{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T17:34:10Z","timestamp":1770140050078,"version":"3.49.0"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030687892","type":"print"},{"value":"9783030687908","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-68790-8_28","type":"book-chapter","created":{"date-parts":[[2021,2,22]],"date-time":"2021-02-22T13:13:24Z","timestamp":1613999604000},"page":"357-370","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["IQ-VQA: Intelligent Visual Question Answering"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2236-8186","authenticated-orcid":false,"given":"Vatsal","family":"Goel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6929-4372","authenticated-orcid":false,"given":"Mohit","family":"Chandak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0024-3358","authenticated-orcid":false,"given":"Ashish","family":"Anand","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2885-0026","authenticated-orcid":false,"given":"Prithwijit","family":"Guha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,23]]},"reference":[{"key":"28_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, A., Batra, D., Parikh, D., Kembhavi, A.: Don\u2019t just assume; look and answer: overcoming priors for visual question answering. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4971\u20134980 (2018)","DOI":"10.1109\/CVPR.2018.00522"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018","DOI":"10.1109\/CVPR.2018.00636"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Denkowski, M., Lavie, A.: Meteor universal: language specific translation evaluation for any target language. In: Proceedings of the EACL 2014 Workshop on Statistical Machine Translation (2014)","DOI":"10.3115\/v1\/W14-3348"},{"key":"28_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1007\/978-3-030-58589-1_23","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Gokhale","year":"2020","unstructured":"Gokhale, T., Banerjee, P., Baral, C., Yang, Y.: VQA-LOL: visual question answering under the lens of logic. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 379\u2013396. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_23"},{"key":"28_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: Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"28_CR7","first-page":"1571","volume":"31","author":"JH Kim","year":"2018","unstructured":"Kim, J.H., Jun, J., Zhang, B.T.: Bilinear attention networks. Adv. Neural Inf. Process. Syst. 31, 1571\u20131581 (2018)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1","key":"28_CR8","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Kumar, V., Ramakrishnan, G., Li, Y.F.: Putting the horse before the cart: a generator-evaluator framework for question generation from text. In: Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), pp. 812\u2013821 (2019)","DOI":"10.18653\/v1\/K19-1076"},{"key":"28_CR10","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: Albert: a lite bert for self-supervised learning of language representations. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=H1eA7AEtvS"},{"key":"28_CR11","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381. Association for Computational Linguistics, Barcelona, July 2004. https:\/\/www.aclweb.org\/anthology\/W04-1013"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Manjunatha, V., Saini, N., Davis, L.S.: Explicit bias discovery in visual question answering models. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019","DOI":"10.1109\/CVPR.2019.00979"},{"key":"28_CR13","doi-asserted-by":"publisher","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, ACL 2002, pp. 311\u2013318. Association for Computational Linguistics (2002). https:\/\/doi.org\/10.3115\/1073083.1073135","DOI":"10.3115\/1073083.1073135"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Ray, A., Sikka, K., Divakaran, A., Lee, S., Burachas, G.: Sunny and dark outside?! Improving answer consistency in VQA through entailed question generation. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 5863\u20135868 (2019)","DOI":"10.18653\/v1\/D19-1596"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Reddy, S., Raghu, D., Khapra, M.M., Joshi, S.: Generating natural language question-answer pairs from a knowledge graph using a RNN based question generation model. In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pp. 376\u2013385. Association for Computational Linguistics, Valencia, April 2017. https:\/\/www.aclweb.org\/anthology\/E17-1036","DOI":"10.18653\/v1\/E17-1036"},{"key":"28_CR16","doi-asserted-by":"publisher","unstructured":"Ribeiro, M.T., Guestrin, C., Singh, S.: Are red roses red? Evaluating consistency of question-answering models. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 6174\u20136184. Association for Computational Linguistics, Florence, July 2019. https:\/\/doi.org\/10.18653\/v1\/P19-1621. https:\/\/www.aclweb.org\/anthology\/P19-1621","DOI":"10.18653\/v1\/P19-1621"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., et al.: SQuINTing at VQA models: introspecting VQA models with sub-questions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10003\u201310011 (2020)","DOI":"10.1109\/CVPR42600.2020.01002"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Shah, M., Chen, X., Rohrbach, M., Parikh, D.: Cycle-consistency for robust visual question answering. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00681"},{"key":"28_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1007\/978-3-642-15549-9_32","volume-title":"Computer Vision \u2013 ECCV 2010","author":"N Sundaram","year":"2010","unstructured":"Sundaram, N., Brox, T., Keutzer, K.: Dense point trajectories by GPU-accelerated large displacement optical flow. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 438\u2013451. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15549-9_32"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"28_CR21","doi-asserted-by":"publisher","unstructured":"Tang, D., et al.: Learning to collaborate for question answering and asking. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 1564\u20131574. Association for Computational Linguistics, New Orleans, June 2018. https:\/\/doi.org\/10.18653\/v1\/N18-1141. https:\/\/www.aclweb.org\/anthology\/N18-1141","DOI":"10.18653\/v1\/N18-1141"},{"key":"28_CR22","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: CIDEr: consensus-based image description evaluation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"28_CR23","unstructured":"Yan, Y., et al.: ProphetNet: predicting future N-gram for sequence-to-sequence pre-training (2020)"},{"key":"28_CR24","unstructured":"Jiang, Y., Natarajan, V., Chen, X., Rohrbach, M., Batra, D., Parikh, D.: Pythia v0.1: the winning entry to the VQA challenge 2018. arXiv preprint arXiv:1807.09956 (2018)"},{"key":"28_CR25","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, pp. 5014\u20135022 (2016)","DOI":"10.1109\/CVPR.2016.542"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition. ICPR International Workshops and Challenges"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-68790-8_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,22]],"date-time":"2021-02-22T13:40:33Z","timestamp":1614001233000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-68790-8_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030687892","9783030687908"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-68790-8_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"23 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 January 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ICPR2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.icpr2020.it\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}