{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T15:48:28Z","timestamp":1777477708399,"version":"3.51.4"},"reference-count":66,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2016,7,12]],"date-time":"2016-07-12T00:00:00Z","timestamp":1468281600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2017,1]]},"DOI":"10.1007\/s11263-016-0924-3","type":"journal-article","created":{"date-parts":[[2016,7,12]],"date-time":"2016-07-12T00:29:40Z","timestamp":1468283380000},"page":"149-168","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":45,"title":["Convolutional Patch Representations for Image Retrieval: An Unsupervised Approach"],"prefix":"10.1007","volume":"121","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7347-4520","authenticated-orcid":false,"given":"Mattis","family":"Paulin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julien","family":"Mairal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthijs","family":"Douze","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zaid","family":"Harchaoui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florent","family":"Perronnin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cordelia","family":"Schmid","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,7,12]]},"reference":[{"key":"924_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, P., Carreira, J., Malik, J. (2015) Learning to see by moving. In IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/ICCV.2015.13"},{"key":"924_CR2","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Zisserman, A. (2013) All about VLAD. In IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2013.207"},{"key":"924_CR3","unstructured":"Babenko, A., Lempitsky, V. (2015) Aggregating deep convolutional features for image retrieval. In International conference on computer vision"},{"key":"924_CR4","doi-asserted-by":"crossref","unstructured":"Babenko, A., Slesarev, A., Chigorin, A., Lempitsky, V. (2014) Neural codes for image retrieval. In European conference on computer vision","DOI":"10.1007\/978-3-319-10590-1_38"},{"key":"924_CR5","first-page":"1","volume":"3","author":"FR Bach","year":"2002","unstructured":"Bach, F. R., & Jordan, M. I. (2002). Kernel independent component analysis. Journal of Machine Learning Research, 3, 1\u201348.","journal-title":"Journal of Machine Learning Research"},{"key":"924_CR6","doi-asserted-by":"crossref","unstructured":"Bay, H., Tuytelaars, T., Van Gool, L. (2006) SURF: Speeded up robust features. In European conference on computer vision","DOI":"10.1007\/11744023_32"},{"key":"924_CR7","doi-asserted-by":"crossref","unstructured":"Bo, L., Ren, X., Fox, D. (2010) Kernel descriptors for visual recognition. Advances in neural information processing systems","DOI":"10.1109\/IROS.2011.6095119"},{"key":"924_CR8","volume-title":"Neural networks: Tricks of the trade","author":"L Bottou","year":"2012","unstructured":"Bottou, L. (2012). Stochastic gradient descent tricks. Neural networks: Tricks of the trade. Berlin: Springer."},{"key":"924_CR9","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/TPAMI.2010.54","volume":"33","author":"M Brown","year":"2011","unstructured":"Brown, M., Hua, G., & Winder, S. (2011). Discriminative learning of local image descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33, 43\u201357.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"924_CR10","doi-asserted-by":"crossref","unstructured":"Calonder, M., Lepetit, V., Strecha, C., Fua (2010). BRIEF: Binary robust independent elementary features. In European conference on computer vision","DOI":"10.1007\/978-3-642-15561-1_56"},{"key":"924_CR11","doi-asserted-by":"crossref","unstructured":"Chopra, S., Hadsell, R., LeCun, Y. (2005) Learning a similarity metric discriminatively, with application to face verification. In IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2005.202"},{"key":"924_CR12","volume-title":"Neural networks: Tricks of the trade","author":"A Coates","year":"2012","unstructured":"Coates, A., & Ng, A. Y. (2012). Learning feature representations with k-mean. Neural networks: Tricks of the trade. Heidelberg: Springer."},{"key":"924_CR13","series-title":"Cambridge Monographs on Applied and Computational Mathematics","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511618796","volume-title":"Learning theory : An approximation theory viewpoint","author":"F Cucker","year":"2007","unstructured":"Cucker, F., & Zhou, D. X. (2007). Learning theory : An approximation theory viewpoint., Cambridge Monographs on Applied and Computational Mathematics Cambridge: Cambridge University Press."