% Key papers for Video-to-audio synthesis (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2023_mm_21494,
  title = {{MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22129},
}

@inproceedings{iclr2021_dance_30748,
  title = {{Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/3263},
}

@inproceedings{cvpr2023_conditional_20625,
  title = {{Conditional Generation of Audio From Video via Foley Analogies}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22328},
}

@inproceedings{aaai2024_diverse_5728,
  title = {{Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28486},
}

@inproceedings{neurips2020_audeo_59401,
  title = {{Audeo: Audio Generation for a Silent Performance Video}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17262},
}

@inproceedings{aaai2017_predicting_104388,
  title = {{Predicting Latent Narrative Mood Using Audio and Physiologic Data}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10625},
}

@inproceedings{cvpr2025_mmaudio_26871,
  title = {{MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33479},
}

@inproceedings{cvpr2022_audio_18308,
  title = {{Audio-Driven Neural Gesture Reenactment With Video Motion Graphs}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2023_physics_21864,
  title = {{Physics-Driven Diffusion Models for Impact Sound Synthesis From Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21628},
}

@inproceedings{cvpr2023_learning_21398,
  title = {{Learning To Dub Movies via Hierarchical Prosody Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/23106},
}

@inproceedings{aaai2024_v2meow_7738,
  title = {{V2Meow: Meowing to the Visual Beat via Video-to-Music Generation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28299},
}

@inproceedings{cvpr2025_vidmuse_28077,
  title = {{VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34954},
}

@inproceedings{cvpr2025_video_28088,
  title = {{Video-Guided Foley Sound Generation with Multimodal Controls}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34372},
}

@inproceedings{neurips2023_diff_69546,
  title = {{Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70378},
}

@inproceedings{aaai2025_read_10469,
  title = {{Read, Watch and Scream! Sound Generation from Text and Video}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33934},
}

@inproceedings{neurips2022_audio_65124,
  title = {{Audio-Driven Co-Speech Gesture Video Generation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55391},
}

@inproceedings{cvpr2022_more_19363,
  title = {{More Than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speech}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{neurips2024_tell_73625,
  title = {{Tell What You Hear From What You See - Video to Audio Generation Through Text}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93863},
}

@inproceedings{neurips2024_frieren_73990,
  title = {{Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matching}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93527},
}

@inproceedings{aaai2025_gvmgen_9297,
  title = {{GVMGen: A General Video-to-Music Generation Model with Hierarchical Attentions}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34474},
}

@inproceedings{aaai2024_danceanyway_5585,
  title = {{DanceAnyWay: Synthesizing Beat-Guided 3D Dances with Randomized Temporal Contrastive Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27836},
}

@inproceedings{aaai2025_tri_11108,
  title = {{Tri-Ergon: Fine-Grained Video-to-Audio Generation with Multi-Modal Conditions and LUFS Control}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32487},
}

@inproceedings{cvpr2025_vintage_28111,
  title = {{VinTAGe: Joint Video and Text Conditioning for Holistic Audio Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/35060},
}

@inproceedings{cvpr2025_audcast_25526,
  title = {{AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion Transformers}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32432},
}

@inproceedings{cvpr2025_emodubber_26117,
  title = {{EmoDubber: Towards High Quality and Emotion Controllable Movie Dubbing}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33077},
}

@inproceedings{cvpr2025_synchronized_27786,
  title = {{Synchronized Video-to-Audio Generation via Mel Quantization-Continuum Decomposition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34260},
}

@inproceedings{cvpr2025_foley_26297,
  title = {{Foley-Flow: Coordinated Video-to-Audio Generation with Masked Audio-Visual Alignment and Dynamic Conditional Flows}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32490},
}

@inproceedings{cvpr2025_learning_26763,
  title = {{Learning to Highlight Audio by Watching Movies}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34249},
}

@inproceedings{neurips2025_audio_74767,
  title = {{Audio-Sync Video Generation with Multi-Stream Temporal Control}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=12z8KLMQJD},
}

@inproceedings{iclr2025_tango_81794,
  title = {{TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/32094},
}

@inproceedings{cvpr2025_animate_25486,
  title = {{Animate and Sound an Image}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33511},
}