20135617).","DOI":"10.1109\/ICCV.2017.598"},{"key":"1363_CR15","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.patrec.2018.09.007","volume":"116","author":"M Chevalier","year":"2018","unstructured":"Chevalier, M., Thome, N., H\u00e9naff, G., & Cord, M. (2018). Classifying low-resolution images by integrating privileged information in deep CNNs. Pattern Recognition Letters, 116, 29\u201335.","journal-title":"Pattern Recognition Letters"},{"key":"1363_CR16","unstructured":"Christie, G., Warnell, G., & Kochersberger, K. (2016). Semantics for UGV registration in GPS-denied environments. arXiv:1609.04794."},{"key":"1363_CR17","doi-asserted-by":"crossref","unstructured":"Chum, O., Mikul, A., Perdoch, M., & Matas, J. (2011). Total recall II : Query expansion revisited. In IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2011.5995601"},{"key":"1363_CR18","doi-asserted-by":"crossref","unstructured":"Chum, O., Philbin, J., Sivic, J., Isard, M., & Zisserman, A. (2007). Total recall: Automatic query expansion with a generative feature model for object retrieval. In IEEE international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2007.4408891"},{"issue":"8","key":"1363_CR19","doi-asserted-by":"publisher","first-page":"3893","DOI":"10.1109\/TIP.2018.2821921","volume":"27","author":"C Deng","year":"2018","unstructured":"Deng, C., Chen, Z., Liu, X., Gao, X., & Tao, D. (2018). Triplet-based deep hashing network for cross-modal retrieval. IEEE Transactions on Image Processing, 27(8), 3893\u20133903.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1363_CR20","unstructured":"Eigen, D., Puhrsch, C., & Fergus, R. (2014). Depth map prediction from a single image using a multi-scale deep network. In Annual conference on neural information processing systems (NIPS) (pp. 1\u20139)."},{"key":"1363_CR21","doi-asserted-by":"crossref","unstructured":"Eitel, A., Springenberg, J. T., Spinello, L., Riedmiller, M., & Burgard, W. (2015). Multimodal deep learning for robust RGB-D object recognition. In IEEE international conference on intelligent robots and systems (IROS) (Vol. 2015, pp. 681\u2013687).","DOI":"10.1109\/IROS.2015.7353446"},{"key":"1363_CR22","doi-asserted-by":"crossref","unstructured":"Garg, S., Suenderhauf, N., & Milford, M. (2018a). Don\u2019t look back: Robustifying place categorization for viewpoint- and condition-invariant place recognition. In IEEE international conference on robotics and automation (ICRA).","DOI":"10.1109\/ICRA.2018.8461051"},{"key":"1363_CR23","doi-asserted-by":"crossref","unstructured":"Garg, S., Suenderhauf, N., & Milford, M. (2018b). LoST? Appearance-invariant place recognition for opposite viewpoints using visual semantics. In Robotics science and systems (RSS).","DOI":"10.15607\/RSS.2018.XIV.022"},{"key":"1363_CR24","unstructured":"Germain, H., Bourmaud, G., & Lepetit, V. (2018). Improving nighttime retrieval-based localization. arXiv:1812.03707.pdf."},{"key":"1363_CR25","doi-asserted-by":"crossref","unstructured":"Germain, H., Bourmaud, G., & Lepetit, V. (2019, September). Sparse-to-dense hypercolumn matching for long-term visual localization. In 2019 International Conference on 3D Vision (3DV) (pp. 513\u2013523). IEEE.","DOI":"10.1109\/3DV.2019.00063"},{"key":"1363_CR26","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., & Brostow, G. J. (2017). Unsupervised monocular depth estimation with left-right consistency. In IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.699"},{"key":"1363_CR27","doi-asserted-by":"crossref","unstructured":"Gordo, A., Almaz\u00e1n, J., Revaud, J., & Larlus, D. (2016). Deep image retrieval: Learning global representations for image search. In European conference on computer vision (ECCV) (Vol. 9905, pp. 241\u2013257).","DOI":"10.1007\/978-3-319-46466-4_15"},{"issue":"2","key":"1363_CR28","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1007\/s11263-017-1016-8","volume":"124","author":"A