% Key papers for Self-supervised audio-visual representation learning (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2022_balanced_18346,
  title = {{Balanced Multimodal Learning via On-the-Fly Gradient Modulation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2021_audio_16614,
  title = {{Audio-Visual Instance Discrimination with Cross-Modal Agreement}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2019_deep_14030,
  title = {{Deep Multimodal Clustering for Unsupervised Audiovisual Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{neurips2020_self_60803,
  title = {{Self-Supervised MultiModal Versatile Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17391},
}

@inproceedings{iclr2022_learning_31405,
  title = {{Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6707},
}

@inproceedings{cvpr2021_distilling_16880,
  title = {{Distilling Audio-Visual Knowledge by Compositional Contrastive Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2021_looking_17369,
  title = {{Looking Into Your Speech: Learning Cross-Modal Affinity for Audio-Visual Speech Separation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2023_collecting_20605,
  title = {{Collecting Cross-Modal Presence-Absence Evidence for Weakly-Supervised Audio-Visual Event Perception}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22448},
}

@inproceedings{aaai2022_multi_2437,
  title = {{Multi-Modal Perception Attention Network with Self-Supervised Learning for Audio-Visual Speaker Tracking}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/01456-multi-modal-perception-attention-network-with-self-supervised-learning-for-audio-visual-speaker-tracking/},
}

@inproceedings{cvpr2024_unveiling_25174,
  title = {{Unveiling the Power of Audio-Visual Early Fusion Transformers with Dense Interactions through Masked Modeling}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30871},
}

@inproceedings{aaai2021_enhancing_525,
  title = {{Enhancing Audio-Visual Association with Self-Supervised Curriculum Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/03351-enhancing-audio-visual-association-with-self-supervised-curriculum-learning/},
}

@inproceedings{aaai2024_xkd_7834,
  title = {{XKD: Cross-Modal Knowledge Distillation with Domain Alignment for Video Representation Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29407},
}

@inproceedings{iclr2023_contrastive_32563,
  title = {{Contrastive Audio-Visual Masked Autoencoder}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/10966},
}

@inproceedings{aaai2021_enhanced_523,
  title = {{Enhanced Audio Tagging via Multi- to Single-Modal Teacher-Student Mutual Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/10709-enhanced-audio-tagging-via-multi-to-single-modal-teacher-student-mutual-learning/},
}

@inproceedings{aaai2022_cross_1904,
  title = {{Cross-Modal Mutual Learning for Audio-Visual Speech Recognition and Manipulation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/03036-cross-modal-mutual-learning-for-audio-visual-speech-recognition-and-manipulation/},
}

@inproceedings{cvpr2025_language_26716,
  title = {{Language-Guided Audio-Visual Learning for Long-Term Sports Assessment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34763},
}

@inproceedings{neurips2022_u_66523,
  title = {{u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54552},
}

@inproceedings{iclr2023_jointly_32204,
  title = {{Jointly Learning Visual and Auditory Speech Representations from Raw Data}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11585},
}

@inproceedings{cvpr2023_language_21321,
  title = {{Language-Guided Audio-Visual Source Separation via Trimodal Consistency}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21840},
}

@inproceedings{cvpr2024_crossmae_23065,
  title = {{CrossMAE: Cross-Modality Masked Autoencoders for Region-Aware Audio-Visual Pre-Training}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29679},
}

@inproceedings{aaai2024_multichannel_6716,
  title = {{Multichannel AV-wav2vec2: A Framework for Learning Multichannel Multi-Modal Speech Representation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29951},
}

@inproceedings{cvpr2024_soundingactions_24855,
  title = {{SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29841},
}

@inproceedings{neurips2024_mixtures_72236,
  title = {{Mixtures of Experts for Audio-Visual Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95106},
}

@inproceedings{aaai2025_multimodal_10064,
  title = {{Multimodal Class-aware Semantic Enhancement Network for Audio-Visual Video Parsing}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33134},
}

@inproceedings{cvpr2024_es3_23312,
  title = {{ES3: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31590},
}

@inproceedings{cvpr2024_separating_24804,
  title = {{Separating the "Chirp" from the "Chat": Self-supervised Visual Grounding of Sound and Language}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29312},
}

@inproceedings{cvpr2025_cav_25644,
  title = {{CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33954},
}

@inproceedings{cvpr2024_looking_24031,
  title = {{Looking Similar Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30023},
}

@inproceedings{icml2024_equiav_43620,
  title = {{EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34832},
}

@inproceedings{icml2026_omnivideo_53674,
  title = {{OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality Attention}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=he06cvibXv},
}

@inproceedings{icml2024_from_45150,
  title = {{From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33302},
}

@inproceedings{neurips2026_asymmetric_92970,
  title = {{Asymmetric Hierarchical Anchoring for Robust Audio–Visual Cross-Modal Generalization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/148414},
}

@inproceedings{cvpr2026_investigating_95882,
  title = {{Investigating Self-Supervised Representations for Audio-Visual Deepfake Detection}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Boldisor_Investigating_Self-Supervised_Representations_for_Audio-Visual_Deepfake_Detection_CVPR_2026_paper.html},
}

@inproceedings{cvpr2026_semantic_96969,
  title = {{Semantic Noise Reduction via Teacher-Guided Dual-Path Audio-Visual Representation Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Wang_Semantic_Noise_Reduction_via_Teacher-Guided_Dual-Path_Audio-Visual_Representation_Learning_CVPR_2026_paper.html},
}

@inproceedings{cvpr2026_unlocking_97775,
  title = {{Unlocking Strong Supervision: A Data-Centric Study of General-Purpose Audio Pre-Training Methods}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Zhou_Unlocking_Strong_Supervision_A_Data-Centric_Study_of_General-Purpose_Audio_Pre-Training_CVPR_2026_paper.html},
}

@inproceedings{cvpr2026_pushing_99559,
  title = {{Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Vyas_Pushing_the_Frontier_of_Audiovisual_Perception_with_Large-Scale_Multimodal_Correspondence_CVPR_2026_paper.html},
}