{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T15:55:10Z","timestamp":1781193310489,"version":"3.54.1"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030687892","type":"print"},{"value":"9783030687908","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-68790-8_20","type":"book-chapter","created":{"date-parts":[[2021,2,22]],"date-time":"2021-02-22T13:13:24Z","timestamp":1613999604000},"page":"245-260","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Content-Based Image Retrieval and the Semantic Gap in the Deep Learning Era"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1019-9538","authenticated-orcid":false,"given":"Bj\u00f6rn","family":"Barz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3193-3300","authenticated-orcid":false,"given":"Joachim","family":"Denzler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,2,23]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Arandjelovi\u0107, R., Zisserman, A.: Three things everyone should know to improve object retrieval. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2911\u20132918, June 2012","DOI":"10.1109\/CVPR.2012.6248018"},{"key":"20_CR2","unstructured":"Arponen, H., Bishop, T.E.: SHREWD: semantic hierarchy based relational embeddings for weakly-supervised deep hashing. In: ICLR 2019 Workshop on Learning from Limited Labeled Data (2019)"},{"key":"20_CR3","unstructured":"Babenko, A., Lempitsky, V.: Aggregating local deep features for image retrieval. In: IEEE International Conference on Computer Vision, pp. 1269\u20131277, December 2015"},{"key":"20_CR4","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. LNCS, vol. 8689, pp. 584\u2013599. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_38"},{"key":"20_CR5","doi-asserted-by":"publisher","unstructured":"Barz, B., Denzler, J.: Automatic query image disambiguation for content-based image retrieval. In: International Conference on Computer Vision Theory and Applications, vol. 5, pp. 249\u2013256. INSTICC, SciTePress (2018). https:\/\/doi.org\/10.5220\/0006593402490256","DOI":"10.5220\/0006593402490256"},{"key":"20_CR6","doi-asserted-by":"publisher","unstructured":"Barz, B., Denzler, J.: Hierarchy-based image embeddings for semantic image retrieval. In: IEEE Winter Conference on Applications of Computer Vision, pp. 638\u2013647 (2019). https:\/\/doi.org\/10.1109\/WACV.2019.00073","DOI":"10.1109\/WACV.2019.00073"},{"key":"20_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"650","DOI":"10.1007\/978-3-030-12939-2_45","volume-title":"Pattern Recognition","author":"B Barz","year":"2019","unstructured":"Barz, B., K\u00e4ding, C., Denzler, J.: Information-theoretic active learning for content-based image retrieval. In: Brox, T., Bruhn, A., Fritz, M. (eds.) GCPR 2018. LNCS, vol. 11269, pp. 650\u2013666. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-12939-2_45"},{"key":"20_CR8","unstructured":"Berman, M., J\u00e9gou, H., Vedaldi, A., Kokkinos, I., Douze, M.: MultiGrain: a unified image embedding for classes and instances. arXiv preprint arXiv:1902.05509 (2019)"},{"key":"20_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1007\/978-3-030-58545-7_39","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Brown","year":"2020","unstructured":"Brown, A., Xie, W., Kalogeiton, V., Zisserman, A.: Smooth-AP: smoothing the path towards large-scale image retrieval. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 677\u2013694. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_39"},{"key":"20_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1007\/978-3-030-58565-5_43","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Cao","year":"2020","unstructured":"Cao, B., Araujo, A., Sim, J.: Unifying deep local and global features for image search. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 726\u2013743. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_43"},{"issue":"36","key":"20_CR11","first-page":"1109","volume":"11","author":"G Chechik","year":"2010","unstructured":"Chechik, G., Sharma, V., Shalit, U., Bengio, S.: Large scale online learning of image similarity through ranking. J. Mach. Learn. Res. 11(36), 1109\u20131135 (2010)","journal-title":"J. Mach. Learn. Res."},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Deng, J., Berg, A.C., Fei-Fei, L.: Hierarchical semantic indexing for large scale image retrieval. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 785\u2013792. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995516"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"20_CR14","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7287.001.0001","volume-title":"WordNet","author":"C Fellbaum","year":"1998","unstructured":"Fellbaum, C.: WordNet. Wiley, Hoboken (1998)"},{"key":"20_CR15","unstructured":"Frome, A., et al.: DeViSE: a deep visual-semantic embedding model. In: International Conference on Neural Information Processing Systems, pp. 2121\u20132129 (2013)"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Gairola, S., Shah, R., Narayanan, P.J.: Unsupervised image style embeddings for retrieval and recognition tasks. In: IEEE Winter Conference on Applications of Computer Vision, pp. 3270\u20133278 (2020)","DOI":"10.1109\/WACV45572.2020.9093421"},{"key":"20_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"514","DOI":"10.1007\/978-3-030-11024-6_40","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"R Gomez","year":"2019","unstructured":"Gomez, R., Gomez, L., Gibert, J., Karatzas, D.: Learning to learn from web data through deep semantic embeddings. