City-scale location recognition Avoiding confusing features in place recognition City-scale landmark identification on mobile devices Fast image-based localization using direct 2D?to?3D matching Image retrieval for image-based localization revisited Learning and calibrating per-location classifiers for visual place recognition Graph-based discriminative learning for location recognition Visual place recognition with repetitive structures DisLocation: Scalable descriptor distinctiveness for location recognition, Proc. CVPR Proc. ECCV Proc. CVPR Proc. ICCV Proc. BMVC. Proc. CVPR Proc. CVPR, 2013. [9] R. Arandjelovi´cArandjelovi´c and A. Zisserman Proc. ACCV, pp.319-336, 2007. ,
24/7 place recognition by view synthesis, Proc. CVPR, 2015. ,
DOI : 10.1109/tpami.2017.2667665
URL : https://hal.archives-ouvertes.fr/hal-01147212
Hyperpoints and Fine Vocabularies for Large-Scale Location Recognition, 2015 IEEE International Conference on Computer Vision (ICCV), 2015. ,
DOI : 10.1109/ICCV.2015.243
FAB-MAP: Probabilistic Localization and Mapping in the Space of Appearance, The International Journal of Robotics Research, vol.27, issue.6, 2008. ,
DOI : 10.1177/0278364908090961
Shady dealings: Robust, long-term visual localisation using illumination invariance, 2014 IEEE International Conference on Robotics and Automation (ICRA), 2014. ,
DOI : 10.1109/ICRA.2014.6906961
Towards robust night and day place recognition using visible and thermal imaging, Proc. Intl. Conf. on Robotics and Automation, 2014. ,
Place Recognition with ConvNet Landmarks: Viewpoint-Robust, Condition-Robust, Training-Free, Robotics: Science and Systems XI, 2015. ,
DOI : 10.15607/RSS.2015.XI.022
Scalable 6-DOF Localization on Mobile Devices, Proc. ECCV, 2014. ,
DOI : 10.1007/978-3-319-10605-2_18
URL : http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.667.8896
Painting-to-3D model alignment via discriminative visual elements, ACM Transactions on Graphics, vol.33, issue.2, p.14, 2014. ,
DOI : 10.1561/0600000009
URL : https://hal.archives-ouvertes.fr/hal-00863615
Local Invariant Feature Detectors: A Survey, Foundations and Trends?? in Computer Graphics and Vision, vol.3, issue.3, pp.177-280, 2008. ,
DOI : 10.1561/0600000017
URL : http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.377.3635
Distinctive Image Features from Scale-Invariant Keypoints, International Journal of Computer Vision, vol.60, issue.2, pp.91-110, 2004. ,
DOI : 10.1023/B:VISI.0000029664.99615.94
URL : http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.14.4931
Video Google: a text retrieval approach to object matching in videos, Proceedings Ninth IEEE International Conference on Computer Vision, pp.1470-1477, 2003. ,
DOI : 10.1109/ICCV.2003.1238663
Object retrieval with large vocabularies and fast spatial matching, 2007 IEEE Conference on Computer Vision and Pattern Recognition, 2007. ,
DOI : 10.1109/CVPR.2007.383172
All about VLAD, Proc. CVPR, 2013. ,
Aggregating local descriptors into a compact image representation, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010. ,
DOI : 10.1109/CVPR.2010.5540039
Large-scale image retrieval with compressed Fisher vectors, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010. ,
DOI : 10.1109/CVPR.2010.5540009
Aggregating Local Image Descriptors into Compact Codes, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.34, issue.9, 2012. ,
DOI : 10.1109/TPAMI.2011.235
Product Quantization for Nearest Neighbor Search, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.33, issue.1, 2011. ,
DOI : 10.1109/TPAMI.2010.57
Worldwide pose estimation using 3D point clouds, Proc. ECCV, 2012. ,
DOI : 10.1007/978-3-642-33718-5_2
URL : http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.362.4910
Backpropagation Applied to Handwritten Zip Code Recognition, Neural Computation, vol.1, issue.4, pp.541-551, 1989. ,
DOI : 10.1007/BF00133697
Gradient-based learning applied to document recognition, Proceedings of the IEEE, vol.86, issue.11, pp.2278-2324, 1998. ,
DOI : 10.1109/5.726791
URL : http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.138.1115
