{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T07:23:28Z","timestamp":1743060208271,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030660956"},{"type":"electronic","value":"9783030660963"}],"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\/978-3-030-66096-3_34","type":"book-chapter","created":{"date-parts":[[2021,1,2]],"date-time":"2021-01-02T07:03:14Z","timestamp":1609570994000},"page":"496-510","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multiple Interaction Learning with Question-Type Prior Knowledge for Constraining Answer Search Space in Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Tuong","family":"Do","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Binh X.","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huy","family":"Tran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erman","family":"Tjiputra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quang D.","family":"Tran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thanh-Toan","family":"Do","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,1,3]]},"reference":[{"key":"34_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, A., Dhruv Batra, D.P., Kembhavi, A.: Don\u2019t just assume; look and answer: overcoming priors for visual question answering. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00522"},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and VQA. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"34_CR5","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT (2019)"},{"key":"34_CR6","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: EMNLP (2016)","DOI":"10.18653\/v1\/D16-1044"},{"key":"34_CR7","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: CVPR (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"34_CR8","unstructured":"Jiang, Y., Natarajan, V., Chen, X., Rohrbach, M., Batra, D., Parikh, D.: Pythia v0.1: the winning entry to the VQA challenge 2018. CoRR (2018)"},{"key":"34_CR9","doi-asserted-by":"crossref","unstructured":"Kafle, K., Kanan, C.: Answer-type prediction for visual question answering. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.538"},{"key":"34_CR10","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":"34_CR11","unstructured":"Kim, J.H., Jun, J., Zhang, B.T.: Bilinear attention networks. In: NIPS (2018)"},{"key":"34_CR12","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"34_CR13","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2016","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. IJCV 123, 32\u201373 (2016)","journal-title":"IJCV"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Li, L., Gan, Z., Cheng, Y., Liu, J.: Relation-aware graph attention network for visual question answering. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.01041"},{"key":"34_CR15","doi-asserted-by":"crossref","unstructured":"Nguyen, D.K., Okatani, T.: Improved fusion of visual and language representations by dense symmetric co-attention for visual question answering. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00637"},{"key":"34_CR16","unstructured":"Paszke, A., et al.: Automatic differentiation in PyTorch. In: NIPS 2017 Workshop (2017)"},{"key":"34_CR17","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"34_CR18","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"key":"34_CR19","unstructured":"Santoro, A., et al.: A simple neural network module for relational reasoning. In: NIPS (2017)"},{"key":"34_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1007\/978-3-030-01225-0_10","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Shi","year":"2018","unstructured":"Shi, Y., Furlanello, T., Zha, S., Anandkumar, A.: Question type guided attention in visual question answering. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 158\u2013175. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_10"},{"key":"34_CR21","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 and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"34_CR22","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: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00444"},{"key":"34_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/978-3-319-46478-7_28","volume-title":"Computer Vision \u2013 ECCV 2016","author":"H Xu","year":"2016","unstructured":"Xu, H., Saenko, K.: Ask, attend and answer: exploring question-guided spatial attention for visual question answering. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 451\u2013466. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_28"},{"key":"34_CR24","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.J.: Stacked attention networks for image question answering. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"34_CR25","unstructured":"Zhang, Y., Hare, J.S., Pr\u00fcgel-Bennett, A.: Learning to count objects in natural images for visual question answering. In: ICLR (2018)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-66096-3_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T00:14:05Z","timestamp":1735776845000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-66096-3_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030660956","9783030660963"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-66096-3_34","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":"3 January 2021","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)"}}]}}