{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T00:50:36Z","timestamp":1769561436096,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Shanghai Science and Technology Commission","award":["21511100700,22511104600"],"award-info":[{"award-number":["21511100700,22511104600"]}]},{"name":"the Open Project Program of the State Key Lab of CADCG","award":["A2203"],"award-info":[{"award-number":["A2203"]}]},{"name":"Natural Science Foundation Project of CQ","award":["CSTB2022NSCQ-MSX0552"],"award-info":[{"award-number":["CSTB2022NSCQ-MSX0552"]}]},{"name":"Shanghai Sailing Program","award":["21YF1411200"],"award-info":[{"award-number":["21YF1411200"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612249","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"4877-4885","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Prior Knowledge-driven Dynamic Scene Graph Generation with Causal Inference"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6963-4525","authenticated-orcid":false,"given":"Jiale","family":"Lu","sequence":"first","affiliation":[{"name":"East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4131-0828","authenticated-orcid":false,"given":"Lianggangxu","family":"Chen","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6769-7862","authenticated-orcid":false,"given":"Youqi","family":"Song","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0284-9940","authenticated-orcid":false,"given":"Shaohui","family":"Lin","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8940-6418","authenticated-orcid":false,"given":"Changbo","family":"Wang","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8365-0970","authenticated-orcid":false,"given":"Gaoqi","family":"He","sequence":"additional","affiliation":[{"name":"East China Normal University & Chongqing Key Laboratory of Precision Optics, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00801"},{"key":"e_1_3_2_2_2_1","volume-title":"Delving deeper into convolutional networks for learning video representations. arXiv preprint arXiv:1511.06432","author":"Ballas Nicolas","year":"2015","unstructured":"Nicolas Ballas, Li Yao, Chris Pal, and Aaron Courville. 2015. Delving deeper into convolutional networks for learning video representations. arXiv preprint arXiv:1511.06432 (2015)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"Elias Bareinboim Juan D Correa Duligur Ibeling and Thomas Icard. 2022. On Pearl's hierarchy and the foundations of causal inference. In Probabilistic and causal inference: the works of judea pearl. 507--556.","DOI":"10.1145\/3501714.3501743"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00632"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19922"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475297"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01606"},{"key":"e_1_3_2_2_8_1","volume-title":"Sinkhorn distances: Lightspeed computation of optimal transport. Advances in neural information processing systems 26","author":"Cuturi Marco","year":"2013","unstructured":"Marco Cuturi. 2013. Sinkhorn distances: Lightspeed computation of optimal transport. Advances in neural information processing systems 26 (2013)."},{"key":"e_1_3_2_2_9_1","volume-title":"William Stafford Noble, and Ritambhara Singh","author":"Demetci Pinar","year":"2020","unstructured":"Pinar Demetci, Rebecca Santorella, Bj\u00f6rn Sandstede, William Stafford Noble, and Ritambhara Singh. 2020. Gromov-Wasserstein optimal transport to align single-cell multiomics data. BioRxiv (2020)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00510"},{"key":"e_1_3_2_2_11_1","volume-title":"Causal inference in statistics: A primer","author":"Glymour Madelyn","unstructured":"Madelyn Glymour, Judea Pearl, and Nicholas P Jewell. 2016. Causal inference in statistics: A primer. John Wiley & Sons."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00207"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3224872"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3148868"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01025"},{"key":"e_1_3_2_2_16_1","volume-title":"Tvr: A large-scale dataset for video-subtitle moment retrieval. In Computer Vision-ECCV 2020: 16th European Conference","author":"Lei Jie","year":"2020","unstructured":"Jie Lei, Licheng Yu, Tamara L Berg, and Mohit Bansal. 2020. Tvr: A large-scale dataset for video-subtitle moment retrieval. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXI 16. Springer, 447--463."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.142"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475540"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01350"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00380"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"e_1_3_2_2_22_1","volume-title":"Multi-Camera Video Scene Graphs for Surveillance Videos Indexing and Retrieval. In 2021 IEEE International Conference on Image Processing (ICIP). IEEE, 2383--2387","author":"Patel Toshal","year":"2021","unstructured":"Toshal Patel, Alvin Yan Hong Yao, Yu Qiang, Wei Tsang Ooi, and Roger Zimmermann. 2021. Multi-Camera Video Scene Graphs for Surveillance Videos Indexing and Retrieval. In 2021 IEEE International Conference on Image Processing (ICIP). IEEE, 2383--2387."},{"key":"e_1_3_2_2_23_1","volume-title":"Interpretation and identification of causal mediation. Psychological methods 19, 4","author":"Pearl Judea","year":"2014","unstructured":"Judea Pearl. 2014. Interpretation and identification of causal mediation. Psychological methods 19, 4 (2014), 459."},{"key":"e_1_3_2_2_24_1","volume-title":"Cambridge, UK: Cambridge University Press 19, 2","author":"Judea Pearl","year":"2000","unstructured":"Judea Pearl et al. 2000. Models, reasoning and inference. Cambridge, UK: Cambridge University Press 19, 2 (2000)."},{"key":"e_1_3_2_2_25_1","unstructured":"Judea Pearl and Dana Mackenzie. 2018. The book of why: the new science of cause and effect. Basic books."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_2_27_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20116"},{"key":"e_1_3_2_2_29_1","first-page":"1513","article-title":"Long-tailed classification by keeping the good and removing the bad momentum causal effect","volume":"33","author":"Tang Kaihua","year":"2020","unstructured":"Kaihua Tang, Jianqiang Huang, and Hanwang Zhang. 2020. Long-tailed classification by keeping the good and removing the bad momentum causal effect. Advances in Neural Information Processing Systems 33 (2020), 1513--1524.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01343"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548324"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01077"},{"key":"e_1_3_2_2_37_1","volume-title":"International conference on machine learning. PMLR","author":"Xu Kelvin","year":"2015","unstructured":"Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio. 2015. Show, attend and tell: Neural image caption generation with visual attention. In International conference on machine learning. PMLR, 2048--2057."},{"key":"e_1_3_2_2_38_1","volume-title":"Tel Aviv","author":"Xu Li","year":"2022","unstructured":"Li Xu, Haoxuan Qu, Jason Kuen, Jiuxiang Gu, and Jun Liu. 2022. Meta spatiotemporal debiasing for video scene graph generation. In Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXVII. Springer, 374--390."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01552"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.121"},{"key":"e_1_3_2_2_41_1","volume-title":"Interventional few-shot learning. Advances in neural information processing systems 33","author":"Yue Zhongqi","year":"2020","unstructured":"Zhongqi Yue, Hanwang Zhang, Qianru Sun, and Xian-Sheng Hua. 2020. Interventional few-shot learning. Advances in neural information processing systems 33 (2020), 2734--2746."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_36"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00527"},{"key":"e_1_3_2_2_45_1","first-page":"655","article-title":"Causal intervention for weakly-supervised semantic segmentation","volume":"33","author":"Zhang Dong","year":"2020","unstructured":"Dong Zhang, Hanwang Zhang, Jinhui Tang, Xian-Sheng Hua, and Qianru Sun. 2020. Causal intervention for weakly-supervised semantic segmentation. Advances in Neural Information Processing Systems 33 (2020), 655--666.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01180"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612249","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612249","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:57:42Z","timestamp":1755820662000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612249"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":46,"alternative-id":["10.1145\/3581783.3612249","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612249","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}