ImageNet classification with deep convolutional neural networks, NIPS, pp.1106-1114, 2012. ,
DOI : 10.1162/neco.2009.10-08-881
URL : http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.299.205
Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks, 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014. ,
DOI : 10.1109/CVPR.2014.222
URL : https://hal.archives-ouvertes.fr/hal-00911179
Very deep convolutional networks for large-scale image recognition, Proc. ICLR, 2015. ,
Going deeper with convolutions, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014. ,
DOI : 10.1109/CVPR.2015.7298594
URL : http://arxiv.org/abs/1409.4842
Learning deep features for scene recognition using places database, NIPS, 2014. ,
DOI : 10.1109/tpami.2017.2723009
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation, 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014. ,
DOI : 10.1109/CVPR.2014.81
URL : http://arxiv.org/abs/1311.2524
DeCAF: A deep convolutional activation feature for generic visual recognition, 1310. ,
OverFeat: Integrated recognition, localization and detection using convolutional networks, 1312. ,
Visualizing and Understanding Convolutional Networks, Proc. ECCV, 2014. ,
DOI : 10.1007/978-3-319-10590-1_53
URL : http://arxiv.org/abs/1311.2901
Factors of transferability from a generic ConvNet representation, 1406. ,
Aggregating local deep features for image retrieval, Proc. ICCV, 2015. ,
Multi-scale Orderless Pooling of Deep Convolutional Activation Features, Proc. ECCV, 2014. ,
DOI : 10.1007/978-3-319-10584-0_26
URL : http://arxiv.org/abs/1403.1840
CNN Features Off-the-Shelf: An Astounding Baseline for Recognition, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 1403. ,
DOI : 10.1109/CVPRW.2014.131
URL : http://arxiv.org/abs/1403.6382
A baseline for visual instance retrieval with deep convolutional networks, Proc. ICLR, 2015. ,
DOI : 10.3169/mta.4.251
Particular object retrieval with integral max-pooling of CNN activations, Proc. ICLR, 2016. ,
Cross-Dimensional Weighting for Aggregated Deep Convolutional Features, ECCV workshop on Web-scale Vision and Social Media, 2016. ,
DOI : 10.1016/j.cviu.2013.12.002
URL : http://arxiv.org/abs/1512.04065
Bags of Local Convolutional Features for Scalable Instance Search, Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval, ICMR '16, 2016. ,
DOI : 10.1145/2324796.2324856
Three things everyone should know to improve object retrieval, Proc. CVPR, 2012. ,
Negative evidences and co-occurrences in image retrieval: the benefit of PCA and whitening, Proc. ECCV, 2012. ,
Total Recall: Automatic Query Expansion with a Generative Feature Model for Object Retrieval, 2007 IEEE 11th International Conference on Computer Vision, 2007. ,
DOI : 10.1109/ICCV.2007.4408891
Total recall II: Query expansion revisited, CVPR 2011, 2011. ,
DOI : 10.1109/CVPR.2011.5995601
Revisiting the VLAD image representation, Proceedings of the 21st ACM international conference on Multimedia, MM '13, 2013. ,
DOI : 10.1145/2502081.2502171
URL : https://hal.archives-ouvertes.fr/hal-00840653
Hamming Embedding and Weak Geometric Consistency for Large Scale Image Search, Proc. ECCV, pp.304-317, 2008. ,
DOI : 10.1007/978-3-540-88682-2_24
Triangulation embedding and democratic aggregation for image search Learning a fine vocabulary, Proc. CVPR Proc. ECCV, 2010. ,
Fisher kernels on visual vocabularies for image categorization Lost in quantization: Improving particular object retrieval in large scale image databases, Proc. CVPR Proc. CVPR, 2007. ,
Descriptor Learning Using Convex Optimisation, Proc. ECCV, 2012. ,
DOI : 10.1007/978-3-642-33718-5_18
URL : http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.370.9634
To Aggregate or Not to aggregate: Selective Match Kernels for Image Search, 2013 IEEE International Conference on Computer Vision, 2013. ,
DOI : 10.1109/ICCV.2013.177
URL : https://hal.archives-ouvertes.fr/hal-00864684
Visual query expansion with or without geometry: Refining local descriptors by feature aggregation, Pattern Recognition, vol.47, issue.10, 2014. ,
