{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:06:51Z","timestamp":1750309611245,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Institute of Information & communications Technology Planning & evaluation (IITP)","award":["RS-2019-II190421","RS-2020-II201821","RS-2024-00438686","RS-2024-00436936","RS-2024-00360227","RS-2023-0022544","IITP-2024-RS-2024-00436857","RS-2019-II190079"],"award-info":[{"award-number":["RS-2019-II190421","RS-2020-II201821","RS-2024-00438686","RS-2024-00436936","RS-2024-00360227","RS-2023-0022544","IITP-2024-RS-2024-00436857","RS-2019-II190079"]}]},{"name":"the Korea Creative Content Agency","award":["RS-2024-00348469","RS-2024-00345025"],"award-info":[{"award-number":["RS-2024-00348469","RS-2024-00345025"]}]},{"name":"Artificial intelligence industrial convergence cluster development project","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,31]]},"DOI":"10.1145\/3672608.3707973","type":"proceedings-article","created":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T18:26:21Z","timestamp":1747247181000},"page":"1282-1289","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MELA: Multi-Event Localization Answering Framework for Video Question Answering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3977-074X","authenticated-orcid":false,"given":"Jimyeong","family":"Han","sequence":"first","affiliation":[{"name":"Sungkyunkwan University, Suwon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7349-0018","authenticated-orcid":false,"given":"Sangpil","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0576-5806","authenticated-orcid":false,"given":"Hogun","family":"Park","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University (SKKU), Suwon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,5,14]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac Jean-Baptiste","year":"2022","unstructured":"Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in Neural Information Processing Systems 35 (2022), 23716\u201323736.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_2_1","volume-title":"Glance and focus: Memory prompting for multi-event video question answering. Advances in Neural Information Processing Systems 36","author":"Bai Ziyi","year":"2024","unstructured":"Ziyi Bai, Ruiping Wang, and Xilin Chen. 2024. Glance and focus: Memory prompting for multi-event video question answering. Advances in Neural Information Processing Systems 36 (2024)."},{"volume-title":"Natural Language Processing with Python: Analyzing Text with the Natural Language Toolkit","author":"Bird Steven","unstructured":"Steven Bird, Ewan Klein, and Edward Loper. 2009. Natural Language Processing with Python: Analyzing Text with the Natural Language Toolkit. O'Reilly Media, Inc. https:\/\/www.nltk.org\/book\/","key":"e_1_3_2_1_3_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_4_1","DOI":"10.1109\/CVPR52688.2022.00293"},{"key":"e_1_3_2_1_5_1","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung Hyung Won","year":"2024","unstructured":"Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Yunxuan Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, et al. 2024. Scaling instruction-finetuned language models. Journal of Machine Learning Research 25, 70 (2024), 1\u201353.","journal-title":"Journal of Machine Learning Research"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_6_1","DOI":"10.1109\/CVPR52729.2023.01855"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_7_1","DOI":"10.1109\/CVPR52729.2023.02193"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_8_1","DOI":"10.1109\/CVPR52729.2023.01419"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_9_1","DOI":"10.5120\/11638-7118"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_10_1","DOI":"10.1109\/CVPR46437.2021.01113"},{"key":"e_1_3_2_1_11_1","first-page":"3343","article-title":"Egotaskqa: Understanding human tasks in egocentric videos","volume":"35","author":"Jia Baoxiong","year":"2022","unstructured":"Baoxiong Jia, Ting Lei, Song-Chun Zhu, and Siyuan Huang. 2022. Egotaskqa: Understanding human tasks in egocentric videos. Advances in Neural Information Processing Systems 35 (2022), 3343\u20133360.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_12_1","volume-title":"Semi-parametric video-grounded text generation. arXiv preprint arXiv:2301.11507 abs\/2301.11507","author":"Kim Sungdong","year":"2023","unstructured":"Sungdong Kim, Jin-Hwa Kim, Jiyoung Lee, and Minjoon Seo. 2023. Semi-parametric video-grounded text generation. arXiv preprint arXiv:2301.11507 abs\/2301.11507 (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"International Conference on Machine Learning","volume":"3","author":"Dong-Hyun","unstructured":"Dong-Hyun Lee et al. 2013. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In International Conference on Machine Learning, Vol. 3. PMLR, 896."},{"key":"e_1_3_2_1_14_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International Conference on Machine Learning. PMLR, 19730\u201319742."},{"key":"e_1_3_2_1_15_1","volume-title":"Visual instruction tuning. Advances in Neural Information Processing Systems 36","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. Advances in Neural Information Processing Systems 36 (2023)."