{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:03:45Z","timestamp":1784138625308,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Natural Science Foundation of China","award":["72293575"],"award-info":[{"award-number":["72293575"]}]},{"name":"Joint Research Project on Integration of Culture and Science and Technology between Chinese Academy of Sciences and Hunan Province","award":["2024JK4003"],"award-info":[{"award-number":["2024JK4003"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809835","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"3781-3786","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Multi-Granularity Game-Theoretic Approach to Weakly Supervised Temporal Article Grounding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0003-8452","authenticated-orcid":false,"given":"Shuyi","family":"He","sequence":"first","affiliation":[{"name":"State Key Laboratory for Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4087-1505","authenticated-orcid":false,"given":"Hao","family":"Wen","sequence":"additional","affiliation":[{"name":"Beijing Wenge Technology Co., Ltd., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2554-4984","authenticated-orcid":false,"given":"Pu","family":"Zou","sequence":"additional","affiliation":[{"name":"Tianwen Digital Media Technology (Hunan) Co., Ltd., Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9687-3610","authenticated-orcid":false,"given":"Song","family":"Zhou","sequence":"additional","affiliation":[{"name":"Beijing Wenge Technology Co., Ltd., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1929-8404","authenticated-orcid":false,"given":"Qingchao","family":"Kong","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16175"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.593"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.639"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 4171-4186."},{"key":"e_1_3_2_1_7_1","volume-title":"European Conference on Computer Vision. Springer, 290-311","author":"Fang Xiang","year":"2024","unstructured":"Xiang Fang, Zeyu Xiong, Wanlong Fang, Xiaoye Qu, Chen Chen, Jianfeng Dong, Keke Tang, Pan Zhou, Yu Cheng, and Daizong Liu. 2024. Rethinking weakly-supervised video temporal grounding from a game perspective. In European Conference on Computer Vision. Springer, 290-311."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"38","author":"Geng Wenjia","year":"2024","unstructured":"Wenjia Geng, Yong Liu, Lei Chen, Sujia Wang, Jie Zhou, and Yansong Tang. 2024. Learning Multi-Scale Video-Text Correspondence for Weakly Supervised Temporal Article Grounding. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38. 1896-1904."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32341"},{"key":"e_1_3_2_1_12_1","volume-title":"The Thirteenth International Conference on Learning Representations.","author":"Guo Yongxin","year":"2025","unstructured":"Yongxin Guo, Jingyu Liu, Mingda Li, Qingbin Liu, Xi Chen, and Xiaoying Tang. 2025. TRACE: Temporal Grounding Video LLM via Causal Event Modeling. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-017-2527-9_3"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00244"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28059"},{"key":"e_1_3_2_1_17_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3532626"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1167"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01105"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2930041"},{"key":"e_1_3_2_1_22_1","volume-title":"Vlanet: Video-language alignment network for weakly-supervised video moment retrieval. In Computer Vision--ECCV 2020: 16th European Conference","author":"Ma Minuk","year":"2020","unstructured":"Minuk Ma, Sunjae Yoon, Junyeong Kim, Youngjoon Lee, Sunghun Kang, and Chang D Yoo. 2020. Vlanet: Video-language alignment network for weakly-supervised video moment retrieval. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXVIII 16. Springer, 156-171."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/2512538.2512553"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Lloyd S Shapley et al. 1953. A value for n-person games. (1953).","DOI":"10.1515\/9781400881970-018"},{"key":"e_1_3_2_1_27_1","volume-title":"Weakly-supervised multi-level attentional reconstruction network for grounding textual queries in videos. arXiv preprint arXiv:2003.07048","author":"Song Yijun","year":"2020","unstructured":"Yijun Song, Jingwen Wang, Lin Ma, Zhou Yu, and Jun Yu. 2020. Weakly-supervised multi-level attentional reconstruction network for grounding textual queries in videos. arXiv preprint arXiv:2003.07048 (2020)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01288"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3096087"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00308"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01249"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112592"}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:08:45Z","timestamp":1784135325000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809835"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":33,"alternative-id":["10.1145\/3805712.3809835","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809835","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}