% Key papers for Talking face generation (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2021_one_17539,
  title = {{One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2019_hierarchical_14279,
  title = {{Hierarchical Cross-Modal Talking Face Generation With Dynamic Pixel-Wise Loss}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{aaai2019_talking_103568,
  title = {{Talking Face Generation by Adversarially Disentangled Audio-Visual Representation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4967},
}

@inproceedings{cvpr2021_flow_17030,
  title = {{Flow-Guided One-Shot Talking Face Generation With a High-Resolution Audio-Visual Dataset}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2022_faceformer_18825,
  title = {{FaceFormer: Speech-Driven 3D Facial Animation With Transformers}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2021_audio_16613,
  title = {{Audio-Driven Emotional Video Portraits}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{aaai2022_one_2502,
  title = {{One-Shot Talking Face Generation from Single-Speaker Audio-Visual Correlation Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/02531-one-shot-talking-face-generation-from-single-speaker-audio-visual-correlation-learning/},
}

@inproceedings{cvpr2023_seeing_22145,
  title = {{Seeing What You Said: Talking Face Generation Guided by a Lip Reading Expert}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21144},
}

@inproceedings{cvpr2021_lipsync3d_17357,
  title = {{LipSync3D: Data-Efficient Learning of Personalized 3D Talking Faces From Video Using Pose and Lighting Normalization}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2023_identity_21206,
  title = {{Identity-Preserving Talking Face Generation With Landmark and Appearance Priors}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/23138},
}

@inproceedings{aaai2022_synctalkface_2798,
  title = {{SyncTalkFace: Talking Face Generation with Precise Lip-Syncing via Audio-Lip Memory}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/02062-synctalkface-talking-face-generation-with-precise-lip-syncing-via-audio-lip-memory/},
}

@inproceedings{aaai2023_styletalk_4743,
  title = {{StyleTalk: One-Shot Talking Head Generation with Controllable Speaking Styles}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25280},
}

@inproceedings{aaai2021_write_1644,
  title = {{Write-a-speaker: Text-based Emotional and Rhythmic Talking-head Generation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/01911-write-a-speaker-text-based-emotional-and-rhythmic-talking-head-generation/},
}

@inproceedings{cvpr2018_every_13082,
  title = {{Every Smile Is Unique: Landmark-Guided Diverse Smile Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Wang_Every_Smile_Is_CVPR_2018_paper.html},
}

@inproceedings{cvpr2023_progressive_21924,
  title = {{Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22385},
}

@inproceedings{cvpr2023_dpe_20705,
  title = {{DPE: Disentanglement of Pose and Expression for General Video Portrait Editing}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21730},
}

@inproceedings{neurips2024_vasa_70559,
  title = {{VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96555},
}

@inproceedings{cvpr2023_high_21166,
  title = {{High-Fidelity and Freely Controllable Talking Head Video Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21890},
}

@inproceedings{neurips2021_fakeavceleb_62293,
  title = {{FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://openreview.net/forum?id=TAXFsg6ZaOl},
}

@inproceedings{aaai2022_flow_2119,
  title = {{Flow-Based Unconstrained Lip to Speech Generation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/00843-flow-based-unconstrained-lip-to-speech-generation/},
}

@inproceedings{cvpr2024_co_22977,
  title = {{Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30369},
}

@inproceedings{cvpr2024_facechain_23439,
  title = {{FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29489},
}

@inproceedings{cvpr2025_sonic_27707,
  title = {{Sonic: Shifting Focus to Global Audio Perception in Portrait Animation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33796},
}

@inproceedings{aaai2024_say_7258,
  title = {{Say Anything with Any Style}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28314},
}

@inproceedings{aaai2024_fg_5936,
  title = {{FG-EmoTalk: Talking Head Video Generation with Fine-Grained Controllable Facial Expressions}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28309},
}

@inproceedings{aaai2025_instructavatar_9572,
  title = {{InstructAvatar: Text-Guided Emotion and Motion Control for Avatar Generation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32877},
}

@inproceedings{cvpr2025_emotivetalk_26119,
  title = {{EmotiveTalk: Expressive Talking Head Generation through Audio Information Decoupling and Emotional Video Diffusion}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32963},
}

@inproceedings{cvpr2025_synergizing_27788,
  title = {{Synergizing Motion and Appearance: Multi-Scale Compensatory Codebooks for Talking Head Video Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32890},
}

@inproceedings{neurips2025_let_74821,
  title = {{Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=1aCYFQRvtz},
}

@inproceedings{cvpr2025_teller_27834,
  title = {{Teller: Real-Time Streaming Audio-Driven Portrait Animation with Autoregressive Motion Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34760},
}

@inproceedings{neurips2024_mimictalk_73319,
  title = {{MimicTalk: Mimicking a personalized and expressive 3D talking face in minutes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94126},
}

@inproceedings{aaai2025_glcf_9280,
  title = {{GLCF: A Global-Local Multimodal Coherence Analysis Framework for Talking Face Generation Detection}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/31982},
}

@inproceedings{aaai2025_moditalker_9970,
  title = {{MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32452},
}

@inproceedings{cvpr2025_diffusion_25947,
  title = {{Diffusion-based Realistic Listening Head Generation via Hybrid Motion Modeling}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/35094},
}

@inproceedings{icml2025_long_47792,
  title = {{Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44808},
}

@inproceedings{neurips2025_omnitalker_78411,
  title = {{OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=eK31JidsTN},
}

@inproceedings{aaai2025_anytalk_8128,
  title = {{AnyTalk: Multi-modal Driven Multi-domain Talking Head Generation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32874},
}

@inproceedings{aaai2025_occlusion_10155,
  title = {{Occlusion-Insensitive Talking Head Video Generation via Facelet Compensation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32277},
}

@inproceedings{aaai2025_vqtalker_11223,
  title = {{VQTalker: Towards Multilingual Talking Avatars Through Facial Motion Tokenization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32595},
}