% Key papers for Layered video decomposition and dynamics (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2016_face2face_11541,
  title = {{Face2Face: Real-Time Face Capture and Reenactment of RGB Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2018_gaze_13143,
  title = {{Gaze Prediction in Dynamic 360° Immersive Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Xu_Gaze_Prediction_in_CVPR_2018_paper.html},
}

@inproceedings{cvpr2017_vidloc_12734,
  title = {{VidLoc: A Deep Spatio-Temporal Model for 6-DoF Video-Clip Relocalization}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2018_revisiting_13535,
  title = {{Revisiting Video Saliency: A Large-Scale Benchmark and a New Model}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Wang_Revisiting_Video_Saliency_CVPR_2018_paper.html},
}

@inproceedings{cvpr2018_visual_13713,
  title = {{Visual to Sound: Generating Natural Sound for Videos in the Wild}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Zhou_Visual_to_Sound_CVPR_2018_paper.html},
}

@inproceedings{cvpr2017_deep_12143,
  title = {{Deep 360 Pilot: Learning a Deep Agent for Piloting Through 360deg Sports Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2017_understanding_12713,
  title = {{Understanding Traffic Density From Large-Scale Web Camera Data}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2016_from_11562,
  title = {{From Keyframes to Key Objects: Video Summarization by Representative Object Proposal Selection}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2018_clusternet_12904,
  title = {{ClusterNet: Detecting Small Objects in Large Scenes by Exploiting Spatio-Temporal Information}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/LaLonde_ClusterNet_Detecting_Small_CVPR_2018_paper.html},
}

@inproceedings{cvpr2023_hyperreel_21195,
  title = {{HyperReel: High-Fidelity 6-DoF Video With Ray-Conditioned Sampling}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22591},
}

@inproceedings{neurips2018_video_57767,
  title = {{Video-to-Video Synthesis}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11133},
}

@inproceedings{neurips2019_unsupervised_59160,
  title = {{Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13252},
}

@inproceedings{cvpr2017_making_12447,
  title = {{Making 360deg Video Watchable in 2D: Learning Videography for Click Free Viewing}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2021_vspw_18109,
  title = {{VSPW: A Large-scale Dataset for Video Scene Parsing in the Wild}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2020_ego_15466,
  title = {{Ego-Topo: Environment Affordances From Egocentric Video}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2020_panda_16006,
  title = {{PANDA: A Gigapixel-Level Human-Centric Video Dataset}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2016_walk_11969,
  title = {{Walk and Learn: Facial Attribute Representation Learning From Egocentric Video and Contextual Data}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2016_what_11977,
  title = {{What Players Do With the Ball: A Physically Constrained Interaction Modeling}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2021_radar_17694,
  title = {{Radar-Camera Pixel Depth Association for Depth Completion}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2021_deepvideomvs_16842,
  title = {{DeepVideoMVS: Multi-View Stereo on Video With Recurrent Spatio-Temporal Fusion}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2025_video_28080,
  title = {{Video Depth Anything: Consistent Depth Estimation for Super-Long Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33862},
}

@inproceedings{cvpr2024_codef_22979,
  title = {{CoDeF: Content Deformation Fields for Temporally Consistent Video Processing}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31435},
}

@inproceedings{cvpr2025_align3r_25468,
  title = {{Align3R: Aligned Monocular Depth Estimation for Dynamic Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32671},
}

@inproceedings{aaai2025_depth_8695,
  title = {{Depth-Centric Dehazing and Depth-Estimation from Real-World Hazy Driving Video}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32291},
}

@inproceedings{cvpr2024_the_25003,
  title = {{The Audio-Visual Conversational Graph: From an Egocentric-Exocentric Perspective}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29491},
}

@inproceedings{cvpr2025_video_28081,
  title = {{Video Depth without Video Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32677},
}

@inproceedings{cvpr2025_fifa_26211,
  title = {{FIFA: Fine-grained Inter-frame Attention for Driver's Video Gaze Estimation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32504},
}

@inproceedings{aaai2025_spectral_10813,
  title = {{Spectral Motion Alignment for Video Motion Transfer Using Diffusion Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32685},
}

@inproceedings{neurips2025_4dgt_79529,
  title = {{4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=qMRFNxioPC},
}

@inproceedings{cvpr2025_diffvsgg_25938,
  title = {{DiffVsgg: Diffusion-Driven Online Video Scene Graph Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33571},
}

@inproceedings{cvpr2025_4d_25345,
  title = {{4D-Fly: Fast 4D Reconstruction from a Single Monocular Video}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34770},
}

@inproceedings{cvpr2025_imvid_26585,
  title = {{ImViD: Immersive Volumetric Videos for Enhanced VR Engagement}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34169},
}

@inproceedings{cvpr2025_unbiased_27982,
  title = {{Unbiased Video Scene Graph Generation via Visual and Semantic Dual Debiasing}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32993},
}

@inproceedings{cvpr2025_mammalps_26918,
  title = {{MammAlps: A Multi-view Video Behavior Monitoring Dataset of Wild Mammals in the Swiss Alps}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34138},
}

@inproceedings{cvpr2025_the_27861,
  title = {{The PanAf-FGBG Dataset: Understanding the Impact of Backgrounds in Wildlife Behaviour Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32459},
}

@inproceedings{cvpr2025_uni4d_27994,
  title = {{Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34289},
}

@inproceedings{cvpr2025_generative_26423,
  title = {{Generative Omnimatte: Learning to Decompose Video into Layers}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34367},
}

@inproceedings{cvpr2025_pursuing_27329,
  title = {{Pursuing Temporal-Consistent Video Virtual Try-On via Dynamic Pose Interaction}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32778},
}

@inproceedings{cvpr2025_buffer_25626,
  title = {{Buffer Anytime: Zero-Shot Video Depth and Normal from Image Priors}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34412},
}

@inproceedings{cvpr2025_gazing_26396,
  title = {{Gazing Into Missteps: Leveraging Eye-Gaze for Unsupervised Mistake Detection in Egocentric Videos of Skilled Human Activities}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32832},
}