},{"key":"924_CR14","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, LJ., Li, K., Fei-Fei, L. (2009) ImageNet: A large-scale hierarchical image database. In IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"924_CR15","unstructured":"Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., Darrell, T. (2014) DeCAF: A deep convolutional activation feature for generic visual recognition. In International conference on machine learning"},{"key":"924_CR16","doi-asserted-by":"crossref","unstructured":"Dong, J., Soatto, S. (2015) Domain-size pooling in local descriptors: Dsp-sift. In IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2015.7299145"},{"key":"924_CR17","unstructured":"Dosovitskiy, A., Springenberg, JT., Riedmiller, M., Brox, T. (2014) Discriminative unsupervised feature learning with convolutional neural networks. Advances in Neural Information Processing Systems"},{"key":"924_CR18","unstructured":"Erhan, D., Manzagol, PA., Bengio, Y., Bengio, S., Vincent, P. (2009) The difficulty of training deep architectures and the effect of unsupervised pre-training. In Twelfth international conference on artificial intelligence and statistics"},{"key":"924_CR19","first-page":"625","volume":"11","author":"D Erhan","year":"2010","unstructured":"Erhan, D., Bengio, Y., Courville, A., Manzagol, P. A., Vincent, P., & Bengio, S. (2010). Why does unsupervised pre-training help deep learning? The Journal of Machine Learning Research, 11, 625\u2013660.","journal-title":"The Journal of Machine Learning Research"},{"key":"924_CR20","doi-asserted-by":"crossref","unstructured":"Fischer, P., Dosovitskiy, A., Brox, T. (2014) Descriptor matching with Convolutional Neural Networks: a comparison to SIFT. arXiv Preprint","DOI":"10.1109\/CVPR.2015.7298761"},{"key":"924_CR21","doi-asserted-by":"crossref","unstructured":"Gong, Y., Wang, L., Guo, R., Lazebnik, S. (2014) Multi-scale orderless pooling of deep convolutional activation features. In European conference on computer vision","DOI":"10.1007\/978-3-319-10584-0_26"},{"key":"924_CR22","unstructured":"Goroshin, R., Bruna, J., Tompson, J., Eigen, D., LeCun, Y. (2014) Unsupervised feature learning from temporal data. In Advances in Neural Information Processing Systems"},{"key":"924_CR23","unstructured":"Goroshin, R., Mathieu, M., LeCun, Y. (2015) Learning to linearize under uncertainty. In Advances in Neural Information Processing Systems"},{"key":"924_CR24","doi-asserted-by":"crossref","unstructured":"Jayaraman, D., Grauman, K. (2015) Learning image representations equivariant to ego-motion. In IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/ICCV.2015.166"},{"key":"924_CR25","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Chum, O. (2012) Negative evidences and co-occurrences in image retrieval: the benefit of PCA and whitening. In European conference on computer vision","DOI":"10.1007\/978-3-642-33709-3_55"},{"key":"924_CR26","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Douze, M., Schmid, C. (2008) Hamming embedding and weak geometric consistency for large scale image search. In European conference on computer vision","DOI":"10.1007\/978-3-540-88682-2_24"},{"key":"924_CR27","doi-asserted-by":"crossref","unstructured":"J\u00e9gou H, Douze M, Schmid C, P\u00e9rez P (2010) Aggregating local descriptors into a compact image representation. In IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2010.5540039"},{"issue":"1","key":"924_CR28","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1109\/TPAMI.2010.57","volume":"33","author":"H J\u00e9gou","year":"2011","unstructured":"J\u00e9gou, H., Douze, M., & Schmid, C. (2011). Product quantization for nearest neighbor search. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(1), 117\u2013128.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"9","key":"924_CR29","doi-asserted-by":"crossref","first-page":"1704","DOI":"10.1109\/TPAMI.2011.235","volume":"34","author":"H J\u00e9gou","year":"2012","unstructured":"J\u00e9gou, H., Perronnin, F., Douze, M., S\u00e1nchez, J., P\u00e9rez, P., & Schmid, C. (2012). Aggregating local image descriptors into compact codes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(9), 1704\u20131716.