{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T14:05:20Z","timestamp":1791295520286,"version":"4.1.0"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585792","type":"print"},{"value":"9783030585808","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\/978-3-030-58580-8_44","type":"book-chapter","created":{"date-parts":[[2020,12,2]],"date-time":"2020-12-02T07:03:09Z","timestamp":1606892589000},"page":"752-768","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":92,"title":["Contrastive Learning for Weakly Supervised Phrase Grounding"],"prefix":"10.1007","author":[{"given":"Tanmay","family":"Gupta","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arash","family":"Vahdat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gal","family":"Chechik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaodong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan","family":"Kautz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Derek","family":"Hoiem","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,12,3]]},"reference":[{"key":"44_CR1","doi-asserted-by":"crossref","unstructured":"Akbari, H., Karaman, S., Bhargava, S., Chen, B., Vondrick, C., Chang, S.F.: Multi-level multimodal common semantic space for image-phrase grounding. In: CVPR (2018)","DOI":"10.1109\/CVPR.2019.01276"},{"key":"44_CR2","doi-asserted-by":"crossref","unstructured":"Alberti, C., Ling, J., Collins, M., Reitter, D.: Fusion of detected objects in text for visual question answering. In: EMNLP (2019)","DOI":"10.18653\/v1\/D19-1219"},{"key":"44_CR3","unstructured":"Alemi, A.A., Fischer, I., Dillon, J.V., Murphy, K.: Deep variational information bottleneck. In: ICLR (2017)"},{"key":"44_CR4","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: CVPR (2017)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"44_CR5","unstructured":"Bachman, P., Hjelm, R.D., Buchwalter, W.: Learning representations by maximizing mutual information across views. arXiv preprint arXiv:1906.00910 (2019)"},{"key":"44_CR6","unstructured":"Belghazi, M.I., et al.: Mutual information neural estimation. In: ICML (2018)"},{"key":"44_CR7","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":"44_CR8","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. arXiv preprint arXiv:2002.05709 (2020)"},{"key":"44_CR9","unstructured":"Chen, Y.C., et al.: UNITER: Learning universal image-text representations. arXiv preprint arXiv:1909.11740 (2019)"},{"key":"44_CR10","doi-asserted-by":"crossref","unstructured":"Choe, J., Oh, S.J., Lee, S., Chun, S., Akata, Z., Shim, H.: Evaluating weakly supervised object localization methods right. ArXiv (2020)","DOI":"10.1109\/CVPR42600.2020.00320"},{"key":"44_CR11","doi-asserted-by":"crossref","unstructured":"Datta, S., Sikka, K., Roy, A., Ahuja, K., Parikh, D., Divakaran, A.: Align2Ground: weakly supervised phrase grounding guided by image-caption alignment. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00269"},{"key":"44_CR12","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT (2018)"},{"key":"44_CR13","doi-asserted-by":"crossref","unstructured":"Fang, H., et al.: From captions to visual concepts and back. In: CVPR (2014)","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"44_CR14","unstructured":"Gutmann, M., Hyv\u00e4rinen, A.: Noise-contrastive estimation: A new estimation principle for unnormalized statistical models. In: AISTATS (2010)"},{"key":"44_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. arXiv preprint arXiv:1911.05722 (2019)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"44_CR16","unstructured":"H\u00e9naff, O.J., Razavi, A., Doersch, C., Eslami, S., Oord, A.V.D.: Data-efficient image recognition with contrastive predictive coding. arXiv preprint arXiv:1905.09272 (2019)"},{"key":"44_CR17","unstructured":"Hjelm, R.D., et al.: Learning deep representations by mutual information estimation and maximization. In: ICLR (2019)"},{"key":"44_CR18","unstructured":"Ilse, M., Tomczak, J.M., Welling, M.: Attention-based deep multiple instance learning. In: ICML (2018)"},{"key":"44_CR19","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)"},{"key":"44_CR20","unstructured":"Kim, H., Mnih, A.: Disentangling by factorising. In: ICML (2018)"},{"key":"44_CR21","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"44_CR22","doi-asserted-by":"crossref","unstructured":"Li, G., Duan, N., Fang, Y., Jiang, D., Zhou, M.: Unicoder-VL: a universal encoder for vision and language by cross-modal