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11134, pp. 514\u2013529. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11024-6_40"},{"issue":"2","key":"20_CR18","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.: End-to-end learning of deep visual representations for image retrieval. Int. J. Comput. Vis. 124(2), 237\u2013254 (2017). https:\/\/doi.org\/10.1007\/s11263-017-1016-8","journal-title":"Int. J. Comput. Vis."},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Ha, M.L., Hosu, V., Blanz, V.: Color composition similarity and its application in fine-grained similarity. In: IEEE Winter Conference on Applications of Computer Vision, pp. 2559\u20132568 (2020)","DOI":"10.1109\/WACV45572.2020.9093522"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Lu, Y., Sclaroff, S.: Local descriptors optimized for average precision. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 596\u2013605 (2018)","DOI":"10.1109\/CVPR.2018.00069"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Hu, H., et al.: Web-scale responsive visual search at Bing. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2018, pp. 359\u2013367. ACM, New York (2018)","DOI":"10.1145\/3219819.3219843"},{"key":"20_CR22","unstructured":"Huiskes, M.J., Lew, M.S.: The MIR flickr retrieval evaluation. In: ACM International Conference on Multimedia Information Retrieval. ACM, New York (2008). http:\/\/press.liacs.nl\/mirflickr\/"},{"issue":"9","key":"20_CR23","doi-asserted-by":"publisher","first-page":"1783","DOI":"10.1109\/TPAMI.2016.2613873","volume":"39","author":"SS Husain","year":"2017","unstructured":"Husain, S.S., Bober, M.: Improving large-scale image retrieval through robust aggregation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 39(9), 1783\u20131796 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"20_CR24","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1145\/582415.582418","volume":"20","author":"K J\u00e4rvelin","year":"2002","unstructured":"J\u00e4rvelin, K., Kek\u00e4l\u00e4inen, J.: Cumulated gain-based evaluation of IR techniques. ACM Trans. Inf. Syst. 20(4), 422\u2013446 (2002)","journal-title":"ACM Trans. Inf. Syst."},{"key":"20_CR25","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. LNCS, vol. 5302, pp. 304\u2013317. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-88682-2_24"},{"key":"20_CR26","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Douze, M., Schmid, C., P\u00e9rez, P.: Aggregating local descriptors into a compact image representation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3304\u20133311, June 2010","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Zisserman, A.: Triangulation embedding and democratic aggregation for image search. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3310\u20133317, June 2014","DOI":"10.1109\/CVPR.2014.417"},{"key":"20_CR28","unstructured":"Kato, T., Kurita, T., Otsu, N., Hirata, K.: A sketch retrieval method for full color image database - query by visual example. In: IAPR International Conference on Pattern Recognition, pp. 530\u2013533, August 1992"},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Long, T., Mettes, P., Shen, H.T., Snoek, C.G.: Searching for actions on the hyperbole. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1141\u20131150 (2020)","DOI":"10.1109\/CVPR42600.2020.00122"},{"issue":"2","key":"20_CR30","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91\u2013110 (2004). https:\/\/doi.org\/10.1023\/B:VISI.0000029664.99615.94","journal-title":"Int. J. Comput. Vis."},{"issue":"1","key":"20_CR31","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1023\/B:VISI.0000027790.02288.f2","volume":"60","author":"K Mikolajczyk","year":"2004","unstructured":"Mikolajczyk, K., Schmid, C.: Scale & affine invariant interest point detectors. Int. J. Comput. Vis. 60(1), 63\u201386 (2004). https:\/\/doi.org\/10.1023\/B:VISI.0000027790.02288.f2","journal-title":"Int. J. Comput. Vis."},{"key":"20_CR32","unstructured":"Narayana, P., Pednekar, A., Krishnamoorthy, A., Sone, K., Basu, S.: HUSE: hierarchical universal semantic embeddings. arXiv preprint arXiv:1911.05978 (2019)"},{"key":"20_CR33","doi-asserted-by":"crossref","unstructured":"Niblack, C.W., et al.: QBIC project: querying images by content, using color, texture, and shape. In: Proceedings of the SPIE, Storage and Retrieval for Image and Video Databases, vol. 1908, pp. 173\u2013188. International Society for Optics and Photonics (1993)","DOI":"10.1117\/12.143648"},{"key":"20_CR34","doi-asserted-by":"crossref","unstructured":"Noh, H., Araujo, A., Sim, J., Weyand, T., Han, B.: Large-scale image retrieval with attentive deep local features. In: IEEE International Conference on Computer Vision, pp. 3476\u20133485 (2017)","DOI":"10.1109\/ICCV.2017.374"},{"key":"20_CR35","doi-asserted-by":"crossref","unstructured":"Perronnin, F., Liu, Y., S\u00e1nchez, J., Poirier, H.: Large-scale image retrieval with compressed fisher vectors. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3384\u20133391, June 2010","DOI":"10.1109\/CVPR.2010.5540009"},{"key":"20_CR36","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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138, June 2007","DOI":"10.1109\/CVPR.2007.383172"},{"key":"20_CR37","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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138, June 2008","DOI":"10.1109\/CVPR.2008.4587635"},{"key":"20_CR38","doi-asserted-by":"crossref","unstructured":"Radenovi\u0107, F., Iscen, A., Tolias, G., Avrithis, Y., Chum, O.: Revisiting Oxford and Paris: large-scale image retrieval benchmarking. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5706\u20135715, June 2018","DOI":"10.1109\/CVPR.2018.00598"},{"issue":"7","key":"20_CR39","doi-asserted-by":"publisher","first-page":"1655","DOI":"10.1109\/TPAMI.2018.2846566","volume":"41","author":"F Radenovi\u0107","year":"2018","unstructured":"Radenovi\u0107, F., Tolias, G., Chum, O.: Fine-tuning CNN image retrieval with no human annotation. IEEE Trans. Pattern Anal. Mach. Intell. 41(7), 1655\u20131668 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"20_CR40","doi-asserted-by":"publisher","first-page":"251","DOI":"10.3169\/mta.4.251","volume":"4","author":"AS Razavian","year":"2016","unstructured":"Razavian, A.S., Sullivan, J., Carlsson, S., Maki, A.: Visual instance retrieval with deep convolutional networks. ITE Trans. Media Technol. Appl. 4(3), 251\u2013258 (2016)","journal-title":"ITE Trans. Media Technol. Appl."},{"key":"20_CR41","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: IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 512\u2013519, June 2014","DOI":"10.1109\/CVPRW.2014.131"},{"key":"20_CR42","doi-asserted-by":"crossref","unstructured":"Revaud, J., Almazan, J., de Rezende, R.S., de Souza, C.R.: Learning with average precision: training image retrieval with a listwise loss. In: The IEEE International Conference on Computer Vision, October 2019","DOI":"10.1109\/ICCV.2019.00521"},{"key":"20_CR43","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 815\u2013823, June 2015","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"20_CR44","doi-asserted-by":"crossref","unstructured":"Sivic, J., Zisserman, A.: Video Google: a text retrieval approach to object matching in videos. In: IEEE International Conference on Computer Vision, vol. 2, pp. 1470\u20131477 (2003)","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"20_CR45","doi-asserted-by":"publisher","first-page":"1349","DOI":"10.1109\/34.895972","volume":"22","author":"AW Smeulders","year":"2000","unstructured":"Smeulders, A.W., Worring, M., Santini, S., Gupta, A., Jain, R.: Content-based image retrieval at the end of the early years. IEEE Trans. Pattern Anal. Mach. Intell. 22, 1349\u20131380 (2000)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"20_CR46","unstructured":"Tolias, G., Sicre, R., J\u00e9gou, H.: Particular object retrieval with integral max-pooling of CNN activations. In: International Conference on Learning Representations (2016)"},{"key":"20_CR47","doi-asserted-by":"crossref","unstructured":"Wu, H., Mao, J., Zhang, Y., Jiang, Y., Li, L., Sun, W., Ma, W.Y.: Unified visual-semantic embeddings: bridging vision and language with structured meaning representations. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6602\u20136611 (2019)","DOI":"10.1109\/CVPR.2019.00677"},{"key":"20_CR48","doi-asserted-by":"crossref","unstructured":"Yang, S., Yu, W., Zheng, Y., Yao, H., Mei, T.: Adaptive semantic-visual tree for hierarchical embeddings. In: ACM International Conference on Multimedia, pp. 2097\u20132105. Association for Computing Machinery, New York (2019)","DOI":"10.1145\/3343031.3350995"},{"key":"20_CR49","doi-asserted-by":"crossref","unstructured":"Zhi, T., Duan, L.Y., Wang, Y., Huang, T.: Two-stage pooling of deep convolutional features for image retrieval. In: IEEE International Conference on Image Processing, pp. 2465\u20132469, September 2016","DOI":"10.1109\/ICIP.2016.7532802"},{"issue":"6","key":"20_CR50","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1007\/s00530-002-0070-3","volume":"8","author":"XS Zhou","year":"2003","unstructured":"Zhou, X.S., Huang, T.S.: Relevance feedback in image retrieval: a comprehensive review. Multimed. Syst. 8(6), 536\u2013544 (2003). https:\/\/doi.org\/10.1007\/s00530-002-0070-3","journal-title":"Multimed. Syst."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition. ICPR International Workshops and Challenges"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-68790-8_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,22]],"date-time":"2021-02-22T13:30:18Z","timestamp":1614000618000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-68790-8_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030687892","9783030687908"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-68790-8_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"23 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 January 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ICPR2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.icpr2020.it\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}