{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T04:11:10Z","timestamp":1743135070599,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030110178"},{"type":"electronic","value":"9783030110185"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-11018-5_15","type":"book-chapter","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T05:50:50Z","timestamp":1548309050000},"page":"162-172","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["How Clever Is the FiLM Model, and How Clever Can it Be?"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2361-115X","authenticated-orcid":false,"given":"Alexander","family":"Kuhnle","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8344-9724","authenticated-orcid":false,"given":"Huiyuan","family":"Xie","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0347-946X","authenticated-orcid":false,"given":"Ann","family":"Copestake","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,1,23]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, A., Batra, D., Parikh, D.: Analyzing the behavior of visual question answering models. In: Su, J., Duh, K., Carreras, X. (eds.) Proceedings of the Conference on Empirical Methods in Natural Language Processing. EMNLP 2016, pp. 1955\u20131960. Association for Computational Linguistics, Stroudsburg (2016)","DOI":"10.18653\/v1\/D16-1203"},{"key":"15_CR2","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. IEEE Computer Society, Washington, DC (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: Proceedings of the 26th Annual International Conference on Machine Learning. ICML 2009, pp. 41\u201348. ACM, New York (2009)","DOI":"10.1145\/1553374.1553380"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Bowman, S.R., Angeli, G., Potts, C., Manning, C.D.: A large annotated corpus for learning natural language inference. In: M\u00e0rquez, L., Callison-Burch, C., Su, J. (eds.) Proceedings of the Conference on Empirical Methods in Natural Language Processing. EMNLP 2015, pp. 632\u2013642. Association for Computational Linguistics, Stroudsburg (2015)","DOI":"10.18653\/v1\/D15-1075"},{"issue":"1","key":"15_CR5","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/0010-0277(93)90058-4","volume":"48","author":"JL Elman","year":"1993","unstructured":"Elman, J.L.: Learning and development in neural networks: the importance of starting small. Cognition 48(1), 71\u201399 (1993)","journal-title":"Cognition"},{"key":"15_CR6","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, pp. 6325\u20136334. IEEE Computer Society, Washington, DC (2017)","DOI":"10.1109\/CVPR.2017.670"},{"issue":"2","key":"15_CR7","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1109\/MIS.2009.36","volume":"24","author":"A Halevy","year":"2009","unstructured":"Halevy, A., Norvig, P., Pereira, F.: The unreasonable effectiveness of data. IEEE Intell. Syst. 24(2), 8\u201312 (2009)","journal-title":"IEEE Intell. Syst."},{"key":"15_CR8","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. IEEE Computer Society, Washington, DC (2017)","DOI":"10.1109\/ICCV.2017.93"},{"key":"15_CR9","unstructured":"Hudson, D.A., Manning, C.D.: Compositional attention networks for machine reasoning. In: Proceedings of the International Conference on Learning Representations. ICLR 2018 (2018)"},{"key":"15_CR10","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 2017. IEEE Computer Society, Washington, DC (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"15_CR11","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. IEEE Computer Society, Washington, DC (2017)","DOI":"10.1109\/ICCV.2017.325"},{"key":"15_CR12","unstructured":"Kuhnle, A., Copestake, A.: ShapeWorld - a new test methodology for multimodal language understanding. arXiv e-prints 1704.04517 (2017)"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Kuhnle, A., Copestake, A.: Deep learning evaluation using deep linguistic processing. In: Walker, M., Ji, H., Stent, A. (eds.) Proceedings of the Workshop on Generalization in the Age of Deep Learning. NAACL 2018, pp. 17\u201323. Association for Computational Linguistics, Stroudsburg (2018)","DOI":"10.18653\/v1\/W18-1003"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Mascharka, D., Tran, P., Soklaski, R., Majumdar, A.: Transparency by design: closing the gap between performance and interpretability in visual reasoning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2018. IEEE Computer Society, Washington, DC (2018)","DOI":"10.1109\/CVPR.2018.00519"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Mudrakarta, P.K., Taly, A., Sundararajan, M., Dhamdhere, K.: Did the model understand the question? arXiv e-prints 1805.05492 (2018)","DOI":"10.18653\/v1\/P18-1176"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., de Vries, H., Dumoulin, V., Courville, A.C.: FiLM: visual reasoning with a general conditioning layer. In: AAAI. AAAI Press, Palo Alto (2018)","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: SQuAD: 100,000+ questions for machine comprehension of text. In: Su, J., Duh, K., Carreras, X. (eds.) Proceedings of the Conference on Empirical Methods in Natural Language Processing. EMNLP 2016, pp. 2383\u20132392. Association for Computational Linguistics, Stroudsburg (2016)","DOI":"10.18653\/v1\/D16-1264"},{"key":"15_CR18","unstructured":"Santoro, A., et al.: A simple neural network module for relational reasoning. In: Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, pp. 4974\u20134983. Curran Associates Inc., Red Hook (2017)"},{"key":"15_CR19","unstructured":"Suarez, J., Johnson, J., Li, F.: DDRprog: a CLEVR differentiable dynamic reasoning programmer. arXiv e-prints 1803.11361 (2018)"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Suhr, A., Lewis, M., Yeh, J., Artzi, Y.: A corpus of natural language for visual reasoning. In: Barzilay, R., Kan, M.Y. (eds.) Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. ACL 2017. Association for Computational Linguistics, Stroudsburg (2017)","DOI":"10.18653\/v1\/P17-2034"},{"key":"15_CR21","unstructured":"Weston, J., Bordes, A., Chopra, S., Mikolov, T.: Towards AI-complete question answering: a set of prerequisite toy tasks. arXiv e-prints 1502.05698 (2015)"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Yang, G.R., Ganichev, I., Wang, X.J., Shlens, J., Sussillo, D.: A dataset and architecture for visual reasoning with a working memory. arXiv e-prints 1803.06092 (2018)","DOI":"10.32470\/CCN.2018.1075-0"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.J.: Stacked attention networks for image question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2016. IEEE Computer Society, Washington, DC (2016)","DOI":"10.1109\/CVPR.2016.10"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-11018-5_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T01:19:48Z","timestamp":1674350388000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-11018-5_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030110178","9783030110185"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-11018-5_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"23 January 2019","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"}]}}