{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T11:38:18Z","timestamp":1779881898333,"version":"3.53.1"},"reference-count":266,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100010663","name":"H2020 European Research Council","doi-asserted-by":"publisher","award":["637076 (project RoboExNovo)"],"award-info":[{"award-number":["637076 (project RoboExNovo)"]}],"id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3054937","type":"journal-article","created":{"date-parts":[[2021,1,27]],"date-time":"2021-01-27T20:48:43Z","timestamp":1611780523000},"page":"19516-19547","source":"Crossref","is-referenced-by-count":175,"title":["A Survey on Deep Visual Place Recognition"],"prefix":"10.1109","volume":"9","author":[{"given":"Carlo","family":"Masone","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Barbara","family":"Caputo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2859916"},{"key":"ref172","first-page":"724","article-title":"Evaluating local features for day-night matching","author":"zhou","year":"2016","journal-title":"Proc IEEE Int Conf Comput Vis (ICCV) Workshops"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.137"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299135"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907067"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139877"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206608"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16865-4_12"},{"key":"ref168","first-page":"2918","article-title":"Adaptive-attentive geolocalization from few queries: A hybrid approach","author":"moreno berton","year":"2021","journal-title":"Proc IEEE\/CVF Winter Conf Appl Comput Vis (WACV)"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref39","first-page":"774","article-title":"Negative evidences and co-occurences in image retrieval: The benefit of PCA and whitening","author":"j\u00e3gou","year":"2012","journal-title":"Proc ECCV"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00525"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"ref32","author":"witten","year":"1999","journal-title":"Managing Gigabytes"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2787132"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0810-4"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.417"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540009"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.207"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919839761"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2899049"},{"key":"ref185","first-page":"1","article-title":"Semantically-aware attentive neural embeddings for 2D long-term visual localization","author":"seymour","year":"2019","journal-title":"British Conference on Machine Vision (BMVC)"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2698524"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989305"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2801879"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353986"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794221"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00012"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197529"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21585"},{"key":"ref27","first-page":"1170","article-title":"Predicting good features for image geo-localization using per-bundle VLAD","author":"jin kim","year":"2015","journal-title":"Proc IEEE Int Conf Comput Vis (ICCV)"},{"key":"ref179","first-page":"487","article-title":"Learning deep features for scene recognition using places database","author":"zhou","year":"2014","journal-title":"Neural Information Processing Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00721"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587784"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873985"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2009.V.039"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126328"},{"key":"ref23","first-page":"748","article-title":"Avoiding confusing features in place recognition","author":"knopp","year":"2010","journal-title":"Proc ECCV"},{"key":"ref26","first-page":"41","author":"hays","year":"2015","journal-title":"Large-scale image geolocalization"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913499193"},{"key":"ref50","first-page":"647","article-title":"Decaf: A deep convolutional activation feature for generic visual recognition","author":"donahue","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301270"},{"key":"ref154","first-page":"1","article-title":"Reference pose generation for long-term visual localization via learned features and view synthesis","volume":"4","author":"zhang","year":"2020","journal-title":"Int J Comput Vis"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.76"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16817-3_13"},{"key":"ref155","first-page":"2013","article-title":"Are we there yet? Challenging SeqSLAM on a 3000 km journey across all four seasons","author":"s\u00fcnderhauf","year":"2013","journal-title":"Proc Workshop Long-Term Autonomy Int Conf Robot Automat (ICRA)"},{"key":"ref150","article-title":"Levelling the playing field: A comprehensive comparison of visual place recognition approaches under changing conditions","author":"zaffar","year":"2019","journal-title":"arXiv 1903 09107"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2011.5940504"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00897"},{"key":"ref146","article-title":"Learning global and local consistent representations for unsupervised image retrieval via deep graph diffusion networks","author":"dou","year":"2020","journal-title":"arXiv 2001 01284"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206609"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460786"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759662"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/2671188.2749289"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/2671188.2749300"},{"key":"ref57","first-page":"584","article-title":"Neural codes for image retrieval","author":"babenko","year":"2014","journal-title":"Proc ECCV"},{"key":"ref56","first-page":"392","article-title":"Multi-scale orderless pooling of deep convolutional activation features","author":"gong","year":"2014","journal-title":"Proc