Gordo","year":"2017","unstructured":"Gordo, A., Almaz\u00e1n, J., Revaud, J., & Larlus, D. (2017). End-to-end learning of deep visual representations for image retrieval. International Journal of Computer Vision (IJCV), 124(2), 237\u2013254.","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"1363_CR29","doi-asserted-by":"crossref","unstructured":"Gupta, S., Girshick, R., Arbel\u00e1ez, P., & Malik, J. (2014). Learning rich features from RGB-D images for object detection and segmentation. In European conference on computer vision (ECCV), LNCS (Vol. 8695, pp. 345\u2013360).","DOI":"10.1007\/978-3-319-10584-0_23"},{"key":"1363_CR30","doi-asserted-by":"crossref","unstructured":"Hays, J. & Efros, A. A. (2008). IM2GPS: Estimating geographic information from a single image. In IEEE conference on computer vision and pattern recognition (CVPR) (Vol. 05).","DOI":"10.1109\/CVPR.2008.4587784"},{"key":"1363_CR31","unstructured":"Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531."},{"key":"1363_CR32","doi-asserted-by":"crossref","unstructured":"Hoffman, J., Gupta, S., & Darrell, T. (2016). Learning with side information through modality hallucination. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 826\u2013834).","DOI":"10.1109\/CVPR.2016.96"},{"key":"1363_CR33","doi-asserted-by":"crossref","unstructured":"Iscen, A., Tolias, G., Avrithis, Y., & Chum, O. (2018). Mining on manifolds: Metric learning without labels.","DOI":"10.1109\/CVPR.2018.00797"},{"key":"1363_CR34","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.-Y. Y., Zhou, T., & Efros, A. A. (2017). Image-to-image translation with conditional adversarial networks. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 1125\u20131134).","DOI":"10.1109\/CVPR.2017.632"},{"key":"1363_CR35","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Douze, M., & Schmid, C. (2009). On the burstiness of visual elements. In IEEE conference on computer vision and pattern recognition workshops (CVPRW) (pp. 1169\u20131176).","DOI":"10.1109\/CVPR.2009.5206609"},{"key":"1363_CR36","doi-asserted-by":"crossref","unstructured":"Jiang, Q.-Y., & Li, W.-J. (2017). Deep cross-modal hashing. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3232\u20133240).","DOI":"10.1109\/CVPR.2017.348"},{"key":"1363_CR37","doi-asserted-by":"crossref","unstructured":"Johnson, J., Alahi, A., & Fei-Fei, L. (2016). Perceptual losses for real-time style transfer and super-resolution. In European conference on computer vision (pp. 694\u2013711). Springer.","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"1363_CR38","unstructured":"Johnson, J., Douze, M., & J\u00e9gou, H. (2017). Billion-scale similarity search with GPUs. https:\/\/ieeexplore.ieee.org\/abstract\/document\/8733051."},{"key":"1363_CR39","doi-asserted-by":"crossref","unstructured":"Kim, H. J., Dunn, E., & Frahm, J.-M. (2017). Learned contextual feature reweighting for image geo-localization. In IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.346"},{"key":"1363_CR40","doi-asserted-by":"crossref","unstructured":"Lai, H., Pan, Y., Liu, Y., & Yan, S. (2015). Simultaneous feature learning and hash coding with deep neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3270\u20133278).","DOI":"10.1109\/CVPR.2015.7298947"},{"issue":"8","key":"1363_CR41","doi-asserted-by":"publisher","first-page":"2030","DOI":"10.1109\/TPAMI.2017.2734890","volume":"40","author":"W Li","year":"2018","unstructured":"Li, W., Chen, L., Xu, D., & Van Gool, L. (2018). Visual recognition in RGB images and videos by learning from RGB-D data. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 40(8), 2030\u20132036.