{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T22:49:06Z","timestamp":1743029346452,"version":"3.40.3"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031204999"},{"type":"electronic","value":"9783031205002"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-20500-2_23","type":"book-chapter","created":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T05:12:32Z","timestamp":1672549952000},"page":"280-290","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Recurrent Contextual Attention Network for\u00a0Video Question Answering"],"prefix":"10.1007","author":[{"given":"Fei","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Yahong","family":"Han","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,1,1]]},"reference":[{"key":"23_CR1","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":"23_CR2","doi-asserted-by":"crossref","unstructured":"Fan, C., Zhang, X., Zhang, S.: Heterogeneous memory enhanced multimodal attention model for video question answering. In: CVPR, pp. 1999\u20132007 (2019)","DOI":"10.1109\/CVPR.2019.00210"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Gao, J., Ge, R., Chen, K.: Motion-appearance co-memory networks for video question answering. In: CVPR, pp. 6576\u20136585 (2018)","DOI":"10.1109\/CVPR.2018.00688"},{"key":"23_CR4","doi-asserted-by":"publisher","first-page":"2758","DOI":"10.1109\/TIP.2021.3051756","volume":"30","author":"M Gu","year":"2021","unstructured":"Gu, M., Zhao, Z., Jin, W., Hong, R., Wu, F.: Graph-based multi-interaction network for video question answering. IEEE Trans. Image Process. 30, 2758\u20132770 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3d cnns retrace the history of 2d cnns and imagenet? In: CVPR, pp. 6546\u20136555 (2018)","DOI":"10.1109\/CVPR.2018.00685"},{"key":"23_CR6","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":"23_CR7","doi-asserted-by":"crossref","unstructured":"Huang, D., Chen, P., Zeng, R.: Location-aware graph convolutional networks for video question answering. In: AAAI, pp. 11021\u201311028 (2020)","DOI":"10.1609\/aaai.v34i07.6737"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Jang, Y., Song, Y., Yu, Y.: Tgif-qa: toward spatio-temporal reasoning in visual question answering. In: CVPR, pp. 2758\u20132766 (2017)","DOI":"10.1109\/CVPR.2017.149"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Jiang, H., Misra, I., Rohrbach, M., Learned-Miller, E., Chen, X.: In defense of grid features for visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10267\u201310276 (2020)","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Jiang, J., Chen, Z.: Divide and conquer: question-guided spatio-temporal contextual attention for video question answering. In: AAAI, pp. 11101\u201311108 (2020)","DOI":"10.1609\/aaai.v34i07.6766"},{"key":"23_CR11","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":"23_CR12","doi-asserted-by":"crossref","unstructured":"Le, T.M., Le, V., Venkatesh, S.: Hierarchical conditional relation networks for video question answering. In: CVPR, pp. 9972\u20139981 (2020)","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Li, X., Song, J., Gao, L.: Beyond rnns: positional self-attention with co-attention for video question answering. In: AAAI, pp. 8658\u20138665 (2019)","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Liu, F., Liu, J., Wang, W., Lu, H.: Hair: hierarchical visual-semantic relational reasoning for video question answering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1698\u20131707 (2021)","DOI":"10.1109\/ICCV48922.2021.00172"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Park, J., Lee, J., Sohn, K.: Bridge to answer: Structure-aware graph interaction network for video question answering. In: CVPR, pp. 15526\u201315535 (2021)","DOI":"10.1109\/CVPR46437.2021.01527"},{"key":"23_CR16","unstructured":"Vaswani, A., Shazeer, N., Parmar, N.: Attention is all you need. In: NeurIPS, pp. 5998\u20136008 (2017)"},{"key":"23_CR17","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. AAAI (2022)","DOI":"10.1609\/aaai.v36i3.20184"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Xu, D., Zhao, Z., Xiao, J.: Video question answering via gradually refined attention over appearance and motion. In: ACM MM, pp. 1645\u20131653 (2017)","DOI":"10.1145\/3123266.3123427"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20500-2_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T05:36:14Z","timestamp":1672551374000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20500-2_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031204999","9783031205002"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20500-2_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"1 January 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CAAI International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cicai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cicai.caai.cn\/#\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"472","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":"164","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":"35% - 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":"3.1","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":"3.7","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)"}}]}}