{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T02:39:38Z","timestamp":1775702378397,"version":"3.50.1"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031441943","type":"print"},{"value":"9783031441950","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-44195-0_35","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T12:04:08Z","timestamp":1695297848000},"page":"427-438","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Gated Multi-modal Fusion with\u00a0Cross-modal Contrastive Learning for\u00a0Video Question Answering"],"prefix":"10.1007","author":[{"given":"Chenyang","family":"Lyu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianbo","family":"Ji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liting","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cathal","family":"Gurrin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"key":"35_CR1","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"35_CR2","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: a joint video and image encoder for end-to-end retrieval. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"35_CR3","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: A clip-hitchhiker\u2019s guide to long video retrieval. arXiv preprint arXiv:2205.08508 (2022)"},{"key":"35_CR4","doi-asserted-by":"crossref","unstructured":"Dang, L.H., Le, T.M., Le, V., Tran, T.: Hierarchical object-oriented spatio-temporal reasoning for video question answering. arXiv preprint arXiv:2106.13432 (2021)","DOI":"10.24963\/ijcai.2021\/88"},{"key":"35_CR5","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)"},{"key":"35_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2020)"},{"key":"35_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":"35_CR8","first-page":"2283","volume":"28","author":"HM Fayek","year":"2020","unstructured":"Fayek, H.M., Johnson, J.: Temporal reasoning via audio question answering. IEEE\/ACM TASLP 28, 2283\u20132294 (2020)","journal-title":"IEEE\/ACM TASLP"},{"key":"35_CR9","doi-asserted-by":"crossref","unstructured":"Gan, Z., et al.: Vision-language pre-training: basics, recent advances, and future trends. FTCGV 14(3\u20134), 163\u2013352 (2022)","DOI":"10.1561\/0600000105"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Jiang, P., Han, Y.: Reasoning with heterogeneous graph alignment for video question answering. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"35_CR11","doi-asserted-by":"crossref","unstructured":"Kim, J., Ma, M., Pham, T., Kim, K., Yoo, C.D.: Modality shifting attention network for multi-modal video question answering. In: CVPR, pp. 10106\u201310115 (2020)","DOI":"10.1109\/CVPR42600.2020.01012"},{"key":"35_CR12","doi-asserted-by":"crossref","unstructured":"Le, T.M., Le, V., Venkatesh, S., Tran, T.: Hierarchical conditional relation networks for video question answering. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"35_CR13","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., Bansal, M., Berg, T.L.: TVQA: localized, compositional video question answering. arXiv preprint arXiv:1809.01696 (2018)","DOI":"10.18653\/v1\/D18-1167"},{"key":"35_CR14","doi-asserted-by":"crossref","unstructured":"Li, G., Wei, Y., Tian, Y., Xu, C., Wen, J.R., Hu, D.: Learning to answer questions in dynamic audio-visual scenarios. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01852"},{"key":"35_CR15","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Learnable aggregating net with diversity learning for video question answering. In: ACM MM (2019)","DOI":"10.1145\/3343031.3350971"},{"key":"35_CR16","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Beyond RNNs: positional self-attention with co-attention for video question answering. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"35_CR17","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, X., Xiao, J., Ji, W., Chua, T.S.: Invariant grounding for video question answering. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00294"},{"key":"35_CR18","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"35_CR19","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Hierarchical question-image co-attention for visual question answering. arXiv preprint arXiv:1606.00061 (2016)"},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"Lyu, C., Nguyen, M.D., Ninh, V.T., Zhou, L., Gurrin, C., Foster, J.: Dialogue-to-video retrieval. In: ECIR (2023)","DOI":"10.1007\/978-3-031-28238-6_40"},{"key":"35_CR21","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"35_CR22","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. CoRR abs\/2212.04356 (2022)"},{"key":"35_CR23","doi-asserted-by":"crossref","unstructured":"Schwartz, I., Schwing, A.G., Hazan, T.: A simple baseline for audio-visual scene-aware dialog. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01283"},{"key":"35_CR24","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: CVPR, pp. 4631\u20134640 (2016)","DOI":"10.1109\/CVPR.2016.501"},{"key":"35_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"35_CR26","unstructured":"Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: EMNLP (2020)"},{"key":"35_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1007\/978-3-030-58539-6_27","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Xiao","year":"2020","unstructured":"Xiao, J., Shang, X., Yang, X., Tang, S., Chua, T.-S.: Visual relation grounding in videos. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 447\u2013464. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_27"},{"key":"35_CR28","doi-asserted-by":"crossref","unstructured":"Xiao, J., Yao, A., Liu, Z., Li, Y., Ji, W., Chua, T.S.: Video as conditional graph hierarchy for multi-granular question answering. In: AAAI, vol. 36, pp. 2804\u20132812 (2022)","DOI":"10.1609\/aaai.v36i3.20184"},{"key":"35_CR29","doi-asserted-by":"crossref","unstructured":"Yang, H., Chaisorn, L., Zhao, Y., Neo, S.Y., Chua, T.S.: Videoqa: question answering on news video. In: ACM MM (2003)","DOI":"10.1145\/957013.957146"},{"key":"35_CR30","doi-asserted-by":"crossref","unstructured":"Yang, P., et al.: AVQA: a dataset for audio-visual question answering on videos. In: ACM MM (2022)","DOI":"10.1145\/3503161.3548291"},{"key":"35_CR31","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Cui, Y., Tao, D., Tian, Q.: Deep modular co-attention networks for visual question answering. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00644"},{"key":"35_CR32","doi-asserted-by":"crossref","unstructured":"Yun, H., Yu, Y., Yang, W., Lee, K., Kim, G.: Pano-AVQA: grounded audio-visual question answering on 360$$^{\\circ }$$ videos. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00204"},{"issue":"1","key":"35_CR33","first-page":"63","volume":"32","author":"J Zhang","year":"2020","unstructured":"Zhang, J., Shao, J., Cao, R., Gao, L., Xu, X., Shen, H.T.: Action-centric relation transformer network for video question answering. IEEE TCSVT 32(1), 63\u201374 (2020)","journal-title":"IEEE TCSVT"},{"key":"35_CR34","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Yang, Q., Cai, D., He, X., Zhuang, Y.: Video question answering via hierarchical spatio-temporal attention networks. In: IJCAI (2017)","DOI":"10.24963\/ijcai.2017\/492"},{"key":"35_CR35","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Ji, W., Xiao, J., Li, Y., Deng, W., Chua, T.S.: Video question answering: datasets, algorithms and challenges. arXiv preprint arXiv:2203.01225 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.432"},{"key":"35_CR36","doi-asserted-by":"crossref","unstructured":"Zhou, P., et al.: Attention-based bidirectional long short-term memory networks for relation classification. In: ACL (2016)","DOI":"10.18653\/v1\/P16-2034"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44195-0_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T12:09:09Z","timestamp":1695298149000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44195-0_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031441943","9783031441950"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44195-0_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Heraklion","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2023\/","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":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"947","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":"426","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":"22","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":"45% - 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":"2.4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"type of other papers accepted  : 9 Abstract","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)"}}]}}