ECCV"},{"key":"ref55","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref53","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2014","journal-title":"Proc ECCV"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.222"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794383"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2018.8516500"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2901984"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2956352"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202131"},{"key":"ref162","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc ECCV"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref160","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.09.013"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2496823"},{"key":"ref6","first-page":"176","article-title":"A survey on local invariant features","volume":"3","author":"tuytelaars","year":"2008","journal-title":"Found Trends Comput Graph Vis"},{"key":"ref5","article-title":"Visual place recognition: A survey from deep learning perspective","volume":"28","author":"zhang","year":"2020","journal-title":"Pattern Recognit"},{"key":"ref8","first-page":"128","article-title":"An affine invariant interest point detector","author":"mikolajczyk","year":"2002","journal-title":"Proc ECCV"},{"key":"ref159","first-page":"487","article-title":"Visual place recognition using landmark distribution descriptors","author":"panphattarasap","year":"2017","journal-title":"Proc ACCV"},{"key":"ref7","first-page":"524","article-title":"A Bayesian hierarchical model for learning natural scene categories","volume":"2","author":"li","year":"2005","journal-title":"Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2004.02.006"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2015.XI.022"},{"key":"ref46","first-page":"1051","article-title":"Visual loop closure detection with a compact image descriptor","author":"liu","year":"2012","journal-title":"Proc IEEE\/RSJ Int Conf Intell Robots Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6224623"},{"key":"ref48","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Neural Information Processing Systems"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.127"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587633"},{"key":"ref41","first-page":"23","article-title":"Building the gist of a scene: The role of global image features in recognition","volume":"155","author":"oliva","year":"2006","journal-title":"The Perceptions of Vision"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6094921"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2009.5457552"},{"key":"ref73","first-page":"1","article-title":"Particular object retrieval with integral max-pooling of CNN activations","author":"tolias","year":"2016","journal-title":"Proc 4th Int Conf Learn Represent (ICLR)"},{"key":"ref72","article-title":"Deep convolutional features for image based retrieval and scene categorization","author":"mousavian","year":"2015","journal-title":"arXiv 1509 06033"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.3169\/mta.4.251"},{"key":"ref70","first-page":"1269","article-title":"Aggregating deep convolutional features for image retrieval","author":"babenko","year":"2015","journal-title":"Proc IEEE\/CVF Int Conf Comput Vis (ICCV)"},{"key":"ref76","first-page":"685","article-title":"Cross-dimensional weighting for aggregated deep convolutional features","author":"kalantidis","year":"2016","journal-title":"Proc IEEE Int Conf Comput Vis (ICCV) Workshops"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2846566"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1016-8"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2889030"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408871"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248035"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654948"},{"key":"ref62","article-title":"Training a convolutional neural network for appearance-invariant place recognition","author":"gomez-ojeda","year":"2015","journal-title":"arXiv 1505 07428"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICInfA.2015.7279659"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.19"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912061"},{"key":"ref66","first-page":"4826","article-title":"Working hard to know your neighbor margins: Local descriptor learning loss","author":"mishchuk","year":"2017","journal-title":"Neural Information Processing Systems"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_43"},{"key":"ref68","article-title":"Siamese network of deep Fisher-vector descriptors for image retrieval","author":"ong","year":"2017","journal-title":"arXiv 1702 00338"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2711011"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462894"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794387"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2898427"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00295"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2967324"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00941"},{"key":"ref95","first-page":"253","article-title":"SOLAR: Second-order loss and attention for image retrieval","author":"ng","year":"2020","journal-title":"Proc ECCV"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01127"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989366"},{"key":"ref93","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1007\/978-3-319-24261-3_7","article-title":"Deep metric learning using triplet network","author":"hoffer","year":"2015","journal-title":"Similarity-Based Pattern Recognition"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00979"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240602"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2788045"},{"key":"ref91","first-page":"3251","article-title":"Learned contextual feature reweighting for image geo-localization","author":"jin kim","year":"2017","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.180"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref99","article-title":"Fracking deep convolutional image descriptors","author":"simo-serra","year":"2014","journal-title":"arXiv 1412 6537"},{"key":"ref96","first-page":"284","article-title":"Repeatability is not enough: Learning affine regions via discriminability","author":"mishkin","year":"2018","journal-title":"Proc