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"1363_CR42","doi-asserted-by":"crossref","unstructured":"Liu, L., Li, H., & Dai, Y. (2019). Stochastic attraction-repulsion embedding for large scale image localization. In proceedings of the IEEE international conference on computer vision (pp. 2570\u20132579).","DOI":"10.1109\/ICCV.2019.00266"},{"issue":"12","key":"1363_CR43","doi-asserted-by":"publisher","first-page":"3071","DOI":"10.1109\/TPAMI.2018.2868685","volume":"41","author":"M Long","year":"2018","unstructured":"Long, M., Cao, Y., Cao, Z., Wang, J., & Jordan, M. I. (2018). Transferable representation learning with deep adaptation networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(12), 3071\u20133085.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1363_CR44","doi-asserted-by":"crossref","unstructured":"Loo, S. Y., Amiri, A. J., Mashohor, S., Tang, S. H., & Zhang, H. (2019). CNN-SVO: Improving the mapping in semi-direct visual odometry using single-image depth prediction. In IEEE international conference on robotics and automation (ICRA) (Vol. 1).","DOI":"10.1109\/ICRA.2019.8794425"},{"issue":"1","key":"1363_CR45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TRO.2015.2496823","volume":"32","author":"S Lowry","year":"2016","unstructured":"Lowry, S., S\u00fcnderhauf, N., Newman, P., Leonard, J. J., Cox, D., Corke, P., et al. (2016). Visual place recognition: A survey. IEEE Transactions on Robotics (TRO), 32(1), 1\u201319.","journal-title":"IEEE Transactions on Robotics (TRO)"},{"key":"1363_CR46","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1177\/0278364916679498","volume":"36","author":"W Maddern","year":"2016","unstructured":"Maddern, W., Pascoe, G., Linegar, C., & Newman, P. (2016). 1 year, 1000 km: The Oxford RobotCar dataset. The International Journal of Robotics Research (IJRR), 36, 3\u201315.","journal-title":"The International Journal of Robotics Research (IJRR)"},{"key":"1363_CR47","doi-asserted-by":"crossref","unstructured":"Mahjourian, R., Wicke, M., & Angelova, A. (2018). Unsupervised learning of depth and ego-motion from monocular video using 3D geometric constraints. In IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00594"},{"key":"1363_CR48","doi-asserted-by":"crossref","unstructured":"Milford, M. J., & Wyeth, G. F. (2012). SeqSLAM: Visual route-based navigation for sunny summer days and stormy winter nights. In IEEE international conference on robotics and automation (ICRA) (pp. 1643\u20131649).","DOI":"10.1109\/ICRA.2012.6224623"},{"issue":"c","key":"1363_CR49","first-page":"1","volume":"7149","author":"B Morago","year":"2016","unstructured":"Morago, B., Bui, G., & Duan, Y. (2016). 2D matching using repetitive and salient features in architectural images. IEEE Transactions on Image Processing (ToIP), 7149(c), 1\u201312.","journal-title":"IEEE Transactions on Image Processing (ToIP)"},{"key":"1363_CR50","unstructured":"Mordan, T., Thome, N., Henaff, G., & Cord, M. (2018). Revisiting multi-task learning with rock: A deep residual auxiliary block for visual detection. In Advances in neural information processing systems (pp. 1310\u20131322)."},{"key":"1363_CR51","unstructured":"Muja, M., & Lowe, D. G. (2009). Fast approximate nearest neighbors with automatic algorithm configuration. In International conference on computer vision theory and applications (VISAPP) (pp. 1\u201310)."},{"issue":"2","key":"1363_CR52","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1109\/TRO.2017.2788045","volume":"34","author":"T Naseer","year":"2018","unstructured":"Naseer, T., Burgard, W., & Stachniss, C. (2018). Robust visual localization across seasons. IEEE Transactions on Robotics (TRO), 34(2), 289\u2013302.","journal-title":"IEEE Transactions on Robotics (TRO)"},{"key":"1363_CR53","doi-asserted-by":"crossref","unstructured":"Naseer, T., Oliveira, G. L., Brox, T., & Burgard, W. (2017). Semantics-aware visual localization under challenging perceptual conditions. In IEEE international conference on