{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T13:48:45Z","timestamp":1742996925584,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030585167"},{"type":"electronic","value":"9783030585174"}],"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\/978-3-030-58517-4_40","type":"book-chapter","created":{"date-parts":[[2020,10,9]],"date-time":"2020-10-09T19:03:11Z","timestamp":1602270191000},"page":"683-698","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Guessing State Tracking for Visual Dialogue"],"prefix":"10.1007","author":[{"given":"Wei","family":"Pang","sequence":"first","affiliation":[]},{"given":"Xiaojie","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,10,10]]},"reference":[{"key":"40_CR1","unstructured":"Abbasnejad, E., Wu, Q., Abbasnejad, I., Shi, J., van den Hengel, A.: An active information seeking model for goal-oriented vision-and-language tasks. arXiv preprint arXiv:1812.06398 (2018)"},{"key":"40_CR2","doi-asserted-by":"crossref","unstructured":"Abbasnejad, E., Wu, Q., Shi, J., van den Hengel, A.: What\u2019s to know? Uncertainty as a guide to asking goal-oriented questions. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00428"},{"key":"40_CR3","doi-asserted-by":"crossref","unstructured":"Bani, G., et al.: Adding object detection skills to visual dialogue agents. In: ECCV (2018)","DOI":"10.1007\/978-3-030-11018-5_17"},{"key":"40_CR4","doi-asserted-by":"crossref","unstructured":"Chattopadhyay, P., et al.: Evaluating visual conversational agents via cooperative human-ai games. In: HCOMP (2017)","DOI":"10.1609\/hcomp.v5i1.13312"},{"key":"40_CR5","doi-asserted-by":"crossref","unstructured":"Das, A., et al.: Visual dialog. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.121"},{"key":"40_CR6","doi-asserted-by":"crossref","unstructured":"Deng, C., Wu, Q., Wu, Q., Hu, F., Lyu, F., Tan, M.: Visual grounding via accumulated attention. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00808"},{"key":"40_CR7","doi-asserted-by":"crossref","unstructured":"Fukui, A., Park, D.H., Yang, D., Rohrbach, A., Darrell, T., Rohrbach, M.: Multimodal compact bilinear pooling for visual question answering and visual grounding. arXiv preprint arXiv:1606.01847 (2016)","DOI":"10.18653\/v1\/D16-1044"},{"issue":"8","key":"40_CR8","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"40_CR9","doi-asserted-by":"crossref","unstructured":"Kim, H., Tan, H., Bansal, M.: Modality-balanced models for visual dialogue. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i05.6320"},{"key":"40_CR10","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"40_CR11","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":"40_CR12","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O., Yuille, A.L., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: CVPR, pp. 11\u201320 (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"40_CR13","doi-asserted-by":"crossref","unstructured":"Pang, W., Wang, X.: Visual dialogue state tracking for question generation. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6856"},{"key":"40_CR14","unstructured":"Seo, P.H., Lehrmann, A., Han, B., Sigal, L.: Visual reference resolution using attention memory for visual dialog. In: NeurIPS (2017)"},{"key":"40_CR15","unstructured":"Serban, I., Sordoni, A., Bengio, Y., Courville, A., Pineau, J.: Hierarchical neural network generative models for movie dialogues. In: arXiv preprint arXiv:1507.04808 (2015)"},{"key":"40_CR16","unstructured":"Shekhar, R., Venkatesh, A., Baumg\u00e4rtner, T., Bruni, E., Plank, B., Bernardi, R., Fern\u00e1ndez, R.: Ask no more: deciding when to guess in referential visual dialogue. In: COLING (2018)"},{"key":"40_CR17","doi-asserted-by":"crossref","unstructured":"Shekhar, R., et al.: Beyond task success: a closer look at jointly learning to see, ask, and guesswhat. In: NAACL (2019)","DOI":"10.18653\/v1\/N19-1265"},{"key":"40_CR18","doi-asserted-by":"crossref","unstructured":"Shukla, P., Elmadjian, C., Sharan, R., Kulkarni, V., Wang, W.Y., Turk, M.: What should I ask? Using conversationally informative rewards for goal-oriented visual dialogue. In: ACL (2019)","DOI":"10.18653\/v1\/P19-1646"},{"key":"40_CR19","doi-asserted-by":"crossref","unstructured":"Strub, F., de Vries, H., Mary, J., Piot, B., Courville, A., Pietquin, O.: End-to-end optimization of goal-driven and visually grounded dialogue systems. In: IJCAI (2017)","DOI":"10.24963\/ijcai.2017\/385"},{"key":"40_CR20","doi-asserted-by":"crossref","unstructured":"de Vries, H., Strub, F., Chandar, S., Pietquin, O., Larochelle, H., Courville, A.C.: Guesswhat?! Visual object discovery through multi-modal dialogue. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.475"},{"issue":"3\u20134","key":"40_CR21","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/978-1-4615-3618-5_2","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3\u20134), 229\u2013256 (1992). https:\/\/doi.org\/10.1007\/978-1-4615-3618-5_2","journal-title":"Mach. Learn."},{"key":"40_CR22","doi-asserted-by":"crossref","unstructured":"Xiao, F., Sigal, L., Lee, Y.J.: Weakly-supervised visual grounding of phrases with linguistic structures. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.558"},{"key":"40_CR23","doi-asserted-by":"crossref","unstructured":"Yang, T., Zha, Z.J., Zhang, H.: Making history matter: history-advantage sequence training for visual dialog. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00265"},{"key":"40_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46475-6_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Yu","year":"2016","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 69\u201385. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_5"},{"key":"40_CR25","doi-asserted-by":"crossref","unstructured":"Yu, L., Tan, H., Bansal, M., Berg, T.L.: A joint speaker-listener-reinforcer model for referring expressions. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.375"},{"key":"40_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, J., Wu, Q., Shen, C., Zhang, J., Lu, J., van den Hengel, A.: Asking the difficult questions: goal-oriented visual question generation via intermediate rewards. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01228-1_12"},{"key":"40_CR27","unstructured":"Zhao, R., Tresp, V.: Improving goal-oriented visual dialog agents via advanced recurrent nets with tempered policy gradient. In: IJCAI (2018)"},{"key":"40_CR28","doi-asserted-by":"crossref","unstructured":"Zhao, R., Tresp, V.: Efficient visual dialog policy learning via positive memory retention. In: NeurIPS (2018)","DOI":"10.1109\/SLT.2018.8639617"}],"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\/978-3-030-58517-4_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T00:17:58Z","timestamp":1728433078000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58517-4_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585167","9783030585174"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58517-4_40","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":"10 October 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)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}