{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:04:34Z","timestamp":1776888274378,"version":"3.51.2"},"publisher-location":"Singapore","reference-count":41,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819985395","type":"print"},{"value":"9789819985401","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T00:00:00Z","timestamp":1703462400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T00:00:00Z","timestamp":1703462400000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8540-1_25","type":"book-chapter","created":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T18:01:32Z","timestamp":1703440892000},"page":"309-322","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["VCD: Visual Causality Discovery for\u00a0Cross-Modal Question Reasoning"],"prefix":"10.1007","author":[{"given":"Yang","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingzhou","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weixing","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,25]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Abbasnejad, E., Teney, D., Parvaneh, A., Shi, J., Hengel, A.V.D.: Counterfactual vision and language learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10044\u201310054 (2020)","DOI":"10.1109\/CVPR42600.2020.01006"},{"key":"25_CR2","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":"25_CR3","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Gao, J., Ge, R., Chen, K., Nevatia, R.: Motion-appearance co-memory networks for video question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6576\u20136585 (2018)","DOI":"10.1109\/CVPR.2018.00688"},{"key":"25_CR5","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1109\/TIP.2021.3120867","volume":"31","author":"L Gao","year":"2022","unstructured":"Gao, L., Lei, Y., Zeng, P., Song, J., Wang, M., Shen, H.T.: Hierarchical representation network with auxiliary tasks for video captioning and video question answering. IEEE Trans. Image Process. 31, 202\u2013215 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"25_CR6","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":"25_CR7","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: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11021\u201311028 (2020)","DOI":"10.1609\/aaai.v34i07.6737"},{"key":"25_CR8","unstructured":"Jang, E., Gu, S., Poole, B.: Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144 (2016)"},{"key":"25_CR9","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2758\u20132766 (2017)","DOI":"10.1109\/CVPR.2017.149"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Jiang, J., Chen, Z., Lin, H., Zhao, X., Gao, Y.: Divide and conquer: question-guided spatio-temporal contextual attention for video question answering. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11101\u201311108 (2020)","DOI":"10.1609\/aaai.v34i07.6766"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Jiang, P., Han, Y.: Reasoning with heterogeneous graph alignment for video question answering. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11109\u201311116 (2020)","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"JiayinCai, C., Shi, C., Li, L., Cheng, Y., Shan, Y.: Feature augmented memory with global attention network for VideoQA. In: IJCAI, pp. 998\u20131004 (2020)","DOI":"10.24963\/ijcai.2020\/139"},{"key":"25_CR13","doi-asserted-by":"publisher","first-page":"5477","DOI":"10.1109\/TIP.2021.3076556","volume":"30","author":"W Jin","year":"2021","unstructured":"Jin, W., Zhao, Z., Cao, X., Zhu, J., He, X., Zhuang, Y.: Adaptive spatio-temporal graph enhanced vision-language representation for video QA. IEEE Trans. Image Process. 30, 5477\u20135489 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Kim, N., Ha, S.J., Kang, J.W.: Video question answering using language-guided deep compressed-domain video feature. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1708\u20131717 (2021)","DOI":"10.1109\/ICCV48922.2021.00173"},{"key":"25_CR15","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Le, T.M., Le, V., Venkatesh, S., Tran, T.: Hierarchical conditional relation networks for video question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9972\u20139981 (2020)","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Lei, J., et al.: Less is more: clipbert for video-and-language learning via sparse sampling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7331\u20137341 (2021)","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, X., Xiao, J., Ji, W., Chua, T.S.: Invariant grounding for video question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2928\u20132937 (2022)","DOI":"10.1109\/CVPR52688.2022.00294"},{"key":"25_CR19","unstructured":"Liu, F., Liu, J., Hong, R., Lu, H.: Question-guided erasing-based spatiotemporal attention learning for video question answering. IEEE Trans. Neural Netw. Learn. Syst. (2021)"},{"key":"25_CR20","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":"25_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11633-022-1362-z","volume":"19","author":"Y Liu","year":"2022","unstructured":"Liu, Y., Wei, Y.S., Yan, H., Li, G.B., Lin, L.: Causal reasoning meets visual representation learning: a prospective study. Mach. Intell. Res. 19, 1\u201327 (2022)","journal-title":"Mach. Intell. Res."},{"key":"25_CR22","doi-asserted-by":"publisher","first-page":"1684","DOI":"10.1109\/TIP.2022.3142526","volume":"31","author":"Y Liu","year":"2022","unstructured":"Liu, Y., Zhang, X., Huang, F., Zhang, B., Li, Z.: Cross-attentional spatio-temporal semantic graph networks for video question answering. IEEE Trans. Image Process. 