DOI : 10.1016/j.patcog.2014.04.007
URL : https://hal.archives-ouvertes.fr/hal-00971267
Better matching with fewer features: The selection of useful features in large database recognition problems, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops, 2009. ,
DOI : 10.1109/ICCVW.2009.5457541
A contextual dissimilarity measure for accurate and efficient image search, 2007 IEEE Conference on Computer Vision and Pattern Recognition, 2007. ,
DOI : 10.1109/CVPR.2007.382970
Hello neighbor: Accurate object retrieval with k-reciprocal nearest neighbors, CVPR 2011, 2011. ,
DOI : 10.1109/CVPR.2011.5995373
Query Adaptive Similarity for Large Scale Object Retrieval, 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013. ,
DOI : 10.1109/CVPR.2013.211
Exemplar SVMs as visual feature encoders, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015. ,
DOI : 10.1109/CVPR.2015.7298924
Learning to rank bagof-word histograms for large-scale object retrieval, Proc. BMVC, 2014. ,
DOI : 10.5244/c.28.43
Picking the best DAISY, 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp.178-185, 2009. ,
DOI : 10.1109/CVPR.2009.5206839
Descriptor Learning for Efficient Retrieval, Proc. ECCV, 2010. ,
DOI : 10.1007/978-3-642-15558-1_49
URL : http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.172.6458
Feature Tracking for Wide-Baseline Image Retrieval, Proc. ECCV, 2010. ,
DOI : 10.1007/978-3-642-15555-0_23
URL : http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.179.1610
Leveraging Structure from Motion to Learn Discriminative Codebooks for Scalable Landmark Classification, 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013. ,
DOI : 10.1109/CVPR.2013.104
URL : http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.367.5102
Quantized kernel learning for feature matching, NIPS, 2014. ,
Fracking deep convolutional image descriptors, 1412. ,
DOI : 10.1109/iccv.2015.22
URL : http://upcommons.upc.edu/bitstream/2117/84259/1/1694-Discriminative-Learning-of-Deep-Convolutional-Feature-Point-Descriptors%281%29.pdf
Local Convolutional Features with Unsupervised Training for Image Retrieval, 2015 IEEE International Conference on Computer Vision (ICCV), 2015. ,
DOI : 10.1109/ICCV.2015.19
URL : https://hal.archives-ouvertes.fr/hal-01207966
LIFT: Learned Invariant Feature Transform, Proc. ECCV, 2016. ,
DOI : 10.1109/TPAMI.2009.167
URL : http://arxiv.org/abs/1603.09114
Neural Codes for Image Retrieval, Proc. ECCV, 2014. ,
DOI : 10.1007/978-3-319-10590-1_38
URL : http://arxiv.org/abs/1404.1777
Deep Image Retrieval: Learning Global Representations for Image Search, Proc. ECCV, 2016. ,
DOI : 10.1109/CVPR.2014.180
URL : http://arxiv.org/abs/1604.01325
CNN image retrieval learns from BoW: Unsupervised fine-tuning with hard examples, Proc. ECCV, 2016. ,
NetVLAD: CNN architecture for weakly supervised place recognition, Proc. CVPR, 2016. ,
PlaNet - Photo Geolocation with Convolutional Neural Networks, Proc. ECCV, 2016. ,
DOI : 10.1145/1631272.1631468
URL : http://arxiv.org/pdf/1602.05314
PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization, 2015 IEEE International Conference on Computer Vision (ICCV), 2015. ,
DOI : 10.1109/ICCV.2015.336
URL : http://arxiv.org/abs/1505.07427
Learning deep representations for ground-to-aerial geolocalization, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015. ,
DOI : 10.1109/CVPR.2015.7299135
Deep filter banks for texture recognition and segmentation, Proc. CVPR, 2015. ,
DOI : 10.1109/cvpr.2015.7299007
URL : https://hal.archives-ouvertes.fr/hal-01263622
Visual categorization with bags of keypoints, Workshop on Statistical Learning in Computer Vision, ECCV, pp.1-22, 2004. ,
Deep Fisher Kernels -- End to End Learning of the Fisher Kernel GMM Parameters, 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014. ,
DOI : 10.1109/CVPR.2014.182
Deep Fisher networks for large-scale image classification, NIPS, 2013. ,
Bilinear CNN Models for Fine-Grained Visual Recognition, 2015 IEEE International Conference on Computer Vision (ICCV), 2015. ,
DOI : 10.1109/ICCV.2015.170
URL : http://arxiv.org/abs/1504.07889
