% Key papers for Temporal video pose estimation (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2018_posetrack_13484,
  title = {{PoseTrack: A Benchmark for Human Pose Estimation and Tracking}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Andriluka_PoseTrack_A_Benchmark_CVPR_2018_paper.html},
}

@inproceedings{cvpr2022_humannerf_19020,
  title = {{HumanNeRF: Free-Viewpoint Rendering of Moving People From Monocular Video}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2022_mixste_19346,
  title = {{MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2019_learning_14400,
  title = {{Learning Individual Styles of Conversational Gesture}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2018_detect_13013,
  title = {{Detect-and-Track: Efficient Pose Estimation in Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Girdhar_Detect-and-Track_Efficient_Pose_CVPR_2018_paper.html},
}

@inproceedings{cvpr2021_beyond_16644,
  title = {{Beyond Static Features for Temporally Consistent 3D Human Pose and Shape From a Video}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2017_arttrack_12066,
  title = {{ArtTrack: Articulated Multi-Person Tracking in the Wild}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2021_motion_17434,
  title = {{Motion Representations for Articulated Animation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2018_future_13138,
  title = {{Future Person Localization in First-Person Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Yagi_Future_Person_Localization_CVPR_2018_paper.html},
}

@inproceedings{cvpr2018_lstm_13253,
  title = {{LSTM Pose Machines}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Luo_LSTM_Pose_Machines_CVPR_2018_paper.html},
}

@inproceedings{cvpr2021_deep_16816,
  title = {{Deep Dual Consecutive Network for Human Pose Estimation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2019_efficient_14135,
  title = {{Efficient Online Multi-Person 2D Pose Tracking With Recurrent Spatio-Temporal Affinity Fields}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2020_combining_15263,
  title = {{Combining Detection and Tracking for Human Pose Estimation in Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2017_dynamic_12227,
  title = {{Dynamic Facial Analysis: From Bayesian Filtering to Recurrent Neural Network}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2017_thin_12699,
  title = {{Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2020_4d_15059,
  title = {{4D Association Graph for Realtime Multi-Person Motion Capture Using Multiple Video Cameras}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2016_personalizing_11764,
  title = {{Personalizing Human Video Pose Estimation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2018_inferring_13228,
  title = {{Inferring Shared Attention in Social Scene Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Fan_Inferring_Shared_Attention_CVPR_2018_paper.html},
}

@inproceedings{cvpr2020_kfnet_15725,
  title = {{KFNet: Learning Temporal Camera Relocalization Using Kalman Filtering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{aaai2019_towards_103519,
  title = {{Towards Highly Accurate and Stable Face Alignment for High-Resolution Videos}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4917},
}

@inproceedings{cvpr2024_hourglass_23714,
  title = {{Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30128},
}

@inproceedings{cvpr2024_fsrt_23437,
  title = {{FSRT: Facial Scene Representation Transformer for Face Reenactment from Factorized Appearance Head-pose and Facial Expression Features}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31517},
}

@inproceedings{cvpr2024_video_25223,
  title = {{Video-Based Human Pose Regression via Decoupled Space-Time Aggregation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30777},
}

@inproceedings{aaai2024_advancing_5142,
  title = {{Advancing Video Synchronization with Fractional Frame Analysis: Introducing a Novel Dataset and Model}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28174},
}

@inproceedings{aaai2025_spatiotemporal_10806,
  title = {{SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videos}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32429},
}

@inproceedings{cvpr2025_anycam_25495,
  title = {{AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33037},
}

@inproceedings{cvpr2025_dynamic_26038,
  title = {{Dynamic Camera Poses and Where to Find Them}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32894},
}

@inproceedings{aaai2025_optimizing_10221,
  title = {{Optimizing Human Pose Estimation Through Focused Human and Joint Regions}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32430},
}

@inproceedings{cvpr2025_can_25678,
  title = {{Can Generative Video Models Help Pose Estimation?}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34581},
}

@inproceedings{cvpr2025_motions_27009,
  title = {{Motions as Queries: One-Stage Multi-Person Holistic Human Motion Capture}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32510},
}

@inproceedings{aaai2026_end_105338,
  title = {{End-to-End Multi-Person Pose Estimation with Pose-Aware Video Transformer}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/38210},
}

@inproceedings{aaai2025_causal_8399,
  title = {{Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32202},
}

@inproceedings{neurips2024_estimating_71754,
  title = {{Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Data}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95535},
}

@inproceedings{neurips2025_whole_77748,
  title = {{Whole-Body Conditioned Egocentric Video Prediction}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=XDTTwmjhAg},
}

@inproceedings{icml2025_imitation_47688,
  title = {{Imitation Learning from a Single Temporally Misaligned Video}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44909},
}

@inproceedings{neurips2026_articulation_93895,
  title = {{Articulation in Prime: Primitive-Based Articulated Object Understanding from a Single Casual Video}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/154376},
}

@inproceedings{cvpr2026_beyond_96240,
  title = {{Beyond Static Frames: Temporal Aggregate-and-Restore Vision Transformer for Human Pose Estimation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Fang_Beyond_Static_Frames_Temporal_Aggregate-and-Restore_Vision_Transformer_for_Human_Pose_CVPR_2026_paper.html},
}

@inproceedings{aaai2026_dual_104860,
  title = {{Dual Coding Theory in Action: Language-Assisted Human Pose Estimation in Videos}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/38049},
}

@inproceedings{aaai2026_attentive_104861,
  title = {{Attentive Keypoint Identification: Progressive Spatiotemporal Refinement for Video-based Human Pose Estimation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/38050},
}

@inproceedings{iclr2026_inclusivevidpose_86699,
  title = {{InclusiveVidPose: Bridging the Pose Estimation Gap for Individuals with Limb Deficiencies in Video-Based Motion}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=SyQqXAdWUq},
}