{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:55:15Z","timestamp":1781538915920,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810680","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"1918-1926","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MultiSoundGen: Video-to-Audio Generation for Multi-Event Scenarios via SlowFast Contrastive Audio-Visual Pretraining and Direct Preference Optimization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7329-3671","authenticated-orcid":false,"given":"Jianxuan","family":"Yang","sequence":"first","affiliation":[{"name":"MiLM Plus, Xiaomi Inc., Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0824-9169","authenticated-orcid":false,"given":"Xiaoran","family":"Yang","sequence":"additional","affiliation":[{"name":"MiLM Plus, Xiaomi Inc. & School of Electronic Information, Wuhan University, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4810-2948","authenticated-orcid":false,"given":"Lipan","family":"Zhang","sequence":"additional","affiliation":[{"name":"MiLM Plus, Xiaomi Inc., Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3548-9874","authenticated-orcid":false,"given":"Xinyue","family":"Guo","sequence":"additional","affiliation":[{"name":"MiLM Plus, Xiaomi Inc., Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3549-1270","authenticated-orcid":false,"given":"Zhao","family":"Wang","sequence":"additional","affiliation":[{"name":"Mi Ecosystem, Xiaomi Inc., Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6825-7473","authenticated-orcid":false,"given":"Gongping","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Electronic Information, Wuhan University, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"e_1_3_3_1_3_2","first-page":"721","volume-title":"IEEE Int. Conf. Acoust. Speech Signal Process. (ICASSP)","author":"Chen Honglie","year":"2020","unstructured":"Honglie Chen, Weidi Xie, Andrea Vedaldi, and Andrew Zisserman. 2020. VGG-Sound: A Large-Scale Audio-Visual Dataset. In IEEE Int. Conf. Acoust. Speech Signal Process. (ICASSP). 721\u2013725."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02691"},{"key":"e_1_3_3_1_5_2","volume-title":"ICML","author":"Esser Patrick","year":"2024","unstructured":"Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas M\u00fcller, Harry Saini, Yam Levi, Dominik Lorenz, and et al.2024. Scaling Rectified Flow Transformers for High-Resolution Image Synthesis. In ICML."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Yuan Gong Yu-An Chung and James Glass. 2021. AST: Audio Spectrogram Transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2104.01778 (2021).","DOI":"10.21437\/Interspeech.2021-698"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Yuan Gong Alexander\u00a0H. Liu Andrew Rouditchenko and James Glass. 2022. UAVM: Towards Unifying Audio and Visual Models. IEEE Sign. Process. Letters (IEEE SPL) 29 (2022) 2437\u20132441.","DOI":"10.1109\/LSP.2022.3224688"},{"key":"e_1_3_3_1_11_2","unstructured":"Chia-Yu Hung Navonil Majumder Zhifeng Kong Ambuj Mehrish Amir\u00a0Ali Bagherzadeh Chuan Li Rafael Valle Bryan Catanzaro and et al.2024. TangoFlux: Super Fast and Faithful Text-to-Audio Generation with Flow Matching and Clap-Ranked Preference Optimization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.21037 (2024)."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Vladimir Iashin and Esa Rahtu. 2021. Taming Visually Guided Sound Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2110.08791 (2021).","DOI":"10.5244\/C.35.336"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448489"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888378"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413376"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Qiuqiang Kong Yin Cao Turab Iqbal Yuxuan Wang Wenwu Wang and Mark\u00a0D. Plumbley. 2020. PANNs: Large-Scale Pre-trained Audio Neural Networks for Audio Pattern Recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. (IEEE\/ACM TASLP) 28 (2020) 2880\u20132894.","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"e_1_3_3_1_17_2","unstructured":"Weijie Kong Qi Tian Zijian Zhang Rox Min Zuozhuo Dai Jin Zhou Jiangfeng Xiong Xin Li and et al.2024. Hun-yuanVideo: A Systematic Framework for Large Video Generative Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.03603 (2024)."},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887957"},{"key":"e_1_3_3_1_19_2","unstructured":"Huadai Liu Kaicheng Luo Jialei Wang Wen Wang Qian Chen Zhou Zhao and Wei Xue. 2025. ThinkSound: Chain-of-Thought Reasoning in Multimodal Large Language Models for Audio Generation and Editing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.21448 (2025)."},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Jing Liu Sihan Chen Xingjian He Longteng Guo Xinxin Zhu Weining Wang and Jinhui Tang. 2025. VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset. IEEE Trans. Pattern Anal. Mach. Intell. (IEEE TPAMI) 47 2 (2025) 708\u2013724.","DOI":"10.1109\/TPAMI.2024.3479776"},{"key":"e_1_3_3_1_21_2","unstructured":"Yixin Liu Kai Zhang Yuan Li Zhiling Yan Chujie Gao Ruoxi Chen Zhengqing Yuan Yue Huang and et al.2024. Sora: A Review on Background Technology Limitations and Opportunities of Large Vision Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.17177 (2024)."