pre-training. arXiv preprint arXiv:1908.06066 (2019)","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"44_CR23","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: VisualBERT: a simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)"},{"key":"44_CR24","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: VilBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: NeurIPS (2019)"},{"key":"44_CR25","unstructured":"Maron, O., Lozano-P\u00e9rez, T.: A framework for multiple-instance learning. In: NeurIPS (1998)"},{"key":"44_CR26","unstructured":"McAllester, D., Stratos, K.: Formal limitations on the measurement of mutual information. arXiv preprint arXiv:1811.04251 (2018)"},{"key":"44_CR27","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: NIPS (2013)"},{"key":"44_CR28","doi-asserted-by":"crossref","unstructured":"Misra, I., van der Maaten, L.: Self-supervised learning of pretext-invariant representations. arXiv preprint arXiv:1912.01991 (2019)","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"44_CR29","unstructured":"Mnih, A., Kavukcuoglu, K.: Learning word embeddings efficiently with noise-contrastive estimation. In: NeurIPS (2013)"},{"key":"44_CR30","unstructured":"Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv (2018)"},{"key":"44_CR31","unstructured":"Poole, B., Ozair, S., Van Den Oord, A., Alemi, A., Tucker, G.: On variational bounds of mutual information. In: ICML (2019)"},{"key":"44_CR32","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurIPS (2015)"},{"key":"44_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1007\/978-3-319-46448-0_49","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Rohrbach","year":"2016","unstructured":"Rohrbach, A., Rohrbach, M., Hu, R., Darrell, T., Schiele, B.: Grounding of textual phrases in images by reconstruction. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 817\u2013834. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_49"},{"key":"44_CR34","unstructured":"Song, J., Ermon, S.: Understanding the limitations of variational mutual information estimators. In: ICLR (2020)"},{"key":"44_CR35","unstructured":"Su, W., et al.: VL-BERT: pre-training of generic visual-linguistic representations (2020)"},{"key":"44_CR36","unstructured":"Sun, C., Baradel, F., Murphy, K., Schmid, C.: Contrastive bidirectional transformer for temporal representation learning. arXiv preprint arXiv:1906.05743 (2019)"},{"key":"44_CR37","doi-asserted-by":"crossref","unstructured":"Sun, C., Myers, A., Vondrick, C., Murphy, K., Schmid, C.: VideoBERT: a joint model for video and language representation learning. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00756"},{"key":"44_CR38","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers. In: EMNLP (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"44_CR39","doi-asserted-by":"crossref","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive multiview coding. arXiv preprint arXiv:1906.05849 (2019)","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"44_CR40","unstructured":"Tschannen, M., Djolonga, J., Rubenstein, P.K., Gelly, S., Lucic, M.: On mutual information maximization for representation learning. In: ICLR (2020)"},{"key":"44_CR41","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"44_CR42","doi-asserted-by":"crossref","unstructured":"Wang, J., Specia, L.: Phrase localization without paired training examples. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00476"},{"key":"44_CR43","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"key":"44_CR44","doi-asserted-by":"crossref","unstructured":"Yeh, R.A., Do, M.N., Schwing, A.G.: Unsupervised textual grounding: linking words to image concepts. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00641"},{"key":"44_CR45","doi-asserted-by":"crossref","unstructured":"Zhou, L., Palangi, H., Zhang, L., Hu, H., Corso, J.J., Gao, J.: Unified vision-language pre-training for image captioning and VQA. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.7005"}],"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\/978-3-030-58580-8_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:17:06Z","timestamp":1733098626000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58580-8_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585792","9783030585808"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58580-8_44","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":"3 December 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)"}}]}}