robotics and automation (ICRA) (pp. 2614\u20132620).","DOI":"10.1109\/ICRA.2017.7989305"},{"issue":"3","key":"1363_CR54","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1023\/A:1011139631724","volume":"42","author":"A Oliva","year":"2001","unstructured":"Oliva, A., & Torralba, A. (2001). Modeling the shape of the scene: A holistic representation of the spatial envelope. International Journal of Computer Vision (IJCV), 42(3), 145\u2013175.","journal-title":"International Journal of Computer Vision (IJCV)"},{"issue":"1","key":"1363_CR55","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1007\/s11263-016-0924-3","volume":"121","author":"M Paulin","year":"2017","unstructured":"Paulin, M., Mairal, J., Douze, M., Harchaoui, Z., Perronnin, F., & Schmid, C. (2017). Convolutional patch representations for image retrieval: An unsupervised approach. International Journal of Computer Vision (IJCV), 121(1), 149\u2013168.","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"1363_CR56","doi-asserted-by":"crossref","unstructured":"Philbin, J., Chum, O., Isard, M., Sivic, J., & Zisserman, A. (2007). Object retrieval with large vocabularies and fast spatial matching. In IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2007.383172"},{"key":"1363_CR57","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.patcog.2017.09.013","volume":"74","author":"N Piasco","year":"2018","unstructured":"Piasco, N., Sidib\u00e9, D., Demonceaux, C., & Gouet-Brunet, V. (2018). A survey on visual-based localization: On the benefit of heterogeneous data. Pattern Recognition, 74, 90\u2013109.","journal-title":"Pattern Recognition"},{"key":"1363_CR58","doi-asserted-by":"crossref","unstructured":"Piasco, N., Sidib\u00e9, D., Demonceaux, C., & Gouet-Brunet, V. (2019a). Geometric camera pose refinement with learned depth maps. In IEEE international conference on image processing (ICIP).","DOI":"10.1109\/ICIP.2019.8803014"},{"key":"1363_CR59","unstructured":"Piasco, N., Sidib\u00e9, D., Demonceaux, C., & Gouet-Brunet, V. (2019b). Perspective-n-learned-point: Pose estimation from relative depth. In British machine vision conference (BMVC)."},{"key":"1363_CR60","doi-asserted-by":"crossref","unstructured":"Piasco, N., Sidib\u00e9, D., Gouet-Brunet, V., & Demonceaux, C. (2019c). Learning scene geometry for visual localization in challenging conditions. In IEEE international conference on robotics and automation (ICRA).","DOI":"10.1109\/ICRA.2019.8794221"},{"key":"1363_CR61","doi-asserted-by":"crossref","unstructured":"Porav, H., Bruls, T., & Newman, P. (2019). I can see clearly now: Image restoration via de-raining. In IEEE international conference on robotics and automation (ICRA).","DOI":"10.1109\/ICRA.2019.8793486"},{"key":"1363_CR62","doi-asserted-by":"crossref","unstructured":"Porav, H., Maddern, W., & Newman, P. (2018). Adversarial training for adverse conditions: Robust metric localisation using appearance transfer. IEEE international conference on robotics and automation (ICRA).","DOI":"10.1109\/ICRA.2018.8462894"},{"key":"1363_CR63","unstructured":"Qi, C. R., Su, H., Mo, K., & Guibas, L. J. (2016). PointNet: Deep learning on point sets for 3D classification and segmentation. In IEEE conference on computer vision and pattern recognition (CVPR)."},{"key":"1363_CR64","doi-asserted-by":"crossref","unstructured":"Radenovi\u0107, F., Tolias, G., & Chum, O. (2016). CNN image retrieval learns from BoW: Unsupervised fine-tuning with hard examples. In European conference on computer vision (ECCV) (Vol. 9905, pp. 3\u201320).","DOI":"10.1007\/978-3-319-46448-0_1"},{"key":"1363_CR65","doi-asserted-by":"publisher","first-page":"1655","DOI":"10.1109\/TPAMI.2018.2846566","volume":"41","author":"F Radenovi\u0107","year":"2017","unstructured":"Radenovi\u0107, F., Tolias, G., & Chum, O. (2017). Fine-tuning CNN image retrieval with no human annotation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 41, 1655\u20131668.