{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T10:46:38Z","timestamp":1743072398861,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030110178"},{"type":"electronic","value":"9783030110185"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-11018-5_36","type":"book-chapter","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T05:50:50Z","timestamp":1548309050000},"page":"413-430","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Compact Deep Aggregation for Set Retrieval"],"prefix":"10.1007","author":[{"given":"Yujie","family":"Zhong","sequence":"first","affiliation":[]},{"given":"Relja","family":"Arandjelovi\u0107","sequence":"additional","affiliation":[]},{"given":"Andrew","family":"Zisserman","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,1,23]]},"reference":[{"key":"36_CR1","doi-asserted-by":"crossref","unstructured":"Arandjelovi\u0107, R., Gronat, P., Torii, A., Pajdla, T., Sivic, J.: NetVLAD: CNN architecture for weakly supervised place recognition. In: Proceedings of CVPR (2016)","DOI":"10.1109\/CVPR.2016.572"},{"key":"36_CR2","doi-asserted-by":"crossref","unstructured":"Arandjelovi\u0107, R., Zisserman, A.: All about VLAD. In: Proceedings of CVPR (2013)","DOI":"10.1109\/CVPR.2013.207"},{"key":"36_CR3","doi-asserted-by":"crossref","unstructured":"Cao, Q., Shen, L., Xie, W., Parkhi, O.M., Zisserman, A.: VGGFace2: a dataset for recognising faces across pose and age. In: Proceedings of International Conference on Automatic Face and Gesture Recognition (2018)","DOI":"10.1109\/FG.2018.00020"},{"key":"36_CR4","doi-asserted-by":"crossref","unstructured":"Chatfield, K., Lempitsky, V., Vedaldi, A., Zisserman, A.: The devil is in the details: an evaluation of recent feature encoding methods. In: Proceedings of BMVC (2011)","DOI":"10.5244\/C.25.76"},{"key":"36_CR5","doi-asserted-by":"crossref","unstructured":"Delhumeau, J., Gosselin, P.H., J\u00e9gou, H., P\u00e9rez, P.: Revisiting the VLAD image representation. In: Proceedings of ACMM (2013)","DOI":"10.1145\/2502081.2502171"},{"key":"36_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/978-3-319-46487-9_6","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Y Guo","year":"2016","unstructured":"Guo, Y., Zhang, L., Hu, Y., He, X., Gao, J.: MS-Celeb-1M: a dataset and benchmark for large-scale face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part III. LNCS, vol. 9907, pp. 87\u2013102. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_6"},{"key":"36_CR7","doi-asserted-by":"crossref","unstructured":"Rezatofighi, S.H., Kumar, B., Milan, A., Abbasnejad, E., Dick, A., Reid, I.: DeepSetNet: predicting sets with deep neural networks. In: Proceedings of CVPR (2017)","DOI":"10.1109\/ICCV.2017.561"},{"key":"36_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"36_CR9","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of ICML (2015)"},{"key":"36_CR10","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1109\/TBDATA.2017.2677964","volume":"4","author":"A Iscen","year":"2017","unstructured":"Iscen, A., Furon, T., Gripon, V., Rabbat, M., J\u00e9gou, H.: Memory vectors for similarity search in high-dimensional spaces. IEEE Trans. Big Data 4, 65\u201377 (2017)","journal-title":"IEEE Trans. Big Data"},{"key":"36_CR11","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":"Computer Vision \u2013 ECCV 2012","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, pp. 774\u2013787. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33709-3_55"},{"key":"36_CR12","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Douze, M., Schmid, C., P\u00e9rez, P.: Aggregating local descriptors into a compact image representation. In: Proceedings of CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"36_CR13","doi-asserted-by":"publisher","first-page":"1704","DOI":"10.1109\/TPAMI.2011.235","volume":"34","author":"H J\u00e9gou","year":"2011","unstructured":"J\u00e9gou, H., Perronnin, F., Douze, M., S\u00e1nchez, J., P\u00e9rez, P., Schmid, C.: Aggregating local image descriptors into compact codes. IEEE PAMI 34, 1704\u20131716 (2011)","journal-title":"IEEE PAMI"},{"key":"36_CR14","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Zisserman, A.: Triangulation embedding and democratic aggregation for image search. In: Proceedings of CVPR (2014)","DOI":"10.1109\/CVPR.2014.417"},{"key":"36_CR15","unstructured":"Kondor, R., Jebara, T.: A kernel between sets of vectors. In: Proceedings of ICML. AAAI Press (2003)"},{"issue":"2","key":"36_CR16","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"D Lowe","year":"2004","unstructured":"Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV 60(2), 91\u2013110 (2004)","journal-title":"IJCV"},{"key":"36_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"720","DOI":"10.1007\/978-3-319-10593-2_47","volume-title":"Computer Vision \u2013 ECCV 2014","author":"M Mathias","year":"2014","unstructured":"Mathias, M., Benenson, R., Pedersoli, M., Van Gool, L.: Face detection without bells and whistles. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part IV. LNCS, vol. 8692, pp. 720\u2013735. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10593-2_47"},{"key":"36_CR18","unstructured":"Nister, D., Stewenius, H.: Scalable recognition with a vocabulary tree. In: Proceedings of CVPR, pp. 2161\u20132168 (2006)"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A.: Deep face recognition. In: Proceedings of BMVC (2015)","DOI":"10.5244\/C.29.41"},{"key":"36_CR20","doi-asserted-by":"crossref","unstructured":"Perronnin, F., Liu, Y., S\u00e1nchez, J., Poirier, H.: Large-scale image retrieval with compressed fisher vectors. In: Proceedings of CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540009"},{"key":"36_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/978-3-642-15561-1_11","volume-title":"Computer Vision \u2013 ECCV 2010","author":"F Perronnin","year":"2010","unstructured":"Perronnin, F., S\u00e1nchez, J., Mensink, T.: Improving the fisher kernel for large-scale image classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 143\u2013156. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15561-1_11"},{"key":"36_CR22","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: Proceedings of CVPR (2007)","DOI":"10.1109\/CVPR.2007.383172"},{"key":"36_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-46448-0_1","volume-title":"Computer Vision \u2013 ECCV 2016","author":"F Radenovi\u0107","year":"2016","unstructured":"Radenovi\u0107, F., Tolias, G., Chum, O.: CNN image retrieval learns from BoW: unsupervised fine-tuning with hard examples. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part I. LNCS, vol. 9905, pp. 3\u201320. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_1"},{"key":"36_CR24","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: Proceedings of CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"36_CR25","doi-asserted-by":"crossref","unstructured":"Sivic, J., Zisserman, A.: Video google: a text retrieval approach to object matching in videos. In: Proceedings of ICCV, vol. 2, pp. 1470\u20131477 (2003)","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"36_CR26","doi-asserted-by":"crossref","unstructured":"Sun, Y., Zheng, L., Deng, W., Wang, S.: SVDNet for pedestrian retrieval. In: Proceedings of ICCV (2017)","DOI":"10.1109\/ICCV.2017.410"},{"key":"36_CR27","doi-asserted-by":"crossref","unstructured":"Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: Deep-face: closing the gap to human-level performance in face verification. In: IEEE CVPR (2014)","DOI":"10.1109\/CVPR.2014.220"},{"key":"36_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1007\/978-3-642-15549-9_56","volume-title":"Computer Vision \u2013 ECCV 2010","author":"L Torresani","year":"2010","unstructured":"Torresani, L., Szummer, M., Fitzgibbon, A.: Efficient object category recognition using classemes. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 776\u2013789. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15549-9_56"},{"key":"36_CR29","doi-asserted-by":"crossref","unstructured":"Vedaldi, A., Lenc, K.: MatConvNet: convolutional neural networks for MATLAB. In: Proceedings of ACMM (2015)","DOI":"10.1145\/2733373.2807412"},{"key":"36_CR30","doi-asserted-by":"crossref","unstructured":"Wang, J., Yang, J., Yu, K., Lv, F., Huang, T., Gong, Y.: Locality-constrained linear coding for image classification. In: Proceedings of CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540018"},{"key":"36_CR31","unstructured":"Zaheer, M., Kottur, S., Ravanbakhsh, S., Poczos, B., Salakhutdinov, R., Smola, A.: Deep sets. In: NIPS, pp. 3391\u20133401 (2017)"},{"key":"36_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1007\/978-3-642-15555-0_11","volume-title":"Computer Vision \u2013 ECCV 2010","author":"X Zhou","year":"2010","unstructured":"Zhou, X., Yu, K., Zhang, T., Huang, T.S.: Image classification using super-vector coding of local image descriptors. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 141\u2013154. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15555-0_11"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-11018-5_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T01:23:39Z","timestamp":1674350619000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-11018-5_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030110178","9783030110185"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-11018-5_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"23 January 2019","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":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.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"}]}}