{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:09:48Z","timestamp":1785542988773,"version":"3.56.0"},"publisher-location":"Cham","reference-count":63,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319464657","type":"print"},{"value":"9783319464664","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-46466-4_15","type":"book-chapter","created":{"date-parts":[[2016,9,16]],"date-time":"2016-09-16T09:31:58Z","timestamp":1474018318000},"page":"241-257","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":427,"title":["Deep Image Retrieval: Learning Global Representations for Image Search"],"prefix":"10.1007","author":[{"given":"Albert","family":"Gordo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jon","family":"Almaz\u00e1n","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jerome","family":"Revaud","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Diane","family":"Larlus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2016,9,17]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C.L., Parikh, D.: VQA: visual question answering. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., Sivic, J.: NetVLAD: CNN architecture for weakly supervised place recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.572"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Zisserman, A.: Three things everyone should know to improve object retrieval. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248018"},{"issue":"99","key":"15_CR4","first-page":"1","volume":"PP","author":"H Azizpour","year":"2015","unstructured":"Azizpour, H., Razavian, A., Sullivan, J., Maki, A., Carlsson, S.: Factors of transferability for a generic convnet representation. TPAMI PP(99), 1 (2015)","journal-title":"TPAMI"},{"key":"15_CR5","unstructured":"Babenko, A., Lempitsky, V.S.: Aggregating deep convolutional features for image retrieval. In: ICCV (2015)"},{"key":"15_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1007\/978-3-319-10590-1_38","volume-title":"Computer Vision \u2013 ECCV 2014","author":"A Babenko","year":"2014","unstructured":"Babenko, A., Slesarev, A., Chigorin, A., Lempitsky, V.: Neural codes for image retrieval. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part I. LNCS, vol. 8689, pp. 584\u2013599. Springer, Heidelberg (2014). doi:\n                      10.1007\/978-3-319-10590-1_38"},{"key":"15_CR7","unstructured":"Chopra, S., Hadsell, R., Lecun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: CVPR (2005)"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Chum, O., Mikulik, A., Perdoch, M., Matas, J.: Total recall II: Query expansion revisited. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995601"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Chum, O., Philbin, J., Sivic, J., Isard, M., Zisserman, A.: Total recall: automatic query expansion with a generative feature model for object retrieval. In: ICCV (2007)","DOI":"10.1109\/ICCV.2007.4408891"},{"key":"15_CR10","unstructured":"Danfeng, Q., Gammeter, S., Bossard, L., Quack, T., Van Gool, L.: Hello neighbor: accurate object retrieval with k-reciprocal nearest neighbors. In: CVPR (2011)"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Deng, C., Ji, R., Liu, W., Tao, D., Gao, X.: Visual reranking through weakly supervised multi-graph learning. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.323"},{"key":"15_CR12","unstructured":"Frome, A., Corrado, G.S., Shlens, J., Bengio, S., Dean, J., Ranzato, M.A., Mikolov, T.: DeViSE: a deep visual-semantic embedding model. In: NIPS (2013)"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: CVPR (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"15_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1007\/978-3-319-10584-0_26","volume-title":"Computer Vision \u2013 ECCV 2014","author":"Y Gong","year":"2014","unstructured":"Gong, Y., Wang, L., Guo, R., Lazebnik, S.: Multi-scale orderless pooling of deep convolutional activation features. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part VII. LNCS, vol. 8695, pp. 392\u2013407. Springer, Heidelberg (2014). doi:\n                      10.1007\/978-3-319-10584-0_26"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Gordo, A., Rodr\u00edguez-Serrano, J.A., Perronnin, F., Valveny, E.: Leveraging category-level labels for instance-level image retrieval. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248035"},{"key":"15_CR17","unstructured":"Hadsell, R., Chopra, S., Lecun, Y.: Dimensionality reduction by learning an invariant mapping. In: CVPR (2006)"},{"key":"15_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/978-3-319-10578-9_23","volume-title":"Computer Vision \u2013 ECCV 2014","author":"K He","year":"2014","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part III. LNCS, vol. 8691, pp. 346\u2013361. Springer, Heidelberg (2014). doi:\n                      10.1007\/978-3-319-10578-9_23"},{"key":"15_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1007\/978-3-319-24261-3_7","volume-title":"Similarity-Based Pattern Recognition","author":"E Hoffer","year":"2015","unstructured":"Hoffer, E., Ailon, N.: Deep metric learning using triplet network. In: Feragen, A., Pelillo, M., Loog, M. (eds.) SIMBAD 2015. LNCS, vol. 9370, pp. 84\u201392. Springer, Heidelberg (2015). doi:\n                      10.1007\/978-3-319-24261-3_7"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Hu, J., Lu, J., Tan, Y.P.: Discriminative deep metric learning for face verification in the wild. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.242"},{"key":"15_CR21","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer networks. In: NIPS (2015)"},{"key":"15_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"774","DOI":"10.1007\/978-3-642-33709-3_55","volume-title":"ECCV 2012, Part II","author":"H J\u00e9gou","year":"2012","unstructured":"J\u00e9gou, H., Chum, O.: Negative evidences and co-occurences in image retrieval: The benefit of PCA and whitening. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol. 7573, pp. 774\u2013787. Springer, Heidelberg (2012). doi:\n                      10.1007\/978-3-642-33709-3_55"},{"key":"15_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1007\/978-3-540-88682-2_24","volume-title":"Computer Vision \u2013 ECCV 2008","author":"H Jegou","year":"2008","unstructured":"Jegou, H., Douze, M., Schmid, C.: Hamming embedding and weak geometric consistency for large scale image search. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 304\u2013317. Springer, Heidelberg (2008). doi:\n                      10.1007\/978-3-540-88682-2_24"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Douze, M., Schmid, C.: Improving bag-of-features for large scale image search. IJCV (2010)","DOI":"10.1109\/ICCV.2009.5459419"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Douze, M., Schmid, C., P\u00e9rez, P.: Aggregating local descriptors into a compact image representation. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Zisserman, A.: Triangulation embedding and democratic aggregation for image search. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.417"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Kalantidis, Y., Mellina, C., Osindero, S.: Cross-dimensional weighting for aggregated deep convolutional features. In: arXiv preprint \n                      arXiv:1512.04065\n                      \n                     (2015)","DOI":"10.1007\/978-3-319-46604-0_48"},{"key":"15_CR28","unstructured":"Karpathy, A., Joulin, A., Fei-Fei, L.: Deep fragment embeddings for bidirectional image-sentence mapping. In: NIPS (2014)"},{"key":"15_CR29","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"15_CR30","unstructured":"Li, X., Larson, M., Hanjalic, A.: Pairwise geometric matching for large-scale object retrieval. In: CVPR (2015)"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"15_CR32","doi-asserted-by":"crossref","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV (2004)","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"Mikolajczyk, K., Schmid, C.: Scale & affine invariant interest point detectors. IJCV (2004)","DOI":"10.1023\/B:VISI.0000027790.02288.f2"},{"key":"15_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-642-15558-1_1","volume-title":"Computer Vision \u2013 ECCV 2010","author":"A Mikul\u00edk","year":"2010","unstructured":"Mikul\u00edk, A., Perdoch, M., Chum, O., Matas, J.: Learning a fine vocabulary. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part III. LNCS, vol. 6313, pp. 1\u201314. Springer, Heidelberg (2010). doi:\n                      10.1007\/978-3-642-15558-1_1"},{"key":"15_CR35","doi-asserted-by":"crossref","unstructured":"Mikulik, A., Perdoch, M., Chum, O., Matas, J.: Learning vocabularies over a fine quantization. IJCV (2013)","DOI":"10.1007\/s11263-013-0682-4"},{"key":"15_CR36","doi-asserted-by":"crossref","unstructured":"Ng, J.Y.H., Yang, F., Davis, L.S.: Exploiting local features from deep networks for image retrieval. In: CVPR workshops (2015)","DOI":"10.1109\/CVPRW.2015.7301272"},{"key":"15_CR37","unstructured":"Nister, D., Stewenius, H.: Scalable recognition with a vocabulary tree. In: CVPR (2006)"},{"key":"15_CR38","doi-asserted-by":"crossref","unstructured":"Paulin, M., Douze, M., Harchaoui, Z., Mairal, J., Perronin, F., Schmid, C.: Local convolutional features with unsupervised training for image retrieval. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.19"},{"key":"15_CR39","doi-asserted-by":"crossref","unstructured":"Perdoch, M., Chum, O., Matas, J.: Efficient representation of local geometry for large scale object retrieval. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206529"},{"key":"15_CR40","doi-asserted-by":"crossref","unstructured":"Perronnin, F., Dance, C.: Fisher kernels on visual vocabularies for image categorization. In: CVPR (2007)","DOI":"10.1109\/CVPR.2007.383266"},{"key":"15_CR41","doi-asserted-by":"crossref","unstructured":"Perronnin, F., Larlus, D.: Fisher vectors meet neural networks: a hybrid classification architecture. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298998"},{"key":"15_CR42","doi-asserted-by":"crossref","unstructured":"Perronnin, F., Liu, Y., S\u00e1nchez, J., Poirier, H.: Large-scale image retrieval with compressed fisher vectors. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540009"},{"key":"15_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1007\/978-3-642-15558-1_49","volume-title":"Computer Vision \u2013 ECCV 2010","author":"J Philbin","year":"2010","unstructured":"Philbin, J., Isard, M., Sivic, J., Zisserman, A.: Descriptor learning for efficient retrieval. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part III. LNCS, vol. 6313, pp. 677\u2013691. Springer, Heidelberg (2010). doi:\n                      10.1007\/978-3-642-15558-1_49"},{"key":"15_CR44","doi-asserted-by":"crossref","unstructured":"Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Object retrieval with large vocabularies and fast spatial matching. In: CVPR (2007)","DOI":"10.1109\/CVPR.2007.383172"},{"key":"15_CR45","doi-asserted-by":"crossref","unstructured":"Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Lost in quantization: Improving particular object retrieval in large scale image databases. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587635"},{"key":"15_CR46","doi-asserted-by":"crossref","unstructured":"Radenovic, F., Jegou, H., Chum, O.: Multiple measurements and joint dimensionality reduction for large scale image search with short vectors-extended version. ICMR (2015)","DOI":"10.1145\/2671188.2749366"},{"key":"15_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-319-46448-0_1","volume-title":"ECCV 2016, Part I","author":"F Radenovic","year":"2016","unstructured":"Radenovic, F., Tolias, G., Chum, O.: CNN image retrieval learns from BoW: unsupervised fine-tuning with hard examples. In: Leibe, B., et al. (eds.) ECCV 2016, Part I. LNCS, vol. 9905, pp. 3\u201320. Springer, Heidelberg (2016)"},{"key":"15_CR48","doi-asserted-by":"crossref","unstructured":"Razavian, A.S., Azizpour, H., Sullivan, J., Carlsson, S.: CNN features off-the-shelf: an astounding baseline for recognition. In: CVPR Deep Vision Workshop (2014)","DOI":"10.1109\/CVPRW.2014.131"},{"key":"15_CR49","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"key":"15_CR50","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A.C., Fei-Fei, L.: Imagenet large scale visual recognition challenge. IJCV (2015)","DOI":"10.1007\/s11263-015-0816-y"},{"key":"15_CR51","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"15_CR52","doi-asserted-by":"crossref","unstructured":"Shen, X., Lin, Z., Brandt, J., Wu, Y.: Spatially-constrained similarity measurefor large-scale object retrieval. TPAMI (2014)","DOI":"10.1109\/TPAMI.2013.237"},{"key":"15_CR53","doi-asserted-by":"crossref","unstructured":"Simo-Serra, E., Trulls, E., Ferraz, L., Kokkinos, I., Fua, P., Moreno-Noguer, F.: Discriminative learning of deep convolutional feature point descriptors. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.22"},{"key":"15_CR54","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"key":"15_CR55","doi-asserted-by":"crossref","unstructured":"Song, H.O., Xiang, Y., Jegelka, S., Savarese, S.: Deep metric learning via lifted structured feature embedding. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.434"},{"key":"15_CR56","unstructured":"Sun, Y., Chen, Y., Wang, X., Tang, X.: Deep learning face representation by joint identification-verification. In: NIPS (2014)"},{"key":"15_CR57","doi-asserted-by":"crossref","unstructured":"Tao, R., Gavves, E., Snoek, C.G., Smeulders, A.W.: Locality in generic instance search from one example. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.269"},{"key":"15_CR58","doi-asserted-by":"crossref","unstructured":"Tolias, G., Avrithis, Y., J\u00e9gou, H.: Image search with selective match kernels: aggregation across single and multiple images. IJCV (2015)","DOI":"10.1007\/s11263-015-0837-6"},{"key":"15_CR59","doi-asserted-by":"crossref","unstructured":"Tolias, G., J\u00e9gou, H.: Visual query expansion with or without geometry: refining local descriptors by feature aggregation. PR (2015)","DOI":"10.1016\/j.patcog.2014.04.007"},{"key":"15_CR60","unstructured":"Tolias, G., Sicre, R., J\u00e9gou, H.: Particular object retrieval with integral max-pooling of CNN activations. In: ICLR (2016)"},{"key":"15_CR61","unstructured":"Vardi, Y., Zhang, C.H.: The multivariate L1-median and associated data depth. In: Proceedings of the National Academy of Sciences (2004)"},{"key":"15_CR62","doi-asserted-by":"crossref","unstructured":"Wang, J., Song, Y., Leung, T., Rosenberg, C., Wang, J., Philbin, J., Chen, B., Wu, Y.: Learning fine-grained image similarity with deep ranking. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.180"},{"key":"15_CR63","unstructured":"Weinberger, K.Q., Saul, L.K.: Distance metric learning for large margin nearest neighbor classification. JMLR (2009)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2016"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46466-4_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,10]],"date-time":"2020-10-10T01:25:34Z","timestamp":1602293134000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46466-4_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319464657","9783319464664"],"references-count":63,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46466-4_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"17 September 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.eccv2016.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}