{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T07:06:26Z","timestamp":1747119986751,"version":"3.40.3"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030585914"},{"type":"electronic","value":"9783030585921"}],"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\/978-3-030-58592-1_10","type":"book-chapter","created":{"date-parts":[[2020,11,3]],"date-time":"2020-11-03T00:34:03Z","timestamp":1604363643000},"page":"153-169","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Describing Unseen Videos via Multi-modal Cooperative Dialog Agents"],"prefix":"10.1007","author":[{"given":"Ye","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,3]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Alamri, H., et al.: Audio visual scene-aware dialog. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00774"},{"key":"10_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1007\/978-3-319-46454-1_24","volume-title":"Computer Vision \u2013 ECCV 2016","author":"P Anderson","year":"2016","unstructured":"Anderson, P., Fernando, B., Johnson, M., Gould, S.: SPICE: semantic propositional image caption evaluation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 382\u2013398. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_24"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"10_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/978-3-030-01246-5_27","volume-title":"Computer Vision \u2013 ECCV 2018","author":"R Arandjelovi\u0107","year":"2018","unstructured":"Arandjelovi\u0107, R., Zisserman, A.: Objects that sound. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 451\u2013466. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_27"},{"key":"10_CR6","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: ICLR (2015)"},{"key":"10_CR7","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372 (2005)"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: SCA-CNN: spatial and channel-wise attention in convolutional networks for image captioning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.667"},{"key":"10_CR9","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.cviu.2017.10.001","volume":"163","author":"A Das","year":"2017","unstructured":"Das, A., Agrawal, H., Zitnick, L., Parikh, D., Batra, D.: Human attention in visual question answering: do humans and deep networks look at the same regions? Comput. Vis. Image Underst. 163, 90\u2013100 (2017)","journal-title":"Comput. Vis. Image Underst."},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Das, A., et al.: Visual dialog. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.121"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Das, A., Kottur, S., Moura, J.M., Lee, S., Batra, D.: Learning cooperative visual dialog agents with deep reinforcement learning. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.321"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"De Vries, H., Strub, F., Chandar, S., Pietquin, O., Larochelle, H., Courville, A.: Guesswhat?! Visual object discovery through multi-modal dialogue. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.475"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Gan, Z., Cheng, Y., Kholy, A., Li, L., Liu, J., Gao, J.: Multi-step reasoning via recurrent dual attention for visual dialog. In: ACL (2019)","DOI":"10.18653\/v1\/P19-1648"},{"key":"10_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1007\/978-3-030-01219-9_3","volume-title":"Computer Vision \u2013 ECCV 2018","author":"R Gao","year":"2018","unstructured":"Gao, R., Feris, R., Grauman, K.: Learning to separate object sounds by watching unlabeled video. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 36\u201354. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_3"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: CVPR (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Hershey, S., et al.: CNN architectures for large-scale audio classification. In: ICASSP. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Hori, C., et al.: End-to-end audio visual scene-aware dialog using multimodal attention-based video features. In: ICASSP. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8682583"},{"key":"10_CR19","unstructured":"Hudson, D.A., Manning, C.D.: Compositional attention networks for machine reasoning. In: ICLR (2018)"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Jain, U., Lazebnik, S., Schwing, A.G.: Two can play this game: visual dialog with discriminative question generation and answering. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00603"},{"key":"10_CR21","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NeurIPS (2012)"},{"key":"10_CR22","unstructured":"Lee, S.W., Heo, Y.J., Zhang, B.T.: Answerer in questioner\u2019s mind: information theoretic approach to goal-oriented visual dialog. In: NeurIPS (2018)"},{"key":"10_CR23","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"10_CR25","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: CVPR (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"10_CR26","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Hierarchical question-image co-attention for visual question answering. In: NeurIPS (2016)"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Mahasseni, B., Lam, M., Todorovic, S.: Unsupervised video summarization with adversarial LSTM networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.318"},{"key":"10_CR28","unstructured":"Massiceti, D., Siddharth, N., Dokania, P.K., Torr, P.H.: FlipDial: a generative model for two-way visual dialogue. In: CVPR (2018)"},{"key":"10_CR29","doi-asserted-by":"crossref","unstructured":"Niu, Y., Zhang, H., Zhang, M., Zhang, J., Lu, Z., Wen, J.R.: Recursive visual attention in visual dialog. