{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:21:11Z","timestamp":1777656071274,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Sichuan Science and Technology Program","award":["2023-XT00-00001-GX"],"award-info":[{"award-number":["2023-XT00-00001-GX"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222203; 62072080;"],"award-info":[{"award-number":["62222203; 62072080;"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"New Cornerstone Science Foundation"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680948","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"6472-6481","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Counterfactually Augmented Event Matching for De-biased Temporal Sentence Grounding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2209-651X","authenticated-orcid":false,"given":"Xun","family":"Jiang","sequence":"first","affiliation":[{"name":"Center for Future Media & School of Computer Science and Engineering University of Electronic Science and Technology of China, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6480-3457","authenticated-orcid":false,"given":"Zhuoyuan","family":"Wei","sequence":"additional","affiliation":[{"name":"Center for Future Media & School of Computer Science and Engineering University of Electronic Science and Technology of China, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6340-012X","authenticated-orcid":false,"given":"Shenshen","family":"Li","sequence":"additional","affiliation":[{"name":"Center for Future Media & School of Computer Science and Engineering University of Electronic Science and Technology of China, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5685-3123","authenticated-orcid":false,"given":"Xing","family":"Xu","sequence":"additional","affiliation":[{"name":"Center for Future Media & School of Computer Science and Engineering University of Electronic Science and Technology of China, University of Electronic Science and Technology of China & College of Electronic and Information Engineering, Tongji University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2549-8322","authenticated-orcid":false,"given":"Jingkuan","family":"Song","sequence":"additional","affiliation":[{"name":"Center for Future Media & School of Computer Science and Engineering University of Electronic Science and Technology of China, University of Electronic Science and Technology of China, & College of Electronic and Information Engineering, Tongji University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9872-8451","authenticated-orcid":false,"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[{"name":"Center for Future Media & School of Computer Science and Engineering University of Electronic Science and Technology of China, University of Electronic Science and Technology of China & College of Electronic and Information Engineering, Tongji University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3396272"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3475723.3484247"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462823"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"e_1_3_2_1_8_1","article-title":"Semantic decoupling network for temporal language grounding","author":"Jiang Xun","year":"2022","unstructured":"Xun Jiang, Xing Xu, Jingran Zhang, Fumin Shen, Zuo Cao, and Heng Tao Shen. Sdn: Semantic decoupling network for temporal language grounding. IEEE Transactions on Neural Networks and Learning Systems, pages 6598--6612, 2022.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems, pages 6598--6612"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_8"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25204"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612401"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547969"},{"key":"e_1_3_2_1_13_1","first-page":"16196","volume-title":"Advances in Neural Information Processing Systems","author":"Veitch Victor","year":"2021","unstructured":"Victor Veitch, Alexander D'Amour, Steve Yadlowsky, and Jacob Eisenstein. Counterfactual invariance to spurious correlations in text classification. In Advances in Neural Information Processing Systems, pages 16196--16208, 2021."},{"key":"e_1_3_2_1_14_1","volume-title":"International Conference on Learning Representations","author":"Black Emily","year":"2021","unstructured":"Emily Black, Zifan Wang, and Matt Fredrikson. Consistent counterfactuals for deep models. In International Conference on Learning Representations, 2021."},{"key":"e_1_3_2_1_15_1","volume-title":"Generalizing to unseen domains via distribution matching. arXiv preprint arXiv:1911.00804","author":"Albuquerque Isabela","year":"2019","unstructured":"Isabela Albuquerque, Jo\u00e3o Monteiro, Mohammad Darvishi, Tiago H Falk, and Ioannis Mitliagkas. Generalizing to unseen domains via distribution matching. arXiv preprint arXiv:1911.00804, 2019."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1214\/20-AOS2004"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2022.1275"},{"key":"e_1_3_2_1_18_1","first-page":"36","article-title":"On the adversarial robustness of out-of-distribution generalization models","author":"Zou Xin","year":"2024","unstructured":"Xin Zou and Weiwei Liu. On the adversarial robustness of out-of-distribution generalization models. Advances in Neural Information Processing Systems, 36, 2024.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11596"},{"key":"e_1_3_2_1_20_1","first-page":"31","article-title":"Minimax statistical learning with wasserstein distances","author":"Lee Jaeho","year":"2018","unstructured":"Jaeho Lee and Maxim Raginsky. Minimax statistical learning with wasserstein distances. Advances in Neural Information Processing Systems, 31, 2018.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_21_1","volume-title":"Domain-wise adversarial training for out-of-distribution generalization","author":"Xin Shiji","year":"2021","unstructured":"Shiji Xin, Yifei Wang, Jingtong Su, and Yisen Wang. Domain-wise adversarial training for out-of-distribution generalization. 2021."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2024.3405541"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29795"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548211"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02538"},{"key":"e_1_3_2_1_26_1","volume-title":"On the out-of-distribution generalization of multimodal large language models. arXiv preprint arXiv:2402.06599","author":"Zhang Xingxuan","year":"2024","unstructured":"Xingxuan Zhang, Jiansheng Li, Wenjing Chu, Junjia Hai, Renzhe Xu, Yuqing Yang, Shikai Guan, Jiazheng Xu, and Peng Cui. On the out-of-distribution generalization of multimodal large language models. arXiv preprint arXiv:2402.06599, 2024."