{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T00:57:33Z","timestamp":1743123453312,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031159367"},{"type":"electronic","value":"9783031159374"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-15937-4_52","type":"book-chapter","created":{"date-parts":[[2022,9,6]],"date-time":"2022-09-06T08:15:35Z","timestamp":1662452135000},"page":"620-632","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["End-to-End Large-Scale Image Retrieval Network with\u00a0Convolution and\u00a0Vision Transformers"],"prefix":"10.1007","author":[{"given":"Qing","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feilong","family":"Bao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangdong","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weihua","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanglai","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,9,7]]},"reference":[{"key":"52_CR1","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"52_CR2","doi-asserted-by":"crossref","unstructured":"Lanchantin, J., Wang, T., Ordonez, V., Qi, Y.: General multi-label image classification with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16478\u201316488 (2021)","DOI":"10.1109\/CVPR46437.2021.01621"},{"key":"52_CR3","doi-asserted-by":"crossref","unstructured":"Miech, A., Alayrac, J.B., Laptev, I., Sivic, J., Zisserman, A.: Thinking fast and slow: efficient text-to-visual retrieval with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9826\u20139836 (2021)","DOI":"10.1109\/CVPR46437.2021.00970"},{"key":"52_CR4","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"52_CR5","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"52_CR6","unstructured":"Wu, B., et al.: Visual transformers: token-based image representation and processing for computer vision. arXiv preprint arXiv:2006.03677 (2020)"},{"key":"52_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/978-3-030-58595-2_16","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Ng","year":"2020","unstructured":"Ng, T., Balntas, V., Tian, Y., Mikolajczyk, K.: SOLAR: second-order loss and attention for image retrieval. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12370, pp. 253\u2013270. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58595-2_16"},{"key":"52_CR8","unstructured":"El-Nouby, A., Neverova, N., Laptev, I., J\u00e9gou, H.: Training vision transformers for image retrieval. arXiv preprint arXiv:2102.05644 (2021)"},{"key":"52_CR9","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"52_CR10","doi-asserted-by":"crossref","unstructured":"Yuan, K., Guo, S., Liu, Z., Zhou, A., Yu, F., Wu, W.: Incorporating convolution designs into visual transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 579\u2013588 (2021)","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"52_CR11","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. 3, pp. 1470\u20131470. IEEE Computer Society (2003)","DOI":"10.1109\/ICCV.2003.1238663"},{"issue":"2","key":"52_CR12","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. Vision 60(2), 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vision"},{"key":"52_CR13","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":"52_CR14","unstructured":"Tolias, G., Sicre, R., J\u00e9gou, H.: Particular object retrieval with integral max-pooling of CNN activations. arXiv preprint arXiv:1511.05879 (2015)"},{"key":"52_CR15","unstructured":"Babenko, A., Lempitsky, V.: Aggregating local deep features for image retrieval. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1269\u20131277 (2015)"},{"key":"52_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1007\/978-3-319-46604-0_48","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"Y Kalantidis","year":"2016","unstructured":"Kalantidis, Y., Mellina, C., Osindero, S.: Cross-dimensional weighting for aggregated deep convolutional features. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9913, pp. 685\u2013701. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46604-0_48"},{"key":"52_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/978-3-319-46466-4_15","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Gordo","year":"2016","unstructured":"Gordo, A., Almaz\u00e1n, J., Revaud, J., Larlus, D.: Deep image retrieval: learning global representations for image search. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 241\u2013257. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_15"},{"key":"52_CR18","doi-asserted-by":"crossref","unstructured":"Yang, T.Y., Kien Nguyen, D., Heijnen, H., Balntas, V.: Dame web: dynamic mean with whitening ensemble binarization for landmark retrieval without human annotation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00353"},{"issue":"7","key":"52_CR19","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."},{"key":"52_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"52_CR21","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"},{"key":"52_CR22","doi-asserted-by":"crossref","unstructured":"Nie, X., Lu, H., Wang, Z., Liu, J., Guo, Z.: Weakly supervised image retrieval via coarse-scale feature fusion and multi-level attention blocks. In: Proceedings of the 2019 on International Conference on Multimedia Retrieval, pp. 48\u201352 (2019)","DOI":"10.1145\/3323873.3325017"},{"key":"52_CR23","doi-asserted-by":"crossref","unstructured":"Messina, N., Falchi, F., Esuli, A., Amato, G.: Transformer reasoning network for image-text matching and retrieval. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 5222\u20135229. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9413172"},{"key":"52_CR24","unstructured":"Kendall, A., Gal, Y., Cipolla, R.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7482\u20137491 (2018)"},{"key":"52_CR25","doi-asserted-by":"crossref","unstructured":"Tian, Y., Yu, X., Fan, B., Wu, F., Heijnen, H., Balntas, V.: Sosnet: second order similarity regularization for local descriptor learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11016\u201311025 (2019)","DOI":"10.1109\/CVPR.2019.01127"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-15937-4_52","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,6]],"date-time":"2022-09-06T08:26:01Z","timestamp":1662452761000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-15937-4_52"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031159367","9783031159374"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-15937-4_52","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"7 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bristol","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2022\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"561","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"255","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"45% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}