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00684"},{"key":"10_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1007\/978-3-030-01231-1_39","volume-title":"Computer Vision \u2013 ECCV 2018","author":"A Owens","year":"2018","unstructured":"Owens, A., Efros, A.A.: Audio-visual scene analysis with self-supervised multisensory features. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 639\u2013658. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_39"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: ACL (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"10_CR32","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.131"},{"key":"10_CR34","unstructured":"Santoro, A., et al.: A simple neural network module for relational reasoning. In: NeurIPS (2017)"},{"key":"10_CR35","doi-asserted-by":"crossref","unstructured":"Schwartz, I., Schwing, A.G., Hazan, T.: A simple baseline for audio-visual scene-aware dialog. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01283"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Schwartz, I., Yu, S., Hazan, T., Schwing, A.G.: Factor graph attention. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00214"},{"key":"10_CR37","unstructured":"Seo, P.H., Lehrmann, A., Han, B., Sigal, L.: Visual reference resolution using attention memory for visual dialog. In: NeurIPS (2017)"},{"key":"10_CR38","doi-asserted-by":"crossref","unstructured":"Shih, K.J., Singh, S., Hoiem, D.: Where to look: focus regions for visual question answering. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.499"},{"key":"10_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1007\/978-3-319-46448-0_31","volume-title":"Computer Vision \u2013 ECCV 2016","author":"GA Sigurdsson","year":"2016","unstructured":"Sigurdsson, G.A., Varol, G., Wang, X., Farhadi, A., Laptev, I., Gupta, A.: Hollywood in homes: crowdsourcing data collection for activity understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 510\u2013526. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_31"},{"key":"10_CR40","doi-asserted-by":"crossref","unstructured":"Song, X., Shi, Y., Chen, X., Han, Y.: Explore multi-step reasoning in video question answering. In: ACM Multimedia (2018)","DOI":"10.1145\/3240508.3240563"},{"key":"10_CR41","unstructured":"Szegedy, C., Toshev, A., Erhan, D.: Deep neural networks for object detection. In: Advances in Neural Information Processing Systems, pp. 2553\u20132561 (2013)"},{"key":"10_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1007\/978-3-030-01216-8_16","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Tian","year":"2018","unstructured":"Tian, Y., Shi, J., Li, B., Duan, Z., Xu, C.: Audio-visual event localization in unconstrained videos. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 252\u2013268. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_16"},{"key":"10_CR43","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: CIDEr: consensus-based image description evaluation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"10_CR44","doi-asserted-by":"crossref","unstructured":"Wang, B., Ma, L., Zhang, W., Liu, W.: Reconstruction network for video captioning. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00795"},{"key":"10_CR45","unstructured":"Wang, L., Schwing, A., Lazebnik, S.: Diverse and accurate image description using a variational auto-encoder with an additive Gaussian encoding space. In: NeurIPS (2017)"},{"key":"10_CR46","doi-asserted-by":"crossref","unstructured":"Wu, Q., Wang, P., Shen, C., Reid, I., Van Den Hengel, A.: Are you talking to me? Reasoned visual dialog generation through adversarial learning. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00639"},{"key":"10_CR47","doi-asserted-by":"crossref","unstructured":"Wu, Y., Zhu, L., Jiang, L., Yang, Y.: Decoupled novel object captioner. In: ACM Multimedia (2018)","DOI":"10.1145\/3240508.3240640"},{"key":"10_CR48","doi-asserted-by":"crossref","unstructured":"Wu, Y., Zhu, L., Yan, Y., Yang, Y.: Dual attention matching for audio-visual event localization. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00639"},{"key":"10_CR49","unstructured":"Xiong, C., Merity, S., Socher, R.: Dynamic memory networks for visual and textual question answering. In: ICML (2016)"},{"key":"10_CR50","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/978-3-319-46478-7_28","volume-title":"Computer Vision \u2013 ECCV 2016","author":"H Xu","year":"2016","unstructured":"Xu, H., Saenko, K.: Ask, attend and answer: exploring question-guided spatial attention for visual question answering. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 451\u2013466. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_28"},{"key":"10_CR51","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"10_CR52","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Li, Y., Qiu, Z., Mei, T.: Boosting image captioning with attributes. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.524"},{"key":"10_CR53","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.503"},{"key":"10_CR54","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1007\/978-3-030-01246-5_35","volume-title":"Computer Vision \u2013 ECCV 2018","author":"H Zhao","year":"2018","unstructured":"Zhao, H., Gan, C., Rouditchenko, A., Vondrick, C., McDermott, J., Torralba, A.: The sound of pixels. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 587\u2013604. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_35"}],"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\/978-3-030-58592-1_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:25:07Z","timestamp":1730593507000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58592-1_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585914","9783030585921"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58592-1_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"3 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.","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)"}}]}}