{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:47:21Z","timestamp":1765500441258,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","funder":[{"name":"the Fundamental Research Funds for the Central Universities","award":["DUT24MS003"],"award-info":[{"award-number":["DUT24MS003"]}]},{"name":"the Liaoning Provincial Natural Science Foundation Joint Fund Program","award":["2023- MSBA-003"],"award-info":[{"award-number":["2023- MSBA-003"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3760857","type":"proceedings-article","created":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T18:37:32Z","timestamp":1762799852000},"page":"5545-5549","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Structuring Video Semantics with Temporal Triplets for Zero-Shot Video Question Answering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1116-1016","authenticated-orcid":false,"given":"Linlin","family":"Zong","sequence":"first","affiliation":[{"name":"Dalian University Of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0031-8847","authenticated-orcid":false,"given":"Xinyu","family":"Zhai","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9036-4665","authenticated-orcid":false,"given":"Xinyue","family":"Liu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9166-3138","authenticated-orcid":false,"given":"Wenxin","family":"Liang","sequence":"additional","affiliation":[{"name":"Dalian University Of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0180-3740","authenticated-orcid":false,"given":"Xianchao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Dalian University Of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5453-978X","authenticated-orcid":false,"given":"Bo","family":"Xu","sequence":"additional","affiliation":[{"name":"Dalian University Of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang et al. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025).","key":"e_1_3_2_1_1_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_2_1","DOI":"10.1109\/TIP.2024.3358726"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_3_1","DOI":"10.52202\/079017-0614"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_4_1","DOI":"10.1109\/CVPR52733.2024.02510"},{"key":"e_1_3_2_1_5_1","volume-title":"Jingkang Yang, Chunyuan Li, and Ziwei Liu.","author":"Li Bo","year":"2025","unstructured":"Bo Li, Yuanhan Zhang, Liangyu Chen, Jinghao Wang, Fanyi Pu, Joshua Adrian Cahyono, Jingkang Yang, Chunyuan Li, and Ziwei Liu. 2025. Otter: A multi-modal model with in-context instruction tuning. IEEE Transactions on Pattern Analysis and Machine Intelligence (2025)."},{"key":"e_1_3_2_1_6_1","volume-title":"Videochat: Chat-centric video understanding. arXiv preprint arXiv:2305.06355","author":"Li KunChang","year":"2023","unstructured":"KunChang Li, Yinan He, Yi Wang, Yizhuo Li, Wenhai Wang, Ping Luo, Yali Wang, Limin Wang, and Yu Qiao. 2023. Videochat: Chat-centric video understanding. arXiv preprint arXiv:2305.06355 (2023)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_7_1","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"e_1_3_2_1_8_1","volume-title":"Video-llava: Learning united visual representation by alignment before projection. arXiv preprint arXiv:2311.10122","author":"Lin Bin","year":"2023","unstructured":"Bin Lin, Yang Ye, Bin Zhu, Jiaxi Cui, Munan Ning, Peng Jin, and Li Yuan. 2023. Video-llava: Learning united visual representation by alignment before projection. arXiv preprint arXiv:2311.10122 (2023)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_9_1","DOI":"10.1109\/CVPR52733.2024.02497"},{"key":"e_1_3_2_1_10_1","volume-title":"Video-chatgpt: Towards detailed video understanding via large vision and language models. arXiv preprint arXiv:2306.05424","author":"Maaz Muhammad","year":"2023","unstructured":"Muhammad Maaz, Hanoona Rasheed, Salman Khan, and Fahad Shahbaz Khan. 2023. Video-chatgpt: Towards detailed video understanding via large vision and language models. arXiv preprint arXiv:2306.05424 (2023)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_11_1","DOI":"10.1109\/CVPR52733.2024.01367"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_12_1","DOI":"10.1109\/TMM.2022.3169065"},{"key":"e_1_3_2_1_13_1","volume-title":"Question-instructed visual descriptions for zero-shot video question answering. arXiv preprint arXiv:2402.10698","author":"Romero David","year":"2024","unstructured":"David Romero and Thamar Solorio. 2024. Question-instructed visual descriptions for zero-shot video question answering. arXiv preprint arXiv:2402.10698 (2024)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_14_1","DOI":"10.1007\/978-3-031-20074-8_9"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_15_1","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"e_1_3_2_1_16_1","volume-title":"Internvideo: General video foundation models via generative and discriminative learning. arXiv preprint arXiv:2212.03191","author":"Wang Yi","year":"2022","unstructured":"Yi Wang, Kunchang Li, Yizhuo Li, Yinan He, Bingkun Huang, Zhiyu Zhao, Hongjie Zhang, Jilan Xu, Yi Liu, Zun Wang, et al., 2022. Internvideo: General video foundation models via generative and discriminative learning. arXiv preprint arXiv:2212.03191 (2022)."},{"key":"e_1_3_2_1_17_1","volume-title":"Star: A benchmark for situated reasoning in real-world videos. arXiv preprint arXiv:2405.09711","author":"Wu Bo","year":"2024","unstructured":"Bo Wu, Shoubin Yu, Zhenfang Chen, Joshua B Tenenbaum, and Chuang Gan. 2024. Star: A benchmark for situated reasoning in real-world videos. arXiv preprint arXiv:2405.09711 (2024)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_18_1","DOI":"10.1109\/CVPR46437.2021.00965"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_19_1","DOI":"10.1145\/3123266.3123427"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_20_1","DOI":"10.1109\/CVPR.2016.571"},{"key":"e_1_3_2_1_21_1","first-page":"124","article-title":"Zero-shot video question answering via frozen bidirectional language models","volume":"35","author":"Yang Antoine","year":"2022","unstructured":"Antoine Yang, Antoine Miech, Josef Sivic, Ivan Laptev, and Cordelia Schmid. 2022. Zero-shot video question answering via frozen bidirectional language models. Advances in Neural Information Processing Systems, Vol. 35 (2022), 124-141.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_22_1","first-page":"76749","article-title":"Self-chained image-language model for video localization and question answering","volume":"36","author":"Yu Shoubin","year":"2023","unstructured":"Shoubin Yu, Jaemin Cho, Prateek Yadav, and Mohit Bansal. 2023. Self-chained image-language model for video localization and question answering. Advances in Neural Information Processing Systems, Vol. 36 (2023), 76749-76771.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_23_1","volume-title":"Video-llama: An instruction-tuned audio-visual language model for video understanding. arXiv preprint arXiv:2306.02858","author":"Zhang Hang","year":"2023","unstructured":"Hang Zhang, Xin Li, and Lidong Bing. 2023b. Video-llama: An instruction-tuned audio-visual language model for video understanding. arXiv preprint arXiv:2306.02858 (2023)."},{"key":"e_1_3_2_1_24_1","volume-title":"Llama-adapter: Efficient fine-tuning of language models with zero-init attention. arXiv preprint arXiv:2303.16199","author":"Zhang Renrui","year":"2023","unstructured":"Renrui Zhang, Jiaming Han, Chris Liu, Peng Gao, Aojun Zhou, Xiangfei Hu, Shilin Yan, Pan Lu, Hongsheng Li, and Yu Qiao. 2023a. Llama-adapter: Efficient fine-tuning of language models with zero-init attention. arXiv preprint arXiv:2303.16199 (2023)."}],"event":{"sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"acronym":"CIKM '25","name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","location":"Seoul Republic of Korea"},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3760857","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:44:24Z","timestamp":1765500264000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3760857"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":24,"alternative-id":["10.1145\/3746252.3760857","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3760857","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}