{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T03:54:24Z","timestamp":1773114864705,"version":"3.50.1"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030664145","type":"print"},{"value":"9783030664152","type":"electronic"}],"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\/978-3-030-66415-2_33","type":"book-chapter","created":{"date-parts":[[2021,1,9]],"date-time":"2021-01-09T14:56:04Z","timestamp":1610204164000},"page":"511-525","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Data Augmentation Techniques for the Video Question Answering Task"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6325-9066","authenticated-orcid":false,"given":"Alex","family":"Falcon","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4793-4276","authenticated-orcid":false,"given":"Oswald","family":"Lanz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4269-4501","authenticated-orcid":false,"given":"Giuseppe","family":"Serra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,1,10]]},"reference":[{"key":"33_CR1","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"33_CR2","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: ICLR (2015)"},{"key":"33_CR3","unstructured":"Damen, D., et al.: Rescaling egocentric vision. CoRR abs\/2006.13256 (2020)"},{"key":"33_CR4","doi-asserted-by":"publisher","unstructured":"Damen, D., et al.: The epic-kitchens dataset: Collection, challenges and baselines. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) (2020). https:\/\/doi.org\/10.1109\/TPAMI.2020.2991965","DOI":"10.1109\/TPAMI.2020.2991965"},{"issue":"3","key":"33_CR5","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1016\/j.amepre.2012.11.008","volume":"44","author":"AR Doherty","year":"2013","unstructured":"Doherty, A.R., et al.: Wearable cameras in health: the state of the art and future possibilities. Am. J. Prev. Med. 44(3), 320\u2013323 (2013)","journal-title":"Am. J. Prev. Med."},{"key":"33_CR6","doi-asserted-by":"crossref","unstructured":"Fan, C.: EgoVQA -an egocentric video question answering benchmark dataset. In: ICCV Workshop (2019)","DOI":"10.1109\/ICCVW.2019.00536"},{"key":"33_CR7","doi-asserted-by":"crossref","unstructured":"Fan, C., Zhang, X., Zhang, S., Wang, W., Zhang, C., Huang, H.: Heterogeneous memory enhanced multimodal attention model for video question answering. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00210"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Gao, J., Ge, R., Chen, K., Nevatia, R.: Motion-appearance co-memory networks for video question answering. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00688"},{"key":"33_CR9","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, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"33_CR10","doi-asserted-by":"crossref","unstructured":"Hori, C., et al.: Attention-based multimodal fusion for video description. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.450"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Huang, D., Chen, P., Zeng, R., Du, Q., Tan, M., Gan, C.: Location-aware graph convolutional networks for video question answering. In: AAAI, pp. 11021\u201311028 (2020)","DOI":"10.1609\/aaai.v34i07.6737"},{"key":"33_CR12","doi-asserted-by":"crossref","unstructured":"Jang, Y., Song, Y., Yu, Y., Kim, Y., Kim, G.: TGIF-QA: toward spatio-temporal reasoning in visual question answering. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.149"},{"key":"33_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, P., Han, Y.: Reasoning with heterogeneous graph alignment for video question answering. In: AAAI, pp. 11109\u201311116 (2020)","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"33_CR14","doi-asserted-by":"crossref","unstructured":"Kafle, K., Yousefhussien, M., Kanan, C.: Data augmentation for visual question answering. In: Proceedings of the 10th International Conference on Natural Language Generation, pp. 198\u2013202 (2017)","DOI":"10.18653\/v1\/W17-3529"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"33_CR16","doi-asserted-by":"crossref","unstructured":"Kim, H., Tang, Z., Bansal, M.: Dense-caption matching and frame-selection gating for temporal localization in VideoQA. arXiv preprint arXiv:2005.06409 (2020)","DOI":"10.18653\/v1\/2020.acl-main.435"},{"key":"33_CR17","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"33_CR18","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NeurIPS (2012)"},{"issue":"11","key":"33_CR19","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"33_CR20","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., Berg, T.L., Bansal, M.: TVQA+: spatio-temporal grounding for video question answering. arXiv preprint arXiv:1904.11574 (2019)","DOI":"10.18653\/v1\/2020.acl-main.730"},{"key":"33_CR21","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. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"Mahendru, A., Prabhu, V., Mohapatra, A., Batra, D., Lee, S.: The promise of premise: harnessing question premises in visual question answering. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 926\u2013935 (2017)","DOI":"10.18653\/v1\/D17-1097"},{"key":"33_CR23","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"},{"issue":"1","key":"33_CR24","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","volume":"6","author":"C Shorten","year":"2019","unstructured":"Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6(1), 60 (2019)","journal-title":"J. Big Data"},{"key":"33_CR25","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"key":"33_CR26","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv:1212.0402 (2012)"},{"key":"33_CR27","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"33_CR28","doi-asserted-by":"crossref","unstructured":"Xu, D., et al.: Video question answering via gradually refined attention over appearance and motion. In: ACM Multimedia (2017)","DOI":"10.1145\/3123266.3123427"},{"key":"33_CR29","doi-asserted-by":"crossref","unstructured":"Yu, Z., et al.: ActivityNet-QA: a dataset for understanding complex web videos via question answering. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 9127\u20139134 (2019)","DOI":"10.1609\/aaai.v33i01.33019127"}],"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\/978-3-030-66415-2_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T00:07:49Z","timestamp":1736381269000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-66415-2_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030664145","9783030664152"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-66415-2_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"10 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)"}}]}}