ECCV"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3043875"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00521"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.374"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240525"},{"key":"ref83","first-page":"3","article-title":"CNN image retrieval learns from BoW: Unsupervised fine-tuning with hard examples","author":"radenovi?","year":"2016","journal-title":"Proc ECCV"},{"key":"ref80","first-page":"241","article-title":"Deep image retrieval: Learning global representations for image search","author":"gordo","year":"2016","journal-title":"Proc ECCV"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1137-8"},{"key":"ref86","first-page":"8034","article-title":"Visual place recognition via robust $\\ell_{2}$\n-norm distance based holism and landmark integration","author":"liu","year":"2019","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref87","first-page":"6501","article-title":"Learning integrated holism-landmark representations for long-term loop closure detection","author":"han","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00514"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1016\/j.nicl.2017.12.022"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14267-3"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.156"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461081"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793752"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00122"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968047"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1145\/2001269.2001293"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299148"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00181"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0107-3"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995464"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.104"},{"key":"ref212","first-page":"828","article-title":"On sampling focal length values to solve the absolute pose problem","author":"sattler","year":"2014","journal-title":"Proc ECCV"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2895826"},{"key":"ref214","article-title":"Are large-scale 3D models really necessary for accurate visual localization?","author":"torii","year":"2019","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.336"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.694"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.75"},{"key":"ref218","first-page":"6234","article-title":"LF-net: Learning local features from images","author":"ono","year":"2018","journal-title":"Neural Information Processing Systems"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.3390\/rs10081243"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2017.2677964"},{"key":"ref222","article-title":"Are state-of-the-art visual place recognition techniques any good for aerial robotics?","author":"zaffar","year":"2019","journal-title":"arXiv 1904 07967"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.451"},{"key":"ref229","first-page":"1","article-title":"Convolutional neural network-based place recognition","author":"chen","year":"2014","journal-title":"Proc 16th Australas Conf Robot Autom"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6943207"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487688"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2986044"},{"key":"ref225","first-page":"152","article-title":"Radar dataset for robust localization and mapping in urban environment","author":"park","year":"2019","journal-title":"Proc ICRA"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00292"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00470"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995601"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408891"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2361319"},{"key":"ref124","first-page":"5153","article-title":"Pairwise geometric matching for large-scale object retrieval","author":"li","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00598"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.022"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00965"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.221"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00828"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01192"},{"key":"ref132","first-page":"812","article-title":"Enhancing RANSAC by generalized model optimization","volume":"2","author":"chum","year":"2004","journal-title":"Proc ACCV"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2017.07.015"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1007\/s00422-019-00806-9"},{"key":"ref230","article-title":"Condition-invariant multi-view place recognition","author":"facil","year":"2019","journal-title":"arXiv 1902 09516"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1307183"},{"key":"ref239","first-page":"563","article-title":"Geolocation estimation of photos using a hierarchical model and scene classification","author":"muller-budack","year":"2018","journal-title":"Proc ECCV"},{"key":"ref238","first-page":"536","article-title":"CPlaNet: Enhancing image geolocalization by combinatorial partitioning of maps","author":"seo","year":"2018","journal-title":"Proc ECCV"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00614"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2869640"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.286"},{"key":"ref236","first-page":"37","article-title":"Planet-photo geolocation with convolutional neural networks","author":"weyand","year":"2016","journal-title":"Proc ECCV"},{"key":"ref136","article-title":"Large-scale landmark retrieval\/recognition under a noisy and diverse dataset","author":"ozaki","year":"2019","journal-title":"arXiv 1906 04087"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.3390\/rs11050493"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/ECMR.2019.8870948"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.174"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.105"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00796"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2828815"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019087"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2984718"},{"key":"ref144","first-page":"1556","article-title":"Guided similarity separation for image