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"924_CR30","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T. (2014) Caffe: Convolutional architecture for fast feature embedding. In ACM multimedia conference","DOI":"10.1145\/2647868.2654889"},{"key":"924_CR31","doi-asserted-by":"crossref","unstructured":"Jiang, W., Song, Y., Leung, T., Rosenberg, C., Wang, J., Philbin, J., Chen, B., Wu, Y. (2014) Learning fine-grained image similarity with deep ranking. In IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2014.180"},{"key":"924_CR32","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G. (2012) ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems"},{"key":"924_CR33","unstructured":"LeCun, Y., Boser, B., Denker, J., Henderson, D., Howard, R., Hubbard, W., Jackel, L. (1989) Handwritten digit recognition with a back-propagation network. Advances in Neural Information Processing Systems"},{"issue":"11","key":"924_CR34","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278\u20132324.","journal-title":"Proceedings of the IEEE"},{"key":"924_CR35","doi-asserted-by":"crossref","unstructured":"Li, Y., Snavely, N., Huttenlocher, DP. (2010) Location recognition using prioritized feature matching. In European conference on computer vision","DOI":"10.1007\/978-3-642-15552-9_57"},{"key":"924_CR36","unstructured":"Long, J., Zhang, N., Darrell, T. (2014) Do Convnets learn correspondances? Advances in Neural Information Processing Systems"},{"issue":"2","key":"924_CR37","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International Journal on Computer Vision, 60(2), 91\u2013110.","journal-title":"International Journal on Computer Vision"},{"key":"924_CR38","doi-asserted-by":"crossref","unstructured":"Mairal, J., Bach, F., Ponce, J. (2014a) Sparse modeling for image and vision processing. Foundations and Trends in Computer Graphics and Vision","DOI":"10.1561\/0600000058"},{"key":"924_CR39","unstructured":"Mairal, J., Koniusz, P., Harchaoui, Z., Schmid C (2014b) Convolutional kernel networks. Advances in Neural Information Processing Systems"},{"issue":"1","key":"924_CR40","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1023\/B:VISI.0000027790.02288.f2","volume":"60","author":"K Mikolajczyk","year":"2004","unstructured":"Mikolajczyk, K., & Schmid, C. (2004). Scale & affine invariant interest point detectors. International Journal on Computer Vision, 60(1), 63\u201386.","journal-title":"International Journal on Computer Vision"},{"issue":"10","key":"924_CR41","doi-asserted-by":"crossref","first-page":"1615","DOI":"10.1109\/TPAMI.2005.188","volume":"27","author":"K Mikolajczyk","year":"2005","unstructured":"Mikolajczyk, K., & Schmid, C. (2005). A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(10), 1615\u20131630.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"924_CR42","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1007\/s11263-005-3848-x","volume":"65","author":"K Mikolajczyk","year":"2005","unstructured":"Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., et al. (2005). A comparison of affine region detectors. International Journal on Computer Vision, 65, 43\u201372.","journal-title":"International Journal on Computer Vision"},{"key":"924_CR43","doi-asserted-by":"crossref","unstructured":"Ng, JYH., Yang, F., Davis, LS. (2015) Exploiting Local Features from Deep Networks for Image Retrieval. In DeepVision workshop","DOI":"10.1109\/CVPRW.2015.7301272"},{"key":"924_CR44","doi-asserted-by":"crossref","unstructured":"Nister, D., Stewenius, H. (2006) Scalable recognition with a vocabulary tree. In IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2006.264"},{"key":"924_CR45","doi-asserted-by":"crossref","unstructured":"Paulin, M., Douze, M., Harchaoui, Z., Mairal, J., Perronnin, F., Schmid, C. (2015) Local convolutional features with unsupervised training for image retrieval. In International conference on computer vision","DOI":"10.1109\/ICCV.2015.19"},{"key":"924_CR46","doi-asserted-by":"crossref","unstructured":"Perd\u2019och, M., Chum, O., Matas, J. (2009) Efficient representation of local geometry for large scale object retrieval. In IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2009.5206529"},{"key":"924_CR47","doi-asserted-by":"crossref","unstructured":"Perronnin, F., Dance, C. (2007) Fisher kernels on visual vocabularies for image categorization. In IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2007.383266"},{"key":"924_CR48","doi-asserted-by":"crossref","unstructured":"Perronnin, F., S\u00e1nchez, J., Liu, Y. (2010) Large-scale image categorization with explicit data embedding. In IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2010.5539914"},{"key":"924_CR49","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","DOI":"10.1109\/CVPR.2007.383172"},{"key":"924_CR50","doi-asserted-by":"crossref","unstructured":"Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A. (2008) Lost in quantization: Improving particular object retrieval in large scale image databases. In IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2008.4587635"},{"key":"924_CR51","doi-asserted-by":"crossref","unstructured":"Philbin, J., Isard, M., Sivic, J., Zisserman, A. (2010) Descriptor