{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:08:49Z","timestamp":1784138929398,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":15,"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-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3808387","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:28:19Z","timestamp":1783693699000},"page":"5166-5170","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ATVG: Agentic System for Factually Grounded Travel Advertisement Video Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4151-8896","authenticated-orcid":false,"given":"Byung Eun","family":"Jeon","sequence":"first","affiliation":[{"name":"Snap Inc., Seattle, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7491-2454","authenticated-orcid":false,"given":"Xiao","family":"Bai","sequence":"additional","affiliation":[{"name":"Snap Inc., Palo Alto, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8934-3346","authenticated-orcid":false,"given":"Wen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Snap Inc., Bellevue, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1116-9923","authenticated-orcid":false,"given":"Jinchao","family":"Li","sequence":"additional","affiliation":[{"name":"Snap Inc., Bellevue, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International conference on machine learning. PMLR, 2206-2240","author":"Borgeaud Sebastian","year":"2022","unstructured":"Sebastian Borgeaud, Arthur Mensch, Jordan Hoffmann, Trevor Cai, Eliza Rutherford, Katie Millican, George Bm Van Den Driessche, Jean-Baptiste Lespiau, Bogdan Damoc, Aidan Clark, et al., 2022. Improving language models by retrieving from trillions of tokens. In International conference on machine learning. PMLR, 2206-2240."},{"key":"e_1_3_2_1_2_1","volume-title":"Re-imagen: Retrieval-augmented text-to-image generator. arXiv preprint arXiv:2209.14491","author":"Chen Wenhu","year":"2022","unstructured":"Wenhu Chen, Hexiang Hu, Chitwan Saharia, and William W Cohen. 2022. Re-imagen: Retrieval-augmented text-to-image generator. arXiv preprint arXiv:2209.14491 (2022)."},{"key":"e_1_3_2_1_3_1","volume-title":"Google Cloud Blog","author":"Davaajav Khulan","year":"2025","unstructured":"Khulan Davaajav and Hussain Chinoy. [n.d.]. The ultimate prompting guide for Veo 3.1. https:\/\/cloud.google.com\/blog\/products\/ai-machine-learning\/ultimate-prompting-guide-for-veo-3-1. Google Cloud Blog, October 16, 2025. Accessed: 2026-01-20."},{"key":"e_1_3_2_1_4_1","volume-title":"Agentic Video Intelligence: A Flexible Framework for Advanced Video Exploration and Understanding. arXiv preprint arXiv:2511.14446","author":"Gao Hong","year":"2025","unstructured":"Hong Gao, Yiming Bao, Xuezhen Tu, Yutong Xu, Yue Jin, Yiyang Mu, Bin Zhong, Linan Yue, and Min-Ling Zhang. 2025. Agentic Video Intelligence: A Flexible Framework for Advanced Video Exploration and Understanding. arXiv preprint arXiv:2511.14446 (2025)."},{"key":"e_1_3_2_1_5_1","volume-title":"International conference on machine learning. PMLR, 3929-3938","author":"Guu Kelvin","year":"2020","unstructured":"Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Mingwei Chang. 2020. Retrieval augmented language model pre-training. In International conference on machine learning. PMLR, 3929-3938."},{"key":"e_1_3_2_1_6_1","volume-title":"Videorag: Retrieval-augmented generation over video corpus. arXiv preprint arXiv:2501.05874","author":"Jeong Soyeong","year":"2025","unstructured":"Soyeong Jeong, Kangsan Kim, Jinheon Baek, and Sung Ju Hwang. 2025. Videorag: Retrieval-augmented generation over video corpus. arXiv preprint arXiv:2501.05874 (2025)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i28.35356"},{"key":"e_1_3_2_1_8_1","unstructured":"Patrick Lewis Ethan Perez Aleksandra Piktus Fabio Petroni Vladimir Karpukhin Naman Goyal Heinrich K\u00fcttler Mike Lewis Wen-tau Yih Tim Rockt\u00e4schel et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems Vol. 33 (2020) 9459-9474."},{"key":"e_1_3_2_1_9_1","volume-title":"Videodirectorgpt: Consistent multi-scene video generation via llm-guided planning. arXiv preprint arXiv:2309.15091","author":"Lin Han","year":"2023","unstructured":"Han Lin, Abhay Zala, Jaemin Cho, and Mohit Bansal. 2023. Videodirectorgpt: Consistent multi-scene video generation via llm-guided planning. arXiv preprint arXiv:2309.15091 (2023)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01591"},{"key":"e_1_3_2_1_11_1","volume-title":"Videodrafter: Content-consistent multi-scene video generation with llm. CoRR","author":"Long Fuchen","year":"2024","unstructured":"Fuchen Long, Zhaofan Qiu, Ting Yao, and Tao Mei. 2024. Videodrafter: Content-consistent multi-scene video generation with llm. CoRR (2024)."},{"key":"e_1_3_2_1_12_1","unstructured":"Pixabay. [n.d.]. Content License Summary. https:\/\/pixabay.com\/service\/license-summary\/. Accessed: 2026-01-19."},{"key":"e_1_3_2_1_13_1","unstructured":"Pixabay (a Canva Germany GmbH brand). [n.d.]. Pixabay. https:\/\/pixabay.com\/. Accessed: 2026-01-19."},{"key":"e_1_3_2_1_14_1","volume-title":"MAViS: A Multi-Agent Framework for Long-Sequence Video Storytelling. arXiv preprint arXiv:2508.08487","author":"Wang Qian","year":"2025","unstructured":"Qian Wang, Ziqi Huang, Ruoxi Jia, Paul Debevec, and Ning Yu. 2025. MAViS: A Multi-Agent Framework for Long-Sequence Video Storytelling. arXiv preprint arXiv:2508.08487 (2025)."},{"key":"e_1_3_2_1_15_1","volume-title":"Compositional 3d-aware video generation with llm director. Advances in neural information processing systems","author":"Zhu Hanxin","year":"2024","unstructured":"Hanxin Zhu, Tianyu He, Anni Tang, Junliang Guo, Zhibo Chen, and Jiang Bian. 2024. Compositional 3d-aware video generation with llm director. Advances in neural information processing systems, Vol. 37 (2024), 131618-131644."}],"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":"2026-07-15T17:25:13Z","timestamp":1784136313000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3808387"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":15,"alternative-id":["10.1145\/3805712.3808387","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3808387","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"}}]}}