},{"key":"e_1_3_3_1_22_2","first-page":"48855","volume-title":"Adv. Neural Inform. Process. Syst. (NeurIPS)","author":"Luo Simian","year":"2023","unstructured":"Simian Luo, Chuanhao Yan, Chenxu Hu, and Hang Zhao. 2023. Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models. In Adv. Neural Inform. Process. Syst. (NeurIPS) , Vol.\u00a036. 48855\u201348876."},{"key":"e_1_3_3_1_23_2","unstructured":"Long Ouyang Jeff Wu Xu Jiang Diogo Almeida Carroll\u00a0L. Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal and et al.2022. Training Language Models to Follow Instructions with Human Feedback. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2203.02155 (2022)."},{"key":"e_1_3_3_1_24_2","first-page":"12493","volume-title":"Adv. Neural Inform. Process. Syst. (NeurIPS)","author":"Patrick Mandela","year":"2021","unstructured":"Mandela Patrick, Dylan Campbell, Yuki\u00a0M. Asano, Ishan Misra, Florian Metze, Christoph Feichtenhofer, Andrea Vedaldi, and Jo\u00e3o\u00a0F. Henriques. 2021. Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers. In Adv. Neural Inform. Process. Syst. (NeurIPS) , Vol.\u00a034. 12493\u201312506."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"e_1_3_3_1_26_2","unstructured":"Adam Polyak Amit Zohar Andrew Brown Andros Tjandra Animesh Sinha Ann Lee Apoorv Vyas and Bowen\u00a0Shi et al.2024. MovieGen: A Cast of Media Foundation Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.13720 (2024)."},{"key":"e_1_3_3_1_27_2","unstructured":"Alec Radford Jong\u00a0Wook Kim Chris Hallacy Aditya Ramesh Gabriel Goh Sandhini Agarwal Girish Sastry Amanda Askell and et al.2021. Learning Transferable Visual Models from Natural Language Supervision. PMLR 8748\u20138763."},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Rafael Rafailov Archit Sharma Eric Mitchell Stefano Ermon Christopher\u00a0D. Manning and Chelsea Finn. 2023. Direct Preference Optimization: Your Language Model Is Secretly a Reward Model. Adv. Neural Inform. Process. Syst. (NeurIPS) 36 (2023) 53728\u201353741.","DOI":"10.52202\/075280-2338"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096023"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Licai Sun Zheng Lian Bin Liu and Jianhua Tao. 2024. HiC-MAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition. Information Fusion 108 (2024) 102382.","DOI":"10.1016\/j.inffus.2024.102382"},{"key":"e_1_3_3_1_31_2","unstructured":"Alexander Tong Kilian Fatras Nikolay Malkin Guillaume Huguet Yanlei Zhang Jarrid Rector-Brooks Guy Wolf and Yoshua Bengio. 2024. Improving and Generalizing Flow-Based Generative Models with Minibatch Optimal Transport. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.00482 (2024)."},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888656"},{"key":"e_1_3_3_1_33_2","unstructured":"Aaron van\u00a0den Oord Yazhe Li and Oriol Vinyals. 2018. Representation Learning with Contrastive Predictive Coding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1807.03748 (2018)."},{"key":"e_1_3_3_1_34_2","unstructured":"Ilpo Viertola Vladimir Iashin and Esa Rahtu. 2024. Temporally Aligned Audio for Video with Autoregression. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.13689 (2024)."},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29475"},{"key":"e_1_3_3_1_37_2","unstructured":"Jun Wang Xijuan Zeng Chunyu Qiang Ruilong Chen Shiyao Wang Le Wang Wangjing Zhou Pengfei Cai and et al.2025. Kling-Foley: Multimodal Diffusion Transformer for High-Quality Video-to-Audio Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.19774 (2025)."},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"crossref","unstructured":"Yongqi Wang Wenxiang Guo Rongjie Huang Jiawei Huang Zehan Wang Fuming You Ruiqi Li and Zhou Zhao. 2024. Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matching. Adv. Neural Inform. Process. Syst. (NeurIPS) 37 (2024) 128118\u2013128138.","DOI":"10.52202\/079017-4068"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"e_1_3_3_1_40_2","unstructured":"Fanyi Xiao Yong\u00a0Jae Lee Kristen Grauman Jitendra Malik and Christoph Feichtenhofer. 2020. Audio-Visual SlowFast Networks for Video Recognition. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2001.08740 (2020)."},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00683"},{"key":"e_1_3_3_1_42_2","unstructured":"Manjie Xu Chenxing Li Xinyi Tu Yong Ren Rilin Chen Yu Gu Wei Liang and Dong Yu. 2024. Video-to-Audio Generation with Hidden Alignment. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.07464 (2024)."},{"key":"e_1_3_3_1_43_2","unstructured":"Yiming Zhang Yicheng Gu Yanhong Zeng Zhening Xing Yuancheng Wang Zhizheng Wu and Kai Chen. 2024. FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.01494 (2024)."}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:16:06Z","timestamp":1781536566000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810680"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":42,"alternative-id":["10.1145\/3805622.3810680","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810680","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}