Learning a distance metric from relative comparisons, NIPS, 2004. ,
Distance metric learning for large margin nearest neighbor classification, NIPS, 2006. ,
Learning Fine-Grained Image Similarity with Deep Ranking, 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014. ,
DOI : 10.1109/CVPR.2014.180
URL : http://arxiv.org/abs/1404.4661
FaceNet: A unified embedding for face recognition and clustering, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015. ,
DOI : 10.1109/CVPR.2015.7298682
URL : http://arxiv.org/abs/1503.03832
A review of multi-instance learning assumptions, The Knowledge Engineering Review, vol.2, issue.01, pp.1-25, 2010. ,
DOI : 10.1007/978-1-4757-4134-6
Deep multi-instance transfer learning, p.3128, 1411. ,
Multiple instance boosting for object detection, NIPS, 2005. ,
Neural network-based face detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.20, issue.1, pp.23-38, 1998. ,
DOI : 10.1109/34.655647
URL : http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.110.5546
Histograms of Oriented Gradients for Human Detection, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), pp.886-893, 2005. ,
DOI : 10.1109/CVPR.2005.177
URL : https://hal.archives-ouvertes.fr/inria-00548512
Object Detection with Discriminatively Trained Part-Based Models, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.32, issue.9, 2010. ,
DOI : 10.1109/TPAMI.2009.167
Self-improving reactive agents based on reinforcement learning, planning and teaching, Machine learning, pp.293-321, 1992. ,
DOI : 10.1007/bf00992699
URL : http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.75.7884
Human-level control through deep reinforcement learning, Nature, vol.101, issue.7540, pp.529-533, 2015. ,
DOI : 10.1016/S0004-3702(98)00023-X
Asynchronous methods for deep reinforcement learning, Proc. ICML, 2016. ,
streetget -a small python package for building place recognition datasets, 2015. ,
Matconvnet ? convolutional neural networks for matlab, Proc. ACMM, 2015. ,
ImageNet: A large-scale hierarchical image database, Proc. CVPR, 2009. ,
Learned contextual feature reweighting for image geo-localization, Proc. CVPR, 2017. ,
Leveraging category-level labels for instance-level image retrieval, 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012. ,
DOI : 10.1109/CVPR.2012.6248035
Deep visual-semantic alignments for generating image descriptions, Proc. CVPR, pp.2015-2016 ,
DOI : 10.1109/tpami.2016.2598339
URL : http://arxiv.org/abs/1412.2306
We compare our best trained network (VGG-16, f V LAD ), and the corresponding off-the-shelf network (whitening learnt on Pittsburgh, on standard image and object retrieval benchmarks, while varying the dimensionality (Dim.) of the image representation ,
Oxford 5k Paris 6k Holidays full crop full crop orig rot NetVLAD off-shelf 16 28 ,
Factors of transferability from a generic ConvNet representation, 1406. ,
Aggregating local deep features for image retrieval, Proc. ICCV, 2015. ,
Multi-scale Orderless Pooling of Deep Convolutional Activation Features, Proc. ECCV, 2014. ,
DOI : 10.1007/978-3-319-10584-0_26
URL : http://arxiv.org/abs/1403.1840
CNN Features Off-the-Shelf: An Astounding Baseline for Recognition, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 1403. ,
DOI : 10.1109/CVPRW.2014.131
URL : http://arxiv.org/abs/1403.6382
A baseline for visual instance retrieval with deep convolutional networks, Proc. ICLR, 2015. ,
DOI : 10.3169/mta.4.251
Particular object retrieval with integral max-pooling of CNN activations, Proc. ICLR, 2016. ,
Cross-Dimensional Weighting for Aggregated Deep Convolutional Features, ECCV workshop on Webscale Vision and Social Media, 2016. ,
DOI : 10.1016/j.cviu.2013.12.002
URL : http://arxiv.org/abs/1512.04065
Modeling the shape of the scene: a holistic representation of the spatial envelope, 2001. ,
Evaluation of GIST descriptors for web-scale image search, Proceeding of the ACM International Conference on Image and Video Retrieval, CIVR '09, 2009. ,
DOI : 10.1145/1646396.1646421
URL : https://hal.archives-ouvertes.fr/inria-00394212