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

@inproceedings{cvpr2017_quo_12560,
  title = {{Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2020_tea_16319,
  title = {{TEA: Temporal Excitation and Aggregation for Action Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2016_a_11362,
  title = {{A Hierarchical Deep Temporal Model for Group Activity Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2018_optical_13445,
  title = {{Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Sun_Optical_Flow_Guided_CVPR_2018_paper.html},
}

@inproceedings{cvpr2018_learning_13312,
  title = {{Learning and Using the Arrow of Time}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Wei_Learning_and_Using_CVPR_2018_paper.html},
}

@inproceedings{cvpr2020_finegym_15554,
  title = {{FineGym: A Hierarchical Video Dataset for Fine-Grained Action Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2020_action_15106,
  title = {{Action Genome: Actions As Compositions of Spatio-Temporal Scene Graphs}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2019_large_14380,
  title = {{Large-Scale Weakly-Supervised Pre-Training for Video Action Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2021_uav_18057,
  title = {{UAV-Human: A Large Benchmark for Human Behavior Understanding With Unmanned Aerial Vehicles}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2020_listen_15841,
  title = {{Listen to Look: Action Recognition by Previewing Audio}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2016_a_11366,
  title = {{A Key Volume Mining Deep Framework for Action Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2019_timeception_14918,
  title = {{Timeception for Complex Action Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2016_actions_11385,
  title = {{Actions ~ Transformations}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{aaai2019_i_103447,
  title = {{I Know the Relationships: Zero-Shot Action Recognition via Two-Stream Graph Convolutional Networks and Knowledge Graphs}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4843},
}

@inproceedings{cvpr2019_what_15028,
  title = {{What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2016_first_11556,
  title = {{First Person Action Recognition Using Deep Learned Descriptors}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{aaai2016_recognizing_104983,
  title = {{Recognizing Complex Activities by a Probabilistic Interval-Based Model}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10155},
}

@inproceedings{cvpr2018_glimpse_13165,
  title = {{Glimpse Clouds: Human Activity Recognition From Unstructured Feature Points}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Baradel_Glimpse_Clouds_Human_CVPR_2018_paper.html},
}

@inproceedings{cvpr2021_babel_16624,
  title = {{BABEL: Bodies, Action and Behavior With English Labels}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2017_adascan_12043,
  title = {{AdaScan: Adaptive Scan Pooling in Deep Convolutional Neural Networks for Human Action Recognition in Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2024_exact_23401,
  title = {{ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and More}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30133},
}

@inproceedings{cvpr2024_tim_24944,
  title = {{TIM: A Time Interval Machine for Audio-Visual Action Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29601},
}

@inproceedings{cvpr2024_just_23857,
  title = {{Just Add ?! Pose Induced Video Transformers for Understanding Activities of Daily Living}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30993},
}

@inproceedings{cvpr2024_align_22744,
  title = {{Align Before Adapt: Leveraging Entity-to-Region Alignments for Generalizable Video Action Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31275},
}

@inproceedings{aaai2024_vistec_7763,
  title = {{ViSTec: Video Modeling for Sports Technique Recognition and Tactical Analysis}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28692},
}

@inproceedings{cvpr2024_selective_24776,
  title = {{Selective Interpretable and Motion Consistent Privacy Attribute Obfuscation for Action Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29272},
}

@inproceedings{aaai2025_frame_9228,
  title = {{Frame Order Matters: A Temporal Sequence-Aware Model for Few-Shot Action Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34004},
}

@inproceedings{aaai2024_generative_6131,
  title = {{Generative Model-Based Feature Knowledge Distillation for Action Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29473},
}

@inproceedings{aaai2025_manta_9905,
  title = {{Manta: Enhancing Mamba for Few-Shot Action Recognition of Long Sub-Sequence}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32391},
}

@inproceedings{aaai2025_va_11207,
  title = {{VA-AR: Learning Velocity-Aware Action Representations with Mixture of Window Attention}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32894},
}

@inproceedings{cvpr2025_temporal_27836,
  title = {{Temporal Alignment-Free Video Matching for Few-shot Action Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34507},
}

@inproceedings{neurips2024_actionatlas_70618,
  title = {{ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97838},
}

@inproceedings{aaai2025_surgical_10878,
  title = {{Surgical Workflow Recognition and Blocking Effectiveness Detection in Laparoscopic Liver Resection with Pringle Maneuver}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32332},
}

@inproceedings{cvpr2024_cpr_22933,
  title = {{CPR-Coach: Recognizing Composite Error Actions based on Single-class Training}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30761},
}

@inproceedings{cvpr2024_modality_24172,
  title = {{Modality-Collaborative Test-Time Adaptation for Action Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29225},
}

@inproceedings{cvpr2024_video_25221,
  title = {{Video Recognition in Portrait Mode}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30766},
}

@inproceedings{cvpr2024_language_23918,
  title = {{Language Model Guided Interpretable Video Action Reasoning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30359},
}

@inproceedings{cvpr2025_action_25423,
  title = {{Action Detail Matters: Refining Video Recognition with Local Action Queries}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34740},
}

@inproceedings{iclr2024_froster_35693,
  title = {{FROSTER: Frozen CLIP is A Strong Teacher for Open-Vocabulary Action Recognition}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17380},
}

@inproceedings{aaai2025_building_8321,
  title = {{Building a Multi-modal Spatiotemporal Expert for Zero-shot Action Recognition with CLIP}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33050},
}