{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T17:55:17Z","timestamp":1772042117544,"version":"3.50.1"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012663","type":"print"},{"value":"9783030012670","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-01267-0_10","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T17:02:36Z","timestamp":1538845356000},"page":"160-178","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":69,"title":["Visual Coreference Resolution in Visual Dialog Using Neural Module Networks"],"prefix":"10.1007","author":[{"given":"Satwik","family":"Kottur","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jos\u00e9 M. F.","family":"Moura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Devi","family":"Parikh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dhruv","family":"Batra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcus","family":"Rohrbach","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,7]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, A., Batra, D., Parikh, D.: Analyzing the behavior of visual question answering models. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) (2016)","DOI":"10.18653\/v1\/D16-1203"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, P. et al.: Bottom-up and top-down attention for image captioning and vqa. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Learning to compose neural networks for question answering (2016)","DOI":"10.18653\/v1\/N16-1181"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Neural module networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.12"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Hendricks, L.A., Wang, O., Shechtman, E., Sivic, J., Darrell, T., Russell, B.: Localizing moments in video with natural language. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.618"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Antol, S. et al.: Vqa: Visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"10_CR7","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: Proceedings of the International Conference on Learning Representations (ICLR) (2015)"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Bergsma, S., Lin, D.: Bootstrapping path-based pronoun resolution. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL). Association for Computational Linguistics (2006)","DOI":"10.3115\/1220175.1220180"},{"issue":"46","key":"10_CR9","doi-asserted-by":"publisher","first-page":"53","DOI":"10.2307\/2001990","volume":"8","author":"Arthur W. Burks","year":"1954","unstructured":"Burks, A.W., Warren, D.W., Wright, J.B.: An analysis of a logical machine using parenthesis-free notation. Math. Tables Other Aids Comput. 8(46), 53\u201357 (1954). http:\/\/www.jstor.org\/stable\/2001990","journal-title":"Mathematical Tables and Other Aids to Computation"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Clark, K., Manning, C.D.: Deep reinforcement learning for mention-ranking coreference models. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) (2016)","DOI":"10.18653\/v1\/D16-1245"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Das, A. et al.: Visual dialog. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.121"},{"key":"10_CR12","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. arXiv preprint arXiv:1703.06585 (2017)","DOI":"10.1109\/ICCV.2017.321"},{"key":"10_CR13","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. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) (2016)","DOI":"10.18653\/v1\/D16-1044"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Geman, D., Geman, S., Hallonquist, N., Younes, L.: Visual Turing Test for computer vision systems. In: Proceedings of the National Academy of Sciences (2015)","DOI":"10.1073\/pnas.1422953112"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the v in vqa matter: elevating the role of image understanding in visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"10_CR16","unstructured":"Grice, H.P.: Logic and conversation. In: Cole, P., Morgan, J.L. (eds.) Syntax and Semantics: Vol. 3: Speech Acts, pp. 41\u201358. Academic Press, New York (1975). http:\/\/www.ucl.ac.uk\/ls\/studypacks\/Grice-Logic.pdf"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Hu, R., Andreas, J., Rohrbach, M., Darrell, T., Saenko, K.: Learning to reason: End-to-end module networks for visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.93"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Hu, R., Xu, H., Rohrbach, M., Feng, J., Saenko, K., Darrell, T.: Natural language object retrieval. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.493"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., van der Maaten, L., Fei-Fei, L., Zitnick, C.L., Girshick, R.: Clevr: a diagnostic dataset for compositional language and elementary visual reasoning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Johnson, J. et al.: Inferring and executing programs for visual reasoning. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.325"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Kong, C., Lin, D., Bansal, M., Urtasun, R., Fidler, S.: What are you talking about? text-to-image coreference. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.455"},{"key":"10_CR23","unstructured":"LeCun, Y., Cortes, C.: MNIST handwritten digit database (2010). http:\/\/yann.lecun.com\/exdb\/mnist\/"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Lin, D., Fidler, S., Kong, C., Urtasun, R.: Visual semantic search: Retrieving videos via complex textual queries. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.340"},{"key":"10_CR25","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"Tsung-Yi Lin","year":"2014","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: Proceedings of the European Conference on Computer Vision (ECCV) (2014)"},{"key":"10_CR26","unstructured":"Lu, J., Kannan, A., Yang, J., Parikh, D., Batra, D.: Best of both worlds: transferring knowledge from discriminative learning to a generative visual dialog model. In: Advances in Neural Information Processing Systems (NIPS) (2017)"},{"key":"10_CR27","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Hierarchical question-image co-attention for visual question answering. In: Advances in Neural Information Processing Systems (NIPS) (2016)"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Malinowski, M., Rohrbach, M., Fritz, M.: Ask your neurons: a neural-based approach to answering questions about images. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.9"},{"key":"10_CR29","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O., Yuille, A., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"10_CR30","unstructured":"Massiceti, D., Siddharth, N., Dokania, P.K., Torr, P.H.S.: Flipdial: A generative model for two-way visual dialogue (2018)"},{"key":"10_CR31","unstructured":"Mitchell, M., van Deemter, K., Reiter, E.: Generating expressions that refer to visible objects. In: Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1174\u20131184. Association for Computational Linguistics, Atlanta, Georgia, June 2013. http:\/\/www.aclweb.org\/anthology\/N13-1137"},{"key":"10_CR32","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: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Ramanathan, V., Joulin, A., Liang, P., Fei-Fei, L.: Linking people in videos with \u201ctheir\u201d names using coreference resolution. In: Proceedings of the European Conference on Computer Vision (ECCV) (2014)","DOI":"10.1007\/978-3-319-10590-1_7"},{"key":"10_CR34","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1162\/tacl_a_00207","volume":"1","author":"M Regneri","year":"2013","unstructured":"Regneri, M., Rohrbach, M., Wetzel, D., Thater, S., Schiele, B., Pinkal, M.: Grounding action descriptions in videos. Trans. Assoc. Comput. Linguist. (TACL) 1, 25\u201336 (2013)","journal-title":"Trans. Assoc. Comput. Linguist. (TACL)"},{"key":"10_CR35","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Rohrbach, M., Hu, R., Darrell, T., Schiele, B.: Grounding of textual phrases in images by reconstruction. In: Proceedings of the European Conference on Computer Vision (ECCV) (2016)","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Rohrbach, M., Tang, S., Oh, S.J., Schiele, B.: Generating descriptions with grounded and co-referenced people. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.447"},{"key":"10_CR37","unstructured":"Seo, P.H., Lehrmann, A., Han, B., Sigal, L.: Visual reference resolution using attention memory for visual dialog. In: Advances in Neural Information Processing Systems (NIPS) (2017)"},{"key":"10_CR38","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of the International Conference on Learning Representations (ICLR) (2015)"},{"key":"10_CR39","doi-asserted-by":"crossref","unstructured":"Strub, F., de Vries, H., Mary, J., Piot, B., Courville, A.C., Pietquin, O.: End-to-end optimization of goal-driven and visually grounded dialogue systems. In: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI) (2017)","DOI":"10.24963\/ijcai.2017\/385"},{"key":"10_CR40","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.475"},{"key":"10_CR41","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, Y., Lazebnik, S.: Learning deep structure-preserving image-text embeddings. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.541"},{"key":"10_CR42","unstructured":"Weston, J., Chopra, S., Bordes, A.: Memory networks. In: Proceedings of the International Conference on Learning Representations (ICLR) (2015)"},{"key":"10_CR43","unstructured":"Winograd, T.: Procedures as a representation for data in a computer program for understanding natural language. Technical report, DTIC Document (1971)"},{"key":"10_CR44","volume-title":"Understanding Natural Language","author":"T Winograd","year":"1972","unstructured":"Winograd, T.: Understanding Natural Language. Academic Press Inc., Orlando, FL, USA (1972)"},{"key":"10_CR45","unstructured":"Yu, H., Siskind, J.M.: Grounded language learning from videos described with sentences. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL) (2013)"},{"key":"10_CR46","doi-asserted-by":"crossref","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: Proceedings of the European Conference on Computer Vision (ECCV) (2016)","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"10_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, P., Goyal, Y., Summers-Stay, D., Batra, D., Parikh, D.: Yin and Yang: balancing and answering binary visual questions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.542"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01267-0_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T00:11:11Z","timestamp":1665015071000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01267-0_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012663","9783030012670"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01267-0_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"7 October 2018","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":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}