{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:20:54Z","timestamp":1775578854985,"version":"3.50.1"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585853","type":"print"},{"value":"9783030585860","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\/978-3-030-58586-0_2","type":"book-chapter","created":{"date-parts":[[2020,11,29]],"date-time":"2020-11-29T17:02:42Z","timestamp":1606669362000},"page":"18-34","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":135,"title":["Consensus-Aware Visual-Semantic Embedding for Image-Text Matching"],"prefix":"10.1007","author":[{"given":"Haoran","family":"Wang","sequence":"first","affiliation":[]},{"given":"Ying","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Zhong","family":"Ji","sequence":"additional","affiliation":[]},{"given":"Yanwei","family":"Pang","sequence":"additional","affiliation":[]},{"given":"Lin","family":"Ma","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,30]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and VQA. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: Visual question answering. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"2_CR3","unstructured":"Bruna, J., Zaremba, W., Szlam, A., LeCun, Y.: Spectral networks and locally connected networks on graphs. In: ICLR (2013)"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Chen, J., Chen, X., Ma, L., Jie, Z., Chua, T.S.: Temporally grounding natural sentence in video (2018)","DOI":"10.18653\/v1\/D18-1015"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Chen, K., Gao, J., Nevatia, R.: Knowledge aided consistency for weakly supervised phrase grounding. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00425"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z.M., Wei, X.S., Wang, P., Guo, Y.: Multi-label image recognition with graph convolutional networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00532"},{"key":"2_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1007\/978-3-319-10590-1_4","volume-title":"Computer Vision","author":"J Deng","year":"2014","unstructured":"Deng, J., et al.: Large-scale object classification using label relation graphs. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 48\u201364. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_4"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Engilberge, M., Chevallier, L., P\u00e9rez, P., Cord, M.: Finding beans in burgers: deep semantic-visual embedding with localization. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00419"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Fang, H., et al.: From captions to visual concepts and back. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"2_CR10","unstructured":"Fartash, F., Fleet, D., Kiros, J., Fidler, S.: VSE++: improved visual-semantic embeddings. In: BMVC (2018)"},{"key":"2_CR11","unstructured":"Frome, A., et al.: Devise: a deep visual-semantic embedding model. In: NIPS (2013)"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Gu, J., Zhao, H., Lin, Z., Li, S., Cai, J., Ling, M.: Scene graph generation with external knowledge and image reconstruction. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00207"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Hou, J., Wu, X., Zhao, W., Luo, J., Jia, Y.: Joint syntax representation learning and visual cue translation for video captioning. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00901"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Hu, Z., Luo, Y., Lin, J., Yan, Y., Chen, J.: Multi-level visual-semantic alignments with relation-wise dual attention network for image and text matching. In: IJCAI (2019)","DOI":"10.24963\/ijcai.2019\/111"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Huang, Y., Wu, Q., Song, C., Wang, L.: Learning semantic concepts and order for image and sentence matching. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00645"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Ji, Z., Wang, H., Han, J., Pang, Y.: Saliency-guided attention network for image-sentence matching. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00585"},{"key":"2_CR17","unstructured":"Karpathy, A., Joulin, A., Li, F.F.: Deep fragment embeddings for bidirectional image sentence mapping. In: NIPS (2014)"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Li, F.F.: Deep visual-semantic alignments for generating image descriptions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"2_CR19","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2014)"},{"key":"2_CR20","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2016)"},{"key":"2_CR21","unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.: Unifying visual-semantic embeddings with multimodal neural language models. In: NIPS Workshop (2014)"},{"key":"2_CR22","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Lee, K.H., Chen, X., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"2_CR24","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","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":"2_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Y., Guo, Y., Bakker, E.M., Lew, M.S.: Learning a recurrent residual fusion network for multimodal matching. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.442"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Ma, L., Lu, Z., Shang, L., Li, H.: Multimodal convolutional neural networks for matching image and sentence. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.301"},{"issue":"7","key":"2_CR27","first-page":"2250","volume":"30","author":"L Ma","year":"2020","unstructured":"Ma, L., Jiang, W., Jie, Z., Jiang, Y., Liu, W.: Matching image and sentence with multi-faceted representations. IEEE Trans. Circ. Syst. Video Technol. 30(7), 2250\u20132261 (2020)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Ma, L., Lu, Z., Li, H.: Learning to answer questions from image using convolutional neural network (2016)","DOI":"10.1609\/aaai.v30i1.10442"},{"key":"2_CR29","first-page":"2579","volume":"9","author":"LVD Maaten","year":"2008","unstructured":"Maaten, L.V.D., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res."},{"key":"2_CR30","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Huang, Z., Yuille, A.: Deep captioning with multimodal recurrent neural networks (M-RNN). In: ICLR (2015)"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Marino, K., Salakhutdinov, R., Gupta, A.: The more you know: using knowledge graphs for image classification. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.10"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Nam, H., Ha, J., Kim, J.: Dual attention networks for multimodal reasoning and matching. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.232"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Plummer, B., Wang, L., Cervantes, C., Caicedo, J., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Plummer, B., Mallya, A., Cervantes, C., Hockenmaier, J., Lazebnik, S.: Phrase localization and visual relationship detection with comprehensive image-language cues. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.213"},{"key":"2_CR36","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"issue":"11","key":"2_CR37","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Sig. Process. 45(11), 2673\u20132681 (1997)","journal-title":"IEEE Trans. Sig. Process."},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"Shi, B., Ji, L., Lu, P., Niu, Z., Duan, N.: Knowledge aware semantic concept expansion for image-text matching. In: IJCAI (2019)","DOI":"10.24963\/ijcai.2019\/720"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Song, Y., Soleymani, M.: Polysemous visual-semantic embedding for cross-modal retrieval. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00208"},{"key":"2_CR40","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"Wang, B., Ma, L., Zhang, W., Liu, W.: Reconstruction network for video captioning (2018)","DOI":"10.1109\/CVPR.2018.00795"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Wang, J., Jiang, W., Ma, L., Liu, W., Xu, Y.: Bidirectional attentive fusion with context gating for dense video captioning (2018)","DOI":"10.1109\/CVPR.2018.00751"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, Y., Lazebnik, S.: Learning deep structure-preserving image-text embeddings. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.541"},{"issue":"10","key":"2_CR44","doi-asserted-by":"publisher","first-page":"2413","DOI":"10.1109\/TPAMI.2017.2754246","volume":"40","author":"P Wang","year":"2018","unstructured":"Wang, P., Wu, Q., Shen, C., Dick, A., van den Hengel, A.: FVQA: Fact-based visual question answering. IEEE Trans. Pattern Anal. Mach. Intell. 40(10), 2413\u20132427 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR45","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Camp: Cross-modal adaptive message passing for text-image retrieval. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00586"},{"key":"2_CR46","doi-asserted-by":"crossref","unstructured":"Wehrmann, J., Souza, D.M., Lopes, M.A., Barros, R.C.: Language-agnostic visual-semantic embeddings. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00590"},{"key":"2_CR47","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Ma, L., Wang, J., Liu, W., Zhu, W.: Semantic conditioned dynamtic modulation for temporal sentence grounding in videos (2019)","DOI":"10.1109\/TPAMI.2020.3038993"},{"key":"2_CR48","doi-asserted-by":"publisher","unstructured":"Zhang, W., Wang, B., Ma, L., Liu, W.: Reconstruct and represent video contents for captioning via reinforcement learning (2019). https:\/\/doi.org\/10.1109\/TPAMI.2019.2920899","DOI":"10.1109\/TPAMI.2019.2920899"},{"key":"2_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lu, H.: Deep cross-modal projection learning for image-text matching. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01246-5_42"}],"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\/978-3-030-58586-0_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T00:04:31Z","timestamp":1732838671000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58586-0_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585853","9783030585860"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58586-0_2","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":"30 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)"}}]}}