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"1363_CR66","doi-asserted-by":"crossref","unstructured":"Russell, B. C., Sivic, J., Ponce, J., & Dessales, H. (2011). Automatic alignment of paintings and photographs depicting a 3D scene. In IEEE international conference on computer vision workshops (ICCVW).","DOI":"10.1109\/ICCVW.2011.6130291"},{"key":"1363_CR67","doi-asserted-by":"crossref","unstructured":"Sarlin, P.-E., Cadena, C., Siegwart, R., & Dymczyk, M. (2019). From coarse to fine: Robust hierarchical localization at large scale. In IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.01300"},{"key":"1363_CR68","unstructured":"Sarlin, P.-E., Debraine, F., Dymczyk, M., Siegwart, R., & Cadena, C. (2018). Leveraging deep visual descriptors for hierarchical efficient localization. In Conference on robot learning (CoRL) (pp. 1\u201310)."},{"key":"1363_CR69","doi-asserted-by":"crossref","unstructured":"Sattler, T., Havlena, M., Schindler, K., & Pollefeys, M. (2016). Large-scale location recognition and the geometric burstiness problem. In IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2016.175"},{"key":"1363_CR70","doi-asserted-by":"crossref","unstructured":"Sattler, T., Maddern, W., Toft, C., Torii, A., Hammarstrand, L., Stenborg, E., et al. (2018a). Benchmarking 6DOF outdoor visual localization in changing conditions. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 8601\u20138610).","DOI":"10.1109\/CVPR.2018.00897"},{"key":"1363_CR71","doi-asserted-by":"crossref","unstructured":"Sattler, T., Maddern, W., Torii, A., Sivic, J., Pajdla, T., Pollefeys, M., & Okutomi, M. (2018b). Benchmarking 6DOF urban visual localization in changing conditions. In IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00897"},{"key":"1363_CR72","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J. L., Pollefeys, M., Geiger, A., & Sattler, T. (2018). Semantic visual localization. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00721"},{"key":"1363_CR73","unstructured":"Seymour, Z., Sikka, K., Chiu, H.-P., Samarasekera, S., & Kumar, R. (2019). Semantically-aware attentive neural embeddings for long-term 2D visual localization. In British Machine Vision Conference (BMVC)."},{"key":"1363_CR74","doi-asserted-by":"crossref","unstructured":"Sharmanska, V., Quadrianto, N., & Lampert, C. H. (2013). Learning to rank using privileged information. In Proceedings of the IEEE international conference on computer vision (pp. 825\u2013832).","DOI":"10.1109\/ICCV.2013.107"},{"key":"1363_CR75","doi-asserted-by":"crossref","unstructured":"Shotton, J., Glocker, B., Zach, C., Izadi, S., Criminisi, A., & Fitzgibbon, A. (2013). Scene coordinate regression forests for camera relocalization in RGB-D images. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 2930\u20132937).","DOI":"10.1109\/CVPR.2013.377"},{"key":"1363_CR76","doi-asserted-by":"crossref","unstructured":"Sizikova, E., Singh, V. K., Georgescu, B., Halber, M., Ma, K., & Chen, T. (2016). Enhancing place recognition using joint intensity\u2014depth analysis and synthetic data. In European conference on computer vision workshops (ECCVW) (pp. 1\u20138).","DOI":"10.1007\/978-3-319-49409-8_74"},{"key":"1363_CR77","doi-asserted-by":"crossref","unstructured":"Stenborg, E., Toft, C., & Hammarstrand, L. (2018). Long-term visual localization using semantically segmented images. In 2018 IEEE International Conference on Robotics and Automation (ICRA) (pp. 6484\u20136490). IEEE.","DOI":"10.1109\/ICRA.2018.8463150"},{"key":"1363_CR78","doi-asserted-by":"crossref","unstructured":"S\u00fcnderhauf, N., Shirazi, S., Jacobson, A., Dayoub, F., Pepperell, E., Upcroft, B., et al. (2015). Place recognition with ConvNet landmarks: Viewpoint-robust, condition-robust, training-free. In Robotics science and systems (RSS).","DOI":"10.15607\/RSS.2015.XI.022"},{"key":"1363_CR79","doi-asserted-by":"crossref","unstructured":"Tateno, K., Tombari, F., Laina, I., & Navab, N. (2017). CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction. In IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.695"},{"key":"1363_CR80","doi-asserted-by":"crossref","unstructured":"Toft, C., Stenborg, E., Hammarstrand, L., Brynte, L., Pollefeys, M., Sattler, T., & Kahl, F. (2018). Semantic match consistency for long-term visual localization. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-01216-8_24"},{"key":"1363_CR81","doi-asserted-by":"crossref","unstructured":"Torii, A., Arandjelovi\u0107, R., Sivic, J., Okutomi, M., & Pajdla, T. (2015). 24\/7 place recognition by view synthesis. In IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2015.7298790"},{"key":"1363_CR82","first-page":"2346","volume":"37","author":"A Torii","year":"2013","unstructured":"Torii, A., Sivic, J., Okutomi, M., & Pajdla, T. (2013). Visual place recognition with repetitive structures. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 37, 2346\u20132359.","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"1363_CR83","doi-asserted-by":"crossref","unstructured":"Tzeng, E., Hoffman, J., Saenko, K., & Darrell, T. (2017). Adversarial discriminative domain adaptation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7167\u20137176).","DOI":"10.1109\/CVPR.2017.316"},{"key":"1363_CR84","doi-asserted-by":"crossref","unstructured":"Uy, M. A. & Lee, G. H. (2018). PointNetVLAD: Deep point cloud based retrieval for large-scale place recognition. In IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00470"},{"issue":"5\u20136","key":"1363_CR85","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1016\/j.neunet.2009.06.042","volume":"22","author":"V Vapnik","year":"2009","unstructured":"Vapnik, V., & Vashist, A. (2009). A new learning paradigm: Learning using privileged information. Neural Networks, 22(5\u20136), 544\u2013557.","journal-title":"Neural Networks"},{"key":"1363_CR86","doi-asserted-by":"crossref","unstructured":"Xu, D., Ouyang, W., Ricci, E., Wang, X., & Sebe, N. (2017). Detection, learning cross-modal deep representations for robust pedestrian. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 5363\u20135371).","DOI":"10.1109\/CVPR.2017.451"},{"key":"1363_CR87","doi-asserted-by":"crossref","unstructured":"Zamir, A. R. & Shah, M. (2010). Accurate image localization based on google maps street view. In European conference on computer vision (ECCV), LNCS (Vol. 6314, pp. 255\u2013268).","DOI":"10.1007\/978-3-642-15561-1_19"},{"issue":"8","key":"1363_CR88","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. (2014). Image geo-localization based on multiplenearest neighbor feature matching using generalized graphs. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 36(8), 1546\u20131558.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"1363_CR89","unstructured":"Zwald, L., & Lambert-Lacroix, S. (2012). The berhu penalty and the grouped effect. arXiv preprint arXiv:1207.6868."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01363-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-020-01363-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01363-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T15:29:12Z","timestamp":1668094152000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-020-01363-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,28]]},"references-count":89,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["1363"],"URL":"https:\/\/doi.org\/10.1007\/s11263-020-01363-6","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8,28]]},"assertion":[{"value":"23 July 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 July 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}