% Key papers for Audio-visual source localization (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2020_music_15929,
  title = {{Music Gesture for Visual Sound Separation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{aaai2020_cross_99760,
  title = {{Cross-Modal Attention Network for Temporal Inconsistent Audio-Visual Event Localization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5361},
}

@inproceedings{cvpr2023_vision_22534,
  title = {{Vision Transformers Are Parameter-Efficient Audio-Visual Learners}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22815},
}

@inproceedings{cvpr2021_semantic_17866,
  title = {{Semantic Audio-Visual Navigation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2024_avff_22695,
  title = {{AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29935},
}

@inproceedings{cvpr2019_a_13789,
  title = {{A Simple Baseline for Audio-Visual Scene-Aware Dialog}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{aaai2024_avsegformer_5106,
  title = {{AVSegFormer: Audio-Visual Segmentation with Transformer}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29104},
}

@inproceedings{cvpr2022_cross_18548,
  title = {{Cross-Modal Background Suppression for Audio-Visual Event Localization}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2021_visually_18134,
  title = {{Visually Informed Binaural Audio Generation without Binaural Audios}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2023_audio_20412,
  title = {{Audio-Visual Grouping Network for Sound Localization From Mixtures}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/23192},
}

@inproceedings{cvpr2022_visual_20188,
  title = {{Visual Acoustic Matching}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2021_beyond_16641,
  title = {{Beyond Image to Depth: Improving Depth Prediction Using Echoes}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2023_sound_22233,
  title = {{Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21827},
}

@inproceedings{cvpr2023_watch_22556,
  title = {{Watch or Listen: Robust Audio-Visual Speech Recognition With Visual Corruption Modeling and Reliability Scoring}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22213},
}

@inproceedings{aaai2024_prompting_7014,
  title = {{Prompting Segmentation with Sound Is Generalizable Audio-Visual Source Localizer}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28378},
}

@inproceedings{aaai2022_visual_2941,
  title = {{Visual Sound Localization in the Wild by Cross-Modal Interference Erasing}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/01801-visual-sound-localization-in-the-wild-by-cross-modal-interference-erasing/},
}

@inproceedings{neurips2020_see_60791,
  title = {{See, Hear, Explore: Curiosity via Audio-Visual Association}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18030},
}

@inproceedings{aaai2023_leveraging_4062,
  title = {{Leveraging Modality-Specific Representations for Audio-Visual Speech Recognition via Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26484},
}

@inproceedings{cvpr2023_iquery_22604,
  title = {{iQuery: Instruments As Queries for Audio-Visual Sound Separation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/23015},
}

@inproceedings{cvpr2024_av_22693,
  title = {{AV-RIR: Audio-Visual Room Impulse Response Estimation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30540},
}

@inproceedings{cvpr2024_real_24586,
  title = {{Real Acoustic Fields: An Audio-Visual Room Acoustics Dataset and Benchmark}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30612},
}

@inproceedings{cvpr2024_unraveling_25157,
  title = {{Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30665},
}

@inproceedings{cvpr2024_t_24932,
  title = {{T-VSL: Text-Guided Visual Sound Source Localization in Mixtures}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29688},
}

@inproceedings{cvpr2025_towards_27916,
  title = {{Towards Open-Vocabulary Audio-Visual Event Localization}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32626},
}

@inproceedings{cvpr2025_echotraffic_26077,
  title = {{EchoTraffic: Enhancing Traffic Anomaly Understanding with Audio-Visual Insights}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/35198},
}

@inproceedings{cvpr2024_av2av_22694,
  title = {{AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30182},
}

@inproceedings{cvpr2025_object_27109,
  title = {{Object-aware Sound Source Localization via Audio-Visual Scene Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34050},
}

@inproceedings{aaai2025_few_9189,
  title = {{Few-Shot Incremental Learning via Foreground Aggregation and Knowledge Transfer for Audio-Visual Semantic Segmentation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32950},
}

@inproceedings{cvpr2025_dynamic_26040,
  title = {{Dynamic Derivation and Elimination: Audio Visual Segmentation with Enhanced Audio Semantics}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34269},
}

@inproceedings{cvpr2025_robust_27480,
  title = {{Robust Audio-Visual Segmentation via Audio-Guided Visual Convergent Alignment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34765},
}

@inproceedings{icml2025_agav_48919,
  title = {{AGAV-Rater: Adapting Large Multimodal Model for AI-Generated Audio-Visual Quality Assessment}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43704},
}

@inproceedings{cvpr2025_revisiting_27459,
  title = {{Revisiting Audio-Visual Segmentation with Vision-Centric Transformer}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33766},
}

@inproceedings{cvpr2025_sam2_27497,
  title = {{SAM2-LOVE: Segment Anything Model 2 in Language-aided Audio-Visual Scenes}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32445},
}

@inproceedings{aaai2024_visual_7778,
  title = {{Visual Hallucination Elevates Speech Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29926},
}

@inproceedings{aaai2025_query_10423,
  title = {{Query-centric Audio-Visual Cognition Network for Moment Retrieval, Segmentation and Step-Captioning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32803},
}

@inproceedings{cvpr2025_audio_25528,
  title = {{Audio-Visual Semantic Graph Network for Audio-Visual Event Localization}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32995},
}