% Key papers for Action anticipation and latent actions (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{aaai2018_towards_104083,
  title = {{Towards Automatic Learning of Procedures From Web Instructional Videos}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/12342},
}

@inproceedings{cvpr2019_coin_13920,
  title = {{COIN: A Large-Scale Dataset for Comprehensive Instructional Video Analysis}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2022_assembly101_18301,
  title = {{Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2018_when_13734,
  title = {{When Will You Do What? - Anticipating Temporal Occurrences of Activities}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Abu_Farha_When_Will_You_CVPR_2018_paper.html},
}

@inproceedings{cvpr2018_from_13131,
  title = {{From Lifestyle Vlogs to Everyday Interactions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Fouhey_From_Lifestyle_Vlogs_CVPR_2018_paper.html},
}

@inproceedings{cvpr2019_time_14917,
  title = {{Time-Conditioned Action Anticipation in One Shot}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2021_drivegan_16904,
  title = {{DriveGAN: Towards a Controllable High-Quality Neural Simulation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2022_future_18888,
  title = {{Future Transformer for Long-Term Action Anticipation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2021_learning_17334,
  title = {{Learning the Predictability of the Future}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2022_jrdb_19115,
  title = {{JRDB-Act: A Large-Scale Dataset for Spatio-Temporal Action, Social Group and Activity Detection}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2023_logo_21313,
  title = {{LOGO: A Long-Form Video Dataset for Group Action Quality Assessment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22145},
}

@inproceedings{cvpr2022_likert_19258,
  title = {{Likert Scoring With Grade Decoupling for Long-Term Action Assessment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2024_egoexolearn_23347,
  title = {{EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29342},
}

@inproceedings{neurips2024_vista_72345,
  title = {{Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95003},
}

@inproceedings{aaai2023_multiact_4211,
  title = {{MultiAct: Long-Term 3D Human Motion Generation from Multiple Action Labels}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25206},
}

@inproceedings{cvpr2023_procedure_21922,
  title = {{Procedure-Aware Pretraining for Instructional Video Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21571},
}

@inproceedings{cvpr2024_can_22949,
  title = {{Can't Make an Omelette Without Breaking Some Eggs: Plausible Action Anticipation Using Large Video-Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29758},
}

@inproceedings{cvpr2022_p3iv_19534,
  title = {{P3IV: Probabilistic Procedure Planning From Instructional Videos With Weak Supervision}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{iclr2017_learning_28228,
  title = {{Learning Recurrent Representations for Hierarchical Behavior Modeling}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=BkLhzHtlg},
}

@inproceedings{neurips2021_contrastive_63379,
  title = {{Contrastive Learning of Global and Local Video Representations}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27843},
}

@inproceedings{cvpr2025_hd_26465,
  title = {{HD-EPIC: A Highly-Detailed Egocentric Video Dataset}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33586},
}

@inproceedings{cvpr2024_action_22706,
  title = {{Action Scene Graphs for Long-Form Understanding of Egocentric Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29292},
}

@inproceedings{cvpr2024_prego_24418,
  title = {{PREGO: Online Mistake Detection in PRocedural EGOcentric Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31241},
}

@inproceedings{neurips2024_gaia_71022,
  title = {{GAIA: Rethinking Action Quality Assessment for AI-Generated Videos}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97817},
}

@inproceedings{icml2024_genie_44806,
  title = {{Genie: Generative Interactive Environments}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33646},
}

@inproceedings{cvpr2024_from_23521,
  title = {{From Isolated Islands to Pangea: Unifying Semantic Space for Human Action Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29771},
}

@inproceedings{aaai2024_towards_7626,
  title = {{Towards Understanding Future: Consistency Guided Probabilistic Modeling for Action Anticipation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28442},
}

@inproceedings{iclr2024_antgpt_33865,
  title = {{AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19210},
}

@inproceedings{neurips2024_differentiable_70262,
  title = {{Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96827},
}

@inproceedings{neurips2024_drivingdojo_74148,
  title = {{DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97477},
}

@inproceedings{cvpr2025_graphmimic_26453,
  title = {{GraphMimic: Graph-to-Graphs Generative Modeling from Videos for Policy Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34942},
}

@inproceedings{neurips2024_captaincook4d_72675,
  title = {{CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97640},
}

@inproceedings{aaai2024_count_5515,
  title = {{Count What You Want: Exemplar Identification and Few-Shot Counting of Human Actions in the Wild}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28869},
}

@inproceedings{cvpr2025_manta_26836,
  title = {{MANTA: Diffusion Mamba for Efficient and Effective Stochastic Long-Term Dense Action Anticipation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32698},
}

@inproceedings{aaai2026_human2robot_104897,
  title = {{Human2Robot: Learning Robot Actions from Paired Human-Robot Videos}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/38086},
}

@inproceedings{icml2026_dreamdojo_50808,
  title = {{DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=FuvU7PTyED},
}

@inproceedings{aaai2024_intentional_6336,
  title = {{Intentional Evolutionary Learning for Untrimmed Videos with Long Tail Distribution}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28605},
}