learning for efficient retrieval. In European conference on computer vision","DOI":"10.1007\/978-3-642-15558-1_49"},{"key":"924_CR52","unstructured":"Rahimi, A., Recht, B. (2008) Random features for large-scale kernel machines. Advances in Neural Information Processing Systems"},{"key":"924_CR53","doi-asserted-by":"crossref","unstructured":"Razavian, AS., Azizpour, H., Sullivan, J., Carlsson, S. (2014) CNN features off-the-shelf: an astounding baseline for recognition. preprint arXiv:1403.6382","DOI":"10.1109\/CVPRW.2014.131"},{"key":"924_CR54","volume-title":"Learning with kernels: Support vector machines, regularization, optimization, and beyond","author":"B Sch\u00f6lkopf","year":"2002","unstructured":"Sch\u00f6lkopf, B., & Smola, A. J. (2002). Learning with kernels: Support vector machines, regularization, optimization, and beyond. Cambridge: MIT press."},{"key":"924_CR55","doi-asserted-by":"crossref","unstructured":"Simo-Serra, E., Trulls, E., Ferraz, L., Kokkinos, I., Moreno-Noguer, F. (2015) Discriminative learning of deep convolutional feature point descriptors. In International conference on computer vision","DOI":"10.1109\/ICCV.2015.22"},{"key":"924_CR56","doi-asserted-by":"crossref","first-page":"1573","DOI":"10.1109\/TPAMI.2014.2301163","volume":"36","author":"K Simonyan","year":"2014","unstructured":"Simonyan, K., Vedaldi, A., & Zisserman, A. (2014). Learning local feature descriptors using convex optimisation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36, 1573\u20131585.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"924_CR57","doi-asserted-by":"crossref","unstructured":"Tola, E., Lepetit, V., & Fua, P. (2010). Daisy: An efficient dense descriptor applied to wide-baseline stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(5), 815\u2013830.","DOI":"10.1109\/TPAMI.2009.77"},{"key":"924_CR58","unstructured":"Tolias, G., Sicre, R., J\u00e9gou H (2015) Particular Object Retrieval with Integral Max-Pooling of CNN Activations. preprint arXiv:1511.05879"},{"key":"924_CR59","doi-asserted-by":"crossref","unstructured":"Tuytelaars, T., & Mikolajczyk, K. (2008). Local invariant feature detectors: A survey. Foundations and Trends in Computer Graphics and Vision, 3(3), 177\u2013280.","DOI":"10.1561\/0600000017"},{"issue":"3","key":"924_CR60","doi-asserted-by":"crossref","first-page":"480","DOI":"10.1109\/TPAMI.2011.153","volume":"34","author":"A Vedaldi","year":"2012","unstructured":"Vedaldi, A., & Zisserman, A. (2012). Efficient additive kernels via explicit feature maps. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(3), 480\u2013492.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"924_CR61","unstructured":"Wang, Z., Fan, B., Wu, F. (2011) Local intensity order pattern for feature description. In International conference on computer vision"},{"key":"924_CR62","unstructured":"Williams, C., Seeger, M. (2001) Using the Nystr\u00f6m method to speed up kernel machines. Advances in Neural Information Processing Systems"},{"key":"924_CR63","doi-asserted-by":"crossref","unstructured":"Winder, S., Hua, G., Brown, M. (2009) Picking the best Daisy. In IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2009.5206839"},{"key":"924_CR64","unstructured":"Yosinski, J., Clune, J., Bengio, Y., Lipson, H. (2014) How transferable are features in deep neural networks? Advances in Neural Information Processing Systems"},{"key":"924_CR65","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., Komodakis, N. (2015) Learning to compare image patches via convolutional neural networks. In IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2015.7299064"},{"key":"924_CR66","doi-asserted-by":"crossref","unstructured":"Zbontar, J., LeCun, Y. (2015) Computing the stereo matching cost with a convolutional neural network. In IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2015.7298767"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-016-0924-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-016-0924-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-016-0924-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-016-0924-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,10]],"date-time":"2019-09-10T21:08:31Z","timestamp":1568149711000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-016-0924-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,7,12]]},"references-count":66,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2017,1]]}},"alternative-id":["924"],"URL":"https:\/\/doi.org\/10.1007\/s11263-016-0924-3","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,7,12]]}}}