{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T10:02:00Z","timestamp":1765620120258,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":7,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1145\/3757374.3771475","type":"proceedings-article","created":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T09:58:37Z","timestamp":1765619917000},"page":"1-2","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Video2Song: Video-to-Song Generation via Retrieval-Augmented Prompt Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7832-7126","authenticated-orcid":false,"given":"Zijiao","family":"Yin","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China and MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9331-4593","authenticated-orcid":false,"given":"Sifei","family":"Li","sequence":"additional","affiliation":[{"name":"MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6502-145X","authenticated-orcid":false,"given":"Weiming","family":"Dong","sequence":"additional","affiliation":[{"name":"MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,12,14]]},"reference":[{"key":"e_1_3_3_2_2_1","unstructured":"Andrea Agostinelli Timo\u00a0I Denk Zal\u00e1n Borsos Jesse Engel Mauro Verzetti Antoine Caillon Qingqing Huang Aren Jansen Adam Roberts Marco Tagliasacchi et\u00a0al. 2023. MusicLM: Generating Music from Text. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2301.11325 (2023)."},{"key":"e_1_3_3_2_3_1","volume-title":"Machine Learning for Music Discovery Workshop, International Conference on Machine Learning (ICML)","author":"Bogdanov Dmitry","year":"2019","unstructured":"Dmitry Bogdanov, Minz Won, Philip Tovstogan, Alastair Porter, and Xavier Serra. 2019. The MTG-Jamendo Dataset for Automatic Music Tagging. In Machine Learning for Music Discovery Workshop, International Conference on Machine Learning (ICML)."},{"key":"e_1_3_3_2_4_1","unstructured":"Junmin Gong Sean Zhao Sen Wang Shengyuan Xu and Joe Guo. 2025. ACE-Step: A Step Towards Music Generation Foundation Model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.00045 (2025)."},{"key":"e_1_3_3_2_5_1","volume-title":"Advances in Neural Information Processing Systems","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_3_2_6_1","unstructured":"Sifei Li Mining Tan Feier Shen Minyan Luo Zijiao Yin Fan Tang Weiming Dong and Changsheng Xu. 2025. A Survey on Cross-Modal Interaction Between Music and Multimodal Data. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.12796 (2025)."},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_3_2_8_1","unstructured":"Xingjian Zhang Xi Weng Yihao Yue Zhaoxin Fan Wenjun Wu and Lei Huang. 2025. TinyLLaVA-Video: Towards Smaller LMMs for Video Understanding with Group Resampler. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.15513 (2025)."}],"event":{"name":"SA Posters '25: SIGGRAPH Asia 2025 Posters","location":"Hong Kong Hong Kong","acronym":"SA Posters '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the SIGGRAPH Asia 2025 Posters"],"original-title":[],"deposited":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T09:58:39Z","timestamp":1765619919000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757374.3771475"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":7,"alternative-id":["10.1145\/3757374.3771475","10.1145\/3757374"],"URL":"https:\/\/doi.org\/10.1145\/3757374.3771475","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]},"assertion":[{"value":"2025-12-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}