31, 1684\u20131696 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Nan, G., et al.: Interventional video grounding with dual contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2765\u20132775 (2021)","DOI":"10.1109\/CVPR46437.2021.00279"},{"key":"25_CR25","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-19772-7_1","volume-title":"ECCV 2022, Part IV","author":"B Ni","year":"2022","unstructured":"Ni, B., et al.: Expanding language-image pretrained models for general video recognition. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, Part IV. LNCS, vol. 13664, pp. 1\u201318. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19772-7_1"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Niu, Y., Tang, K., Zhang, H., Lu, Z., Hua, X.S., Wen, J.R.: Counterfactual VQA: a cause-effect look at language bias. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12700\u201312710 (2021)","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"25_CR27","doi-asserted-by":"crossref","unstructured":"Park, J., Lee, J., Sohn, K.: Bridge to answer: structure-aware graph interaction network for video question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15526\u201315535 (2021)","DOI":"10.1109\/CVPR46437.2021.01527"},{"key":"25_CR28","volume-title":"Causal Inference in Statistics: A Primer","author":"J Pearl","year":"2016","unstructured":"Pearl, J., Glymour, M., Jewell, N.P.: Causal Inference in Statistics: A Primer. Wiley, Hoboken (2016)"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Seo, A., Kang, G.C., Park, J., Zhang, B.T.: Attend what you need: motion-appearance synergistic networks for video question answering. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 6167\u20136177 (2021)","DOI":"10.18653\/v1\/2021.acl-long.481"},{"key":"25_CR31","first-page":"2440","volume":"2015","author":"S Sukhbaatar","year":"2015","unstructured":"Sukhbaatar, S., Szlam, A., Weston, J., Fergus, R.: End-to-end memory networks. Adv. Neural. Inf. Process. Syst. 2015, 2440\u20132448 (2015)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Tang, K., Niu, Y., Huang, J., Shi, J., Zhang, H.: Unbiased scene graph generation from biased training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3716\u20133725 (2020)","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"25_CR33","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"25_CR34","doi-asserted-by":"publisher","first-page":"3369","DOI":"10.1109\/TMM.2021.3097171","volume":"24","author":"J Wang","year":"2021","unstructured":"Wang, J., Bao, B., Xu, C.: DualVGR: a dual-visual graph reasoning unit for video question answering. IEEE Trans. Multimedia 24, 3369\u20133380 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"25_CR35","doi-asserted-by":"crossref","unstructured":"Wang, P., Vasconcelos, N.: Scout: self-aware discriminant counterfactual explanations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8981\u20138990 (2020)","DOI":"10.1109\/CVPR42600.2020.00900"},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhou, C., Sun, Q., Zhang, H.: Causal attention for unbiased visual recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3091\u20133100 (2021)","DOI":"10.1109\/ICCV48922.2021.00308"},{"key":"25_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1007\/978-3-030-58568-6_43","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Wang","year":"2020","unstructured":"Wang, T., et al.: The devil is in classification: a simple framework for long-tail instance segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 728\u2013744. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_43"},{"key":"25_CR38","doi-asserted-by":"crossref","unstructured":"Xu, D., et al.: Video question answering via gradually refined attention over appearance and motion. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 1645\u20131653 (2017)","DOI":"10.1145\/3123266.3123427"},{"key":"25_CR39","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"25_CR40","doi-asserted-by":"crossref","unstructured":"Xu, L., Huang, H., Liu, J.: SUTD-TrafficQA: a question answering benchmark and an efficient network for video reasoning over traffic events. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9878\u20139888 (2021)","DOI":"10.1109\/CVPR46437.2021.00975"},{"key":"25_CR41","doi-asserted-by":"crossref","unstructured":"Yang, X., Zhang, H., Qi, G., Cai, J.: Causal attention for vision-language tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9847\u20139857 (2021)","DOI":"10.1109\/CVPR46437.2021.00972"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8540-1_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T18:05:08Z","timestamp":1703441108000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8540-1_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,25]]},"ISBN":["9789819985395","9789819985401"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8540-1_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,25]]},"assertion":[{"value":"25 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","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":"532","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":"37% - 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":"3,78","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":"3,69","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)"}}]}}