{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T23:18:58Z","timestamp":1742944738265,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030880064"},{"type":"electronic","value":"9783030880071"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/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":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-88007-1_41","type":"book-chapter","created":{"date-parts":[[2021,10,21]],"date-time":"2021-10-21T23:06:25Z","timestamp":1634857585000},"page":"498-510","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Variational Deep Representation Learning for Cross-Modal Retrieval"],"prefix":"10.1007","author":[{"given":"Chen","family":"Yang","sequence":"first","affiliation":[]},{"given":"Zongyong","family":"Deng","sequence":"additional","affiliation":[]},{"given":"Tianyu","family":"Li","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Libo","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,10,22]]},"reference":[{"key":"41_CR1","unstructured":"Belghazi, M.I., Baratin, A., Rajeswar, S., et al.: MINE: mutual information neural estimation. arXiv (2018)"},{"issue":"35","key":"41_CR2","doi-asserted-by":"publisher","first-page":"25697","DOI":"10.1007\/s11042-020-09251-4","volume":"79","author":"M Cornia","year":"2020","unstructured":"Cornia, M., Baraldi, L., Tavakoli, H.R., et al.: A unified cycle-consistent neural model for text and image retrieval. Multimedia Tools Appl. 79(35), 25697\u201325721 (2020)","journal-title":"Multimedia Tools Appl."},{"key":"41_CR3","unstructured":"Devlin, J., Chang, M.W., Lee, K., et al.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv (2018)"},{"issue":"3","key":"41_CR4","first-page":"571","volume":"19","author":"K Ding","year":"2016","unstructured":"Ding, K., Fan, B., Huo, C., Xiang, S., Pan, C.: Cross-modal hashing via rank-order preserving. IEEE TMM 19(3), 571\u2013585 (2016)","journal-title":"IEEE TMM"},{"key":"41_CR5","unstructured":"Faghri, F., Fleet, D.J., Kiros, J.R., et al.: Vse++: improving visual-semantic embeddings with hard negatives. arXiv (2017)"},{"issue":"2","key":"41_CR6","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1307\/mmj\/1029003026","volume":"31","author":"CR Givens","year":"1984","unstructured":"Givens, C.R., Shortt, R.M., et al.: A class of wasserstein metrics for probability distributions. Michigan Math. J. 31(2), 231\u2013240 (1984)","journal-title":"Michigan Math. J."},{"key":"41_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"41_CR8","unstructured":"Hjelm, R.D., Fedorov, A., Lavoie-Marchildon, S., et al.: Learning deep representations by mutual information estimation and maximization. In: ICLR (2018)"},{"issue":"4","key":"41_CR9","first-page":"973","volume":"21","author":"D Hu","year":"2018","unstructured":"Hu, D., Nie, F., Li, X.: Deep binary reconstruction for cross-modal hashing. IEEE TMM 21(4), 973\u2013985 (2018)","journal-title":"IEEE TMM"},{"key":"41_CR10","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: CVPR, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"41_CR11","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv (2013)"},{"issue":"1","key":"41_CR12","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1002\/asi.24373","volume":"72","author":"W Li","year":"2021","unstructured":"Li, W., Zheng, Y., Zhang, Y., et al.: Cross-modal retrieval with dual multi-angle self-attention. J. Assoc. Inf. Sci. Technol. 72(1), 46\u201365 (2021)","journal-title":"J. Assoc. Inf. Sci. Technol."},{"key":"41_CR13","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":"TY 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"},{"issue":"1","key":"41_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3300939","volume":"15","author":"R Liu","year":"2019","unstructured":"Liu, R., Zhao, Y., Wei, S., et al.: Modality-invariant image-text embedding for image-sentence matching. ACM Trans. Multimedia Comput. Commun. Appl. 15(1), 1\u201319 (2019)","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl."},{"key":"41_CR15","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1016\/j.patcog.2019.05.008","volume":"93","author":"Y Liu","year":"2019","unstructured":"Liu, Y., Guo, Y., Liu, L., et al.: CycleMatch: a cycle-consistent embedding network for image-text matching. Pattern Recogn. 93, 365\u2013379 (2019)","journal-title":"Pattern Recogn."