},{"key":"e_1_3_2_1_27_1","article-title":"Recovering generalization via pre-training-like knowledge distillation for out-of-distribution visual question answering","author":"Song Yaguang","year":"2023","unstructured":"Yaguang Song, Xiaoshan Yang, Yaowei Wang, and Changsheng Xu. Recovering generalization via pre-training-like knowledge distillation for out-of-distribution visual question answering. IEEE Transactions on Multimedia, 2023.","journal-title":"IEEE Transactions on Multimedia"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548309"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612244"},{"key":"e_1_3_2_1_30_1","article-title":"Multigrained attention network with mutual exclusion for composed query-based image retrieval","author":"Li Shenshen","year":"2023","unstructured":"Shenshen Li, Xing Xu, Xun Jiang, Fumin Shen, Xin Liu, and Heng Tao Shen. Multigrained attention network with mutual exclusion for composed query-based image retrieval. IEEE Transactions on Circuits and Systems for Video Technology, pages 2959--2972, 2023.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology, pages 2959--2972"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045530"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00250"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612394"},{"key":"e_1_3_2_1_34_1","volume-title":"Bias-conflict sample synthesis and adversarial removal debias strategy for temporal sentence grounding in video. arXiv preprint arXiv:2401.07567","author":"Qi Zhaobo","year":"2024","unstructured":"Zhaobo Qi, Yibo Yuan, Xiaowen Ruan, Shuhui Wang, Weigang Zhang, and Qingming Huang. Bias-conflict sample synthesis and adversarial removal debias strategy for temporal sentence grounding in video. arXiv preprint arXiv:2401.07567, 2024."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01824"},{"key":"e_1_3_2_1_36_1","first-page":"30","article-title":"When worlds collide: integrating different counterfactual assumptions in fairness","author":"Russell Chris","year":"2017","unstructured":"Chris Russell, Matt J Kusner, Joshua Loftus, and Ricardo Silva. When worlds collide: integrating different counterfactual assumptions in fairness. Advances in Neural Information Processing Systems, 30, 2017.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511948"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462855"},{"key":"e_1_3_2_1_39_1","article-title":"Data augmented sequential recommendation based on counterfactual thinking","author":"Chen Xu","year":"2022","unstructured":"Xu Chen, Zhenlei Wang, Hongteng Xu, Jingsen Zhang, Yongfeng Zhang, Wayne Xin Zhao, and Ji-Rong Wen. Data augmented sequential recommendation based on counterfactual thinking. IEEE Transactions on Knowledge and Data Engineering, 2022.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401083"},{"key":"e_1_3_2_1_41_1","volume-title":"Core: A retrieve-then-edit framework for counterfactual data generation. arXiv preprint arXiv:2210.04873","author":"Dixit Tanay","year":"2022","unstructured":"Tanay Dixit, Bhargavi Paranjape, Hannaneh Hajishirzi, and Luke Zettlemoyer. Core: A retrieve-then-edit framework for counterfactual data generation. arXiv preprint arXiv:2210.04873, 2022."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.374"},{"key":"e_1_3_2_1_43_1","volume-title":"Yeon Ju Kim, and Yong Man Ro. What if...?: Counterfactual inception to mitigate hallucination effects in large multimodal models. arXiv preprint arXiv:2403.13513","author":"Kim Junho","year":"2024","unstructured":"Junho Kim, Yeon Ju Kim, and Yong Man Ro. What if...?: Counterfactual inception to mitigate hallucination effects in large multimodal models. arXiv preprint arXiv:2403.13513, 2024."},{"key":"e_1_3_2_1_44_1","first-page":"36","article-title":"Automatically constructed counterfactual examples for image-text pairs","author":"Le Tiep","year":"2024","unstructured":"Tiep Le, Vasudev Lal, and Phillip Howard. Coco-counterfactuals: Automatically constructed counterfactual examples for image-text pairs. Advances in Neural Information Processing Systems, 36, 2024.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29795"},{"key":"e_1_3_2_1_46_1","first-page":"10044","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Abbasnejad Ehsan","year":"2020","unstructured":"Ehsan Abbasnejad, Damien Teney, Amin Parvaneh, Javen Shi, and Anton van den Hengel. Counterfactual vision and language learning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pages 10044--10054, 2020."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2967597"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_51_1","first-page":"4171","volume-title":"Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. BERT: pre-training of deep bidirectional transformers for language understanding. In Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4171--4186, 2019."},{"key":"e_1_3_2_1_52_1","first-page":"73","volume-title":"Siamese neural networks: An overview. Artificial neural networks","author":"Chicco Davide","year":"2021","unstructured":"Davide Chicco. Siamese neural networks: An overview. Artificial neural networks, pages 73--94, 2021."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00304"},{"key":"e_1_3_2_1_54_1","volume-title":"International Conference on Learning Representations","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In International Conference on Learning Representations, 2015."},{"key":"e_1_3_2_1_55_1","first-page":"36","article-title":"Generative video moment retrieval from random to real","author":"Li Pandeng","year":"2024","unstructured":"Pandeng Li, Chen-Wei Xie, Hongtao Xie, Liming Zhao, Lei Zhang, Yun Zheng, Deli Zhao, and Yongdong Zhang. Momentdiff: Generative video moment retrieval from random to real. Advances in Neural Information Processing Systems, 36, 2024.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02207"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01830"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28177"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680948","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680948","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:34Z","timestamp":1750295854000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680948"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":58,"alternative-id":["10.1145\/3664647.3680948","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680948","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}