{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:42:07Z","timestamp":1772905327104,"version":"3.50.1"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030586003","type":"print"},{"value":"9783030586010","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58601-0_33","type":"book-chapter","created":{"date-parts":[[2020,11,27]],"date-time":"2020-11-27T19:02:52Z","timestamp":1606503772000},"page":"549-565","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":55,"title":["Adaptive Offline Quintuplet Loss for Image-Text Matching"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6355-6474","authenticated-orcid":false,"given":"Tianlang","family":"Chen","sequence":"first","affiliation":[]},{"given":"Jiajun","family":"Deng","sequence":"additional","affiliation":[]},{"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,28]]},"reference":[{"key":"33_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"33_CR2","doi-asserted-by":"crossref","unstructured":"Chen, T., Luo, J.: Expressing objects just like words: Recurrent visual embedding for image-text matching. arXiv preprint arXiv:2002.08510 (2020)","DOI":"10.1609\/aaai.v34i07.6631"},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"Chen, T., et al.: \u201cfactual\"or\u201cemotional\": Stylized image captioning with adaptive learning and attention. In: Proceedings of the European Conference on Computer Vision (ECCV). pp. 519\u2013535 (2018)","DOI":"10.1007\/978-3-030-01249-6_32"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Chen, W., Chen, X., Zhang, J., Huang, K.: Beyond triplet loss: a deep quadruplet network for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 403\u2013412 (2017)","DOI":"10.1109\/CVPR.2017.145"},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"Eisenschtat, A., Wolf, L.: Linking image and text with 2-way nets. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4601\u20134611 (2017)","DOI":"10.1109\/CVPR.2017.201"},{"key":"33_CR6","unstructured":"Faghri, F., Fleet, D.J., Kiros, J.R., Fidler, S.: Vse++: Improved visual-semantic embeddings. arXiv preprint arXiv:1707.05612 2(7), 8 (2017)"},{"key":"33_CR7","unstructured":"Frome, A., et al.: Devise: A deep visual-semantic embedding model. In: Advances in Neural Information Processing Systems. pp. 2121\u20132129 (2013)"},{"key":"33_CR8","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":"33_CR9","doi-asserted-by":"crossref","unstructured":"Huang, Y., Wang, L.: Acmm: aligned cross-modal memory for few-shot image and sentence matching. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 5774\u20135783 (2019)","DOI":"10.1109\/ICCV.2019.00587"},{"key":"33_CR10","doi-asserted-by":"crossref","unstructured":"Huang, Y., Wang, W., Wang, L.: Instance-aware image and sentence matching with selective multimodal lstm. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 2310\u20132318 (2017)","DOI":"10.1109\/CVPR.2017.767"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Ji, Z., Wang, H., Han, J., Pang, Y.: Saliency-guided attention network for image-sentence matching. arXiv preprint arXiv:1904.09471 (2019)","DOI":"10.1109\/ICCV.2019.00585"},{"key":"33_CR12","unstructured":"Kim, J.H., et al.: Multimodal residual learning for visual qa. In: Advances in Neural Information Processing Systems. pp. 361\u2013369 (2016)"},{"key":"33_CR13","unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.S.: Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539 (2014)"},{"key":"33_CR14","doi-asserted-by":"crossref","unstructured":"Lee, K.H., Chen, X., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching. In: Proceedings of the European Conference on Computer Vision (ECCV). pp. 201\u2013216 (2018)","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Li, K., Zhang, Y., Li, K., Li, Y., Fu, Y.: Visual semantic reasoning for image-text matching. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 4654\u20134662 (2019)","DOI":"10.1109\/ICCV.2019.00475"},{"key":"33_CR16","doi-asserted-by":"crossref","unstructured":"Li, S., Xiao, T., Li, H., Yang, W., Wang, X.: Identity-aware textual-visual matching with latent co-attention. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 1890\u20131899 (2017)","DOI":"10.1109\/ICCV.2017.209"},{"key":"33_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"33_CR18","doi-asserted-by":"crossref","unstructured":"Liu, C., Mao, Z., Liu, A.A., Zhang, T., Wang, B., Zhang, Y.: Focus your attention: a bidirectional focal attention network for image-text matching. In: Proceedings of the 27th ACM International Conference on Multimedia. pp. 3\u201311 (2019)","DOI":"10.1145\/3343031.3350869"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"Liu, F., Ye, R., Wang, X., Li, S.: Hal: Improved text-image matching by mitigating visual semantic hubs. arXiv preprint arXiv:1911.10097 (2019)","DOI":"10.1609\/aaai.v34i07.6823"},{"key":"33_CR20","doi-asserted-by":"crossref","unstructured":"Lu, J., Xiong, C., Parikh, D., Socher, R.: Knowing when to look: Adaptive attention via a visual sentinel for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). vol. 6 (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"33_CR21","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Hierarchical question-image co-attention for visual question answering. In: Advances In Neural Information Processing Systems. pp. 289\u2013297 (2016)"},{"key":"33_CR22","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)"},{"key":"33_CR23","doi-asserted-by":"crossref","unstructured":"Nam, H., Ha, J.W., Kim, J.: Dual attention networks for multimodal reasoning and matching. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 299\u2013307 (2017)","DOI":"10.1109\/CVPR.2017.232"},{"key":"33_CR24","doi-asserted-by":"crossref","unstructured":"Pedersoli, M., Lucas, T., Schmid, C., Verbeek, J.: Areas of attention for image captioning. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 1242\u20131250 (2017)","DOI":"10.1109\/ICCV.2017.140"},{"key":"33_CR25","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems. pp. 91\u201399 (2015)"},{"key":"33_CR26","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 815\u2013823 (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"33_CR27","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Camp: Cross-modal adaptive message passing for text-image retrieval. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 5764\u20135773 (2019)","DOI":"10.1109\/ICCV.2019.00586"},{"issue":"1","key":"33_CR28","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/s10994-010-5198-3","volume":"81","author":"J Weston","year":"2010","unstructured":"Weston, J., Bengio, S., Usunier, N.: Large scale image annotation: learning to rank with joint word-image embeddings. Mach. Learn. 81(1), 21\u201335 (2010)","journal-title":"Mach. Learn."},{"key":"33_CR29","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning. pp. 2048\u20132057 (2015)"},{"key":"33_CR30","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 21\u201329 (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"33_CR31","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4651\u20134659 (2016)","DOI":"10.1109\/CVPR.2016.503"},{"key":"33_CR32","doi-asserted-by":"crossref","unstructured":"You, Q., Zhang, Z., Luo, J.: End-to-end convolutional semantic embeddings. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 5735\u20135744 (2018)","DOI":"10.1109\/CVPR.2018.00601"},{"key":"33_CR33","first-page":"67","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Ling. 2, 67\u201378 (2014)","journal-title":"Trans. Assoc. Comput. Ling."},{"key":"33_CR34","doi-asserted-by":"crossref","unstructured":"Yu, D., Fu, J., Mei, T., Rui, Y.: Multi-level attention networks for visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4709\u20134717 (2017)","DOI":"10.1109\/CVPR.2017.446"},{"key":"33_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lu, H.: Deep cross-modal projection learning for image-text matching. In: Proceedings of the European Conference on Computer Vision (ECCV). pp. 686\u2013701 (2018)","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"33_CR36","unstructured":"Zheng, Z., Zheng, L., Garrett, M., Yang, Y., Shen, Y.D.: Dual-path convolutional image-text embedding with instance loss. arXiv preprint arXiv:1711.05535 (2017)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58601-0_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:15:48Z","timestamp":1732666548000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58601-0_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030586003","9783030586010"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58601-0_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"28 November 2020","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":"Glasgow","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":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"0","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":"27% - 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":"7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}