retrieval","author":"liu","year":"2019","journal-title":"Neural Information Processing Systems"},{"key":"ref1","first-page":"1697","article-title":"CityLearn: Diverse real-world environments for sample-efficient navigation policy learning","author":"chancan","year":"2020","journal-title":"Proc IEEE Int Conf Robot Autom (ICRA)"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01066"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509547"},{"key":"ref242","first-page":"791","article-title":"Location recognition using prioritized feature matching","author":"li","year":"2010","journal-title":"Proc ECCV"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995610"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.377"},{"key":"ref240","first-page":"1","article-title":"Unaided stereo vision based pose estimation","author":"warren","year":"2010","journal-title":"Proc Australas Conf Robot Autom"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916679498"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915614638"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.02.002"},{"key":"ref245","first-page":"2564","article-title":"Robust visual robot localization across seasons using network flows","author":"naseer","year":"2014","journal-title":"Proc 28th AAAI Conf Artif Intell"},{"key":"ref249","doi-asserted-by":"crossref","first-page":"324","DOI":"10.1007\/978-3-030-29888-3_26","article-title":"Place recognition in gardens by learning visual representations: Data set and benchmark analysis","author":"leyva-vallina","year":"2019","journal-title":"Computer Analysis of Images and Patterns"},{"key":"ref109","first-page":"331","article-title":"Fast approximate nearest neighbors with automatic algorithm configuration","volume":"2","author":"muja","year":"2009","journal-title":"Proc Int Conf Comput Vis Theory Appl"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1145\/502807.502809"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.032"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01300"},{"key":"ref105","first-page":"456","article-title":"Leveraging deep visual descriptors for hierarchical efficient localization","volume":"87","author":"sarlin","year":"2018","journal-title":"Proc The 2nd Conf Robot Learn"},{"key":"ref104","first-page":"1","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"Proc NIPS Deep Learn Represent Learn Workshop"},{"key":"ref103","first-page":"12 405","article-title":"R2d2: Reliable and repeatable detector and descriptor","author":"revaud","year":"2019","journal-title":"Adv in Neural Info Proc Syst"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00196"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699960"},{"key":"ref112","first-page":"537","article-title":"An efficient approximate kNN graph method for diffusion on image retrieval","author":"magliani","year":"2019","journal-title":"Image Process and analysis"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CRV.2012.60"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2910150"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00265"},{"key":"ref254","author":"kesten","year":"2019","journal-title":"Lyft Level 5 Perception Dataset"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2926463"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00270"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00048"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00895"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref259","article-title":"A2D2: Audi autonomous driving dataset","author":"geyer","year":"2020","journal-title":"arXiv 2004 06320"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790410"},{"key":"ref258","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1016\/j.cviu.2007.09.014","article-title":"Speeded-up robust features (SURF)","volume":"110","author":"bay","year":"2008","journal-title":"Comput Vis Image Understand"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.222"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299145"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2671188.2749379"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00962"},{"key":"ref118","first-page":"304","article-title":"Hamming embedding and weak geometric consistency for large scale image search","author":"j\u00e3gou","year":"2008","journal-title":"Proc ECCV"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/3DPVT.2006.80"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2409868"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383150"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/0278364908090961"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00752"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2299799"},{"key":"ref113","article-title":"Billion-scale similarity search with GPUs","author":"johnson","year":"2019","journal-title":"IEEE Trans Big Data"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383172"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1016\/0306-4573(88)90021-0"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2667665"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587635"},{"key":"ref123","article-title":"Local visual Query expansion: Exploiting an image collection to refine local descriptors","author":"tolias","year":"2013"},{"key":"ref260","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.352"},{"key":"ref262","first-page":"102","article-title":"Playing for data: Ground truth from computer games","volume":"9906","author":"richter","year":"2016","journal-title":"Proc ECCV"},{"key":"ref263","first-page":"4340","article-title":"Virtual worlds as proxy for multi-object tracking analysis","author":"gaidon","year":"2016","journal-title":"Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref264","article-title":"Virtual KITTI 2","author":"cabon","year":"2020","journal-title":"arXiv 2001 10773"},{"key":"ref265","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3009075"},{"key":"ref266","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206505"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09336674.pdf?arnumber=9336674","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T12:49:04Z","timestamp":1643201344000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9336674\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":266,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3054937","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}