{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:12:53Z","timestamp":1778170373774,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":38,"publisher":"Springer Singapore","isbn-type":[{"value":"9789811610912","type":"print"},{"value":"9789811610929","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\/978-981-16-1092-9_7","type":"book-chapter","created":{"date-parts":[[2021,3,27]],"date-time":"2021-03-27T16:02:26Z","timestamp":1616860946000},"page":"75-86","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["Visual Question Answering Using Deep Learning: A Survey and Performance Analysis"],"prefix":"10.1007","author":[{"given":"Yash","family":"Srivastava","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vaishnav","family":"Murali","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiv Ram","family":"Dubey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Snehasis","family":"Mukherjee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,3,28]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Acharya, M., Kafle, K., Kanan, C.: Tallyqa: Answering complex counting questions. arXiv preprint arXiv:1810.12440 (2018)","DOI":"10.1609\/aaai.v33i01.33018076"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: IEEE ICCV, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Chen, L., Yan, X., Xiao, J., Zhang, H., Pu, S., Zhuang, Y.: Counterfactual samples synthesizing for robust visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10800\u201310809 (2020)","DOI":"10.1109\/CVPR42600.2020.01081"},{"key":"7_CR4","unstructured":"Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Gupta, S., Arbelaez, P., Malik, J.: Perceptual organization and recognition of indoor scenes from RGB-D images. In: IEEE CVPR, pp. 564\u2013571 (2013)","DOI":"10.1109\/CVPR.2013.79"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"7_CR7","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":"7_CR8","doi-asserted-by":"crossref","unstructured":"Huang, Q., et al.: Aligned dual channel graph convolutional network for visual question answering. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 7166\u20137176 (2020)","DOI":"10.18653\/v1\/2020.acl-main.642"},{"key":"7_CR9","unstructured":"Jiang, L., Liang, J., Cao, L., Kalantidis, Y., Farfade, S., Hauptmann, A.: MemexQA: Visual memex question answering. arXiv preprint arXiv:1708.01336 (2017)"},{"key":"7_CR10","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":"7_CR11","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., van der Maaten, L., Fei-Fei, L., Lawrence Zitnick, C., Girshick, R.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: IEEE CVPR, pp. 2901\u20132910 (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Kafle, K., Kanan, C.: An analysis of visual question answering algorithms. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.217"},{"key":"7_CR13","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS, pp. 1097\u20131105 (2012)"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Li, G., Wang, X., Zhu, W.: Boosting visual question answering with context-aware knowledge aggregation. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1227\u20131235 (2020)","DOI":"10.1145\/3394171.3413943"},{"key":"7_CR15","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1016\/j.patrec.2020.02.031","volume":"133","author":"W Li","year":"2020","unstructured":"Li, W., Sun, J., Liu, G., Zhao, L., Fang, X.: Visual question answering with attention transfer and a cross-modal gating mechanism. Pattern Recogn. Lett. 133, 334\u2013340 (2020)","journal-title":"Pattern Recogn. Lett."},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Liang, J., Jiang, L., Cao, L., Li, L.J., Hauptmann, A.G.: Focal visual-text attention for visual question answering. In: IEEE CVPR, pp. 6135\u20136143 (2018)","DOI":"10.1109\/CVPR.2018.00642"},{"key":"7_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part V. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"issue":"12","key":"7_CR18","doi-asserted-by":"publisher","first-page":"8555","DOI":"10.1109\/TGRS.2020.2988782","volume":"58","author":"S Lobry","year":"2020","unstructured":"Lobry, S., Marcos, D., Murray, J., Tuia, D.: RSVQA: visual question answering for remote sensing data. IEEE Trans. Geosci. Remote Sens. 58(12), 8555\u20138566 (2020)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"7_CR19","unstructured":"Malinowski, M., Fritz, M.: A multi-world approach to question answering about real-world scenes based on uncertain input. In: NIPS, pp. 1682\u20131690 (2014)"},{"key":"7_CR20","unstructured":"Medsker, L.R., Jain, L.: Recurrent neural networks. Design and Applications 5, (2001)"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Patro, B., Namboodiri, V.P.: Differential attention for visual question answering. In: IEEE CVPR, pp. 7680\u20137688 (2018)","DOI":"10.1109\/CVPR.2018.00801"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: Glove: global vectors for word representation. In: EMNLP, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"7_CR23","unstructured":"Ren, M., Kiros, R., Zemel, R.: Exploring models and data for image question answering. In: Advances in Neural Information Processing Systems, pp. 2953\u20132961 (2015)"},{"key":"7_CR24","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp. 91\u201399 (2015)"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Shah, S., Mishra, A., Yadati, N., Talukdar, P.P.: KVQA: knowledge-aware visual question answering. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33018876"},{"key":"7_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part V. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54"},{"key":"7_CR27","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: IEEE CVPR, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Tapaswi, M., Zhu, Y., Stiefelhagen, R., Torralba, A., Urtasun, R., Fidler, S.: MovieQA: understanding stories in movies through question-answering. In: IEEE CVPR, pp. 4631\u20134640 (2016)","DOI":"10.1109\/CVPR.2016.501"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Teney, D., Anderson, P., He, X., van den Hengel, A.: Tips and tricks for visual question answering: learnings from the 2017 challenge. In: IEEE CVPR, pp. 4223\u20134232 (2018)","DOI":"10.1109\/CVPR.2018.00444"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Wu, C., Liu, J., Wang, X., Li, R.: Differential networks for visual question answering. In: AAAI 2019 (2019)","DOI":"10.1609\/aaai.v33i01.33018997"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: IEEE CVPR, pp. 21\u201329 (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"7_CR33","unstructured":"Yi, K., Wu, J., Gan, C., Torralba, A., Kohli, P., Tenenbaum, J.: Neural-symbolic VQA: disentangling reasoning from vision and language understanding. In: NIPS, pp. 1031\u20131042 (2018)"},{"key":"7_CR34","doi-asserted-by":"publisher","first-page":"107563","DOI":"10.1016\/j.patcog.2020.107563","volume":"108","author":"J Yu","year":"2020","unstructured":"Yu, J., Zhu, Z., Wang, Y., Zhang, W., Hu, Y., Tan, J.: Cross-modal knowledge reasoning for knowledge-based visual question answering. Pattern Recogn. 108, 107563 (2020)","journal-title":"Pattern Recogn."},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Yu, L., Park, E., Berg, A.C., Berg, T.L.: Visual madlibs: fill in the blank description generation and question answering. In: IEEE ICCV, pp. 2461\u20132469 (2015)","DOI":"10.1109\/ICCV.2015.283"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Zhan, L.M., Liu, B., Fan, L., Chen, J., Wu, X.M.: Medical visual question answering via conditional reasoning. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2345\u20132354 (2020)","DOI":"10.1145\/3394171.3413761"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wang, W., Qi, S., Zhu, S.C.: Reasoning visual dialogs with structural and partial observations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6669\u20136678 (2019)","DOI":"10.1109\/CVPR.2019.00683"},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Groth, O., Bernstein, M., Fei-Fei, L.: Visual7W: grounded question answering in images. In: IEEE CVPR, pp. 4995\u20135004 (2016)","DOI":"10.1109\/CVPR.2016.540"}],"container-title":["Communications in Computer and Information Science","Computer Vision and Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-16-1092-9_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,24]],"date-time":"2021-04-24T19:46:58Z","timestamp":1619293618000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-16-1092-9_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9789811610912","9789811610929"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-981-16-1092-9_7","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"28 March 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CVIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Vision and Image Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prayagraj","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"4 December 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cvip2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cvip2020.iiita.ac.in","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"352","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":"134","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":"38% - 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":"4","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":"Due to the COVID-19 pandemic the conference was partially held in a virtual mode.","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)"}}]}}