},{"issue":"12","key":"41_CR16","first-page":"3101","volume":"22","author":"X Ma","year":"2020","unstructured":"Ma, X., Zhang, T., Xu, C.: Multi-level correlation adversarial hashing for cross-modal retrieval. IEEE TMM 22(12), 3101\u20133114 (2020)","journal-title":"IEEE TMM"},{"key":"41_CR17","doi-asserted-by":"crossref","unstructured":"Malisiewicz, T., Gupta, A., Efros, A.A.: Ensemble of exemplar-SVMs for object detection and beyond. In: ICCV, pp. 89\u201396. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126229"},{"key":"41_CR18","doi-asserted-by":"crossref","unstructured":"Peters, M.E., Neumann, M., Iyyer, M., et al.: Deep contextualized word representations. arXiv (2018)","DOI":"10.18653\/v1\/N18-1202"},{"key":"41_CR19","doi-asserted-by":"crossref","unstructured":"Sarafianos, N., Xu, X., Kakadiaris, I.A.: Adversarial representation learning for text-to-image matching. In: ICCV, pp. 5814\u20135824 (2019)","DOI":"10.1109\/ICCV.2019.00591"},{"key":"41_CR20","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv (2014)"},{"key":"41_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"711","DOI":"10.1007\/978-3-030-11018-5_62","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"D Sur\u00eds","year":"2019","unstructured":"Sur\u00eds, D., Duarte, A., Salvador, A., Torres, J., Gir\u00f3-i-Nieto, X.: Cross-modal embeddings for video and audio retrieval. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11132, pp. 711\u2013716. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11018-5_62"},{"key":"41_CR22","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, Y., Lazebnik, S.: Learning deep structure-preserving image-text embeddings. In: CVPR, pp. 5005\u20135013 (2016)","DOI":"10.1109\/CVPR.2016.541"},{"key":"41_CR23","doi-asserted-by":"crossref","unstructured":"Wang, S., Chen, Y., Zhuo, J., et al.: Joint global and co-attentive representation learning for image-sentence retrieval. In: ACM MM, pp. 1398\u20131406 (2018)","DOI":"10.1145\/3240508.3240535"},{"key":"41_CR24","doi-asserted-by":"crossref","unstructured":"Wu, H., Mao, J., Zhang, Y., et al.: Unified visual-semantic embeddings: bridging vision and language with structured meaning representations. In: CVPR, pp. 6609\u20136618 (2019)","DOI":"10.1109\/CVPR.2019.00677"},{"key":"41_CR25","doi-asserted-by":"crossref","unstructured":"You, Q., Zhang, Z., Luo, J.: End-to-end convolutional semantic embeddings. In: CVPR, pp. 5735\u20135744 (2018)","DOI":"10.1109\/CVPR.2018.00601"},{"key":"41_CR26","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., et al.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguist. 2, 67\u201378 (2014)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"41_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1007\/978-3-030-01246-5_42","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Zhang","year":"2018","unstructured":"Zhang, Y., Lu, H.: Deep cross-modal projection learning for image-text matching. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 707\u2013723. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_42"},{"issue":"2","key":"41_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3383184","volume":"16","author":"Z Zheng","year":"2020","unstructured":"Zheng, Z., Zheng, L., Garrett, M., et al.: Dual-path convolutional image-text embeddings with instance loss. ACM Trans. Multimedia Comput. Commun. Appl. 16(2), 1\u201323 (2020)","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-88007-1_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T19:58:26Z","timestamp":1710359906000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-88007-1_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030880064","9783030880071"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-88007-1_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"22 October 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 October 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 November 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.prcv.cn\/2021\/index_en.html","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"513","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":"201","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":"39% - 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":"5","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":"There were 30 oral and 171 poster presentations at the conference.","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)"}}]}}