},{"key":"e_1_3_2_1_16_1","first-page":"25198","article-title":"Lgdn: Language-guided denoising network for video-language modeling","volume":"35","author":"Lu Haoyu","year":"2022","unstructured":"Haoyu Lu, Mingyu Ding, Nanyi Fei, Yuqi Huo, and Zhiwu Lu. 2022. Lgdn: Language-guided denoising network for video-language modeling. Advances in Neural Information Processing Systems 35 (2022), 25198\u201325211.","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_17_1","DOI":"10.1016\/j.neucom.2022.07.028"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_18_1","DOI":"10.1109\/CVPR52733.2024.01367"},{"key":"e_1_3_2_1_19_1","volume-title":"Faster, Cheaper and Lighter. arXiv preprint arXiv:1910.01108","author":"Sanh V","year":"2019","unstructured":"V Sanh. 2019. DistilBERT, A Distilled Version of BERT: Smaller, Faster, Cheaper and Lighter. arXiv preprint arXiv:1910.01108 (2019)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_20_1","DOI":"10.1007\/978-3-319-46448-0_31"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_21_1","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"e_1_3_2_1_22_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems","author":"Vaswani A","year":"2017","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017), 5998\u20136008."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_23_1","DOI":"10.1109\/CVPR52729.2023.00638"},{"key":"e_1_3_2_1_24_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_25_1","first-page":"8483","article-title":"Language models with image descriptors are strong few-shot video-language learners","volume":"35","author":"Wang Zhenhailong","year":"2022","unstructured":"Zhenhailong Wang, Manling Li, Ruochen Xu, Luowei Zhou, Jie Lei, Xudong Lin, Shuohang Wang, Ziyi Yang, Chenguang Zhu, Derek Hoiem, et al. 2022. Language models with image descriptors are strong few-shot video-language learners. Advances in Neural Information Processing Systems 35 (2022), 8483\u20138497.","journal-title":"Advances in Neural Information Processing Systems"},{"volume-title":"Proc. of the Conference of the Asia-Pacific","author":"Wang Zixu","unstructured":"Zixu Wang, Yujie Zhong, Yishu Miao, Lin Ma, and Lucia Specia. 2022. Contrastive video-language learning with fine-grained frame sampling. In Proc. of the Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing. Association for Computational Linguistics, 694\u2013705.","key":"e_1_3_2_1_26_1"},{"key":"e_1_3_2_1_27_1","volume-title":"Conference on Neural Information Processing Systems.","author":"Wu Bo","year":"2021","unstructured":"Bo Wu, Shoubin Yu, Zhenfang Chen, Joshua B Tenenbaum, and Chuang Gan. 2021. Star: A benchmark for situated reasoning in real-world videos. In Conference on Neural Information Processing Systems."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_28_1","DOI":"10.1109\/CVPR46437.2021.00965"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_29_1","DOI":"10.1145\/3123266.3123427"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_30_1","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"e_1_3_2_1_31_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 35 (2022), 124\u2013141.","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_32_1","DOI":"10.1109\/ICCV51070.2023.01413"},{"key":"e_1_3_2_1_33_1","volume-title":"Self-chained image-language model for video localization and question answering. Advances in Neural Information Processing Systems 36","author":"Yu Shoubin","year":"2024","unstructured":"Shoubin Yu, Jaemin Cho, Prateek Yadav, and Mohit Bansal. 2024. Self-chained image-language model for video localization and question answering. Advances in Neural Information Processing Systems 36 (2024)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_34_1","DOI":"10.1007\/978-3-030-01234-2_29"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_35_1","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"e_1_3_2_1_36_1","volume-title":"Proc. of the European Conference on Computer Vision","volume":"15104","author":"Zeng Yingsen","year":"2024","unstructured":"Yingsen Zeng, Yujie Zhong, Chengjian Feng, and Lin Ma. 2024. UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection. In Proc. of the European Conference on Computer Vision, Vol. 15104. Springer, 286\u2013304."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_37_1","DOI":"10.1007\/s11263-022-01653-1"}],"event":{"sponsor":["SIGAPP ACM Special Interest Group on Applied Computing"],"acronym":"SAC '25","name":"SAC '25: 40th ACM\/SIGAPP Symposium on Applied Computing","location":"Catania International Airport Catania Italy"},"container-title":["Proceedings of the 40th ACM\/SIGAPP Symposium on Applied Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3672608.3707973","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3672608.3707973","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:57:37Z","timestamp":1750298257000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3672608.3707973"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,31]]},"references-count":37,"alternative-id":["10.1145\/3672608.3707973","10.1145\/3672608"],"URL":"https:\/\/doi.org\/10.1145\/3672608.3707973","relation":{},"subject":[],"published":{"date-parts":[[2025,3,31]]},"assertion":[{"value":"2025-05-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}