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

@inproceedings{cvpr2020_end_15476,
  title = {{End-to-End Learning of Visual Representations From Uncurated Instructional Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2017_untrimmednets_12728,
  title = {{UntrimmedNets for Weakly Supervised Action Recognition and Detection}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2017_social_12646,
  title = {{Social Scene Understanding: End-To-End Multi-Person Action Localization and Collective Activity Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2017_weakly_12748,
  title = {{Weakly Supervised Action Learning With RNN Based Fine-To-Coarse Modeling}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2019_cross_13987,
  title = {{Cross-Task Weakly Supervised Learning From Instructional Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2018_neuralnetwork_13425,
  title = {{NeuralNetwork-Viterbi: A Framework for Weakly Supervised Video Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Richard_NeuralNetwork-Viterbi_A_Framework_CVPR_2018_paper.html},
}

@inproceedings{cvpr2022_finediving_18862,
  title = {{FineDiving: A Fine-Grained Dataset for Procedure-Aware Action Quality Assessment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2019_unsupervised_14979,
  title = {{Unsupervised Learning of Action Classes With Continuous Temporal Embedding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2018_weakly_13726,
  title = {{Weakly-Supervised Action Segmentation With Iterative Soft Boundary Assignment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Ding_Weakly-Supervised_Action_Segmentation_CVPR_2018_paper.html},
}

@inproceedings{cvpr2018_unsupervised_13686,
  title = {{Unsupervised Learning and Segmentation of Complex Activities From Video}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Sener_Unsupervised_Learning_and_CVPR_2018_paper.html},
}

@inproceedings{cvpr2018_action_12819,
  title = {{Action Sets: Weakly Supervised Action Segmentation Without Ordering Constraints}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Richard_Action_Sets_Weakly_CVPR_2018_paper.html},
}

@inproceedings{cvpr2019_relational_14726,
  title = {{Relational Action Forecasting}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2021_temporally_17989,
  title = {{Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2020_oops_15990,
  title = {{Oops! Predicting Unintentional Action in Video}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2021_temporal_17984,
  title = {{Temporal Action Segmentation From Timestamp Supervision}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2022_bridge_18392,
  title = {{Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2019_a_13785,
  title = {{A Perceptual Prediction Framework for Self Supervised Event Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{aaai2019_learning_103559,
  title = {{Learning Transferable Self-Attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4958},
}

@inproceedings{cvpr2020_sct_16154,
  title = {{SCT: Set Constrained Temporal Transformer for Set Supervised Action Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2022_unsupervised_20138,
  title = {{Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2024_fact_23424,
  title = {{FACT: Frame-Action Cross-Attention Temporal Modeling for Efficient Action Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29976},
}

@inproceedings{cvpr2024_fineparser_23474,
  title = {{FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30233},
}

@inproceedings{cvpr2024_temporally_24972,
  title = {{Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31480},
}

@inproceedings{cvpr2024_progress_24523,
  title = {{Progress-Aware Online Action Segmentation for Egocentric Procedural Task Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30120},
}

@inproceedings{cvpr2024_learning_23984,
  title = {{Learning to Predict Activity Progress by Self-Supervised Video Alignment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31088},
}

@inproceedings{aaai2024_unsupervised_7713,
  title = {{Unsupervised Action Segmentation via Fast Learning of Semantically Consistent Actoms}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28445},
}

@inproceedings{cvpr2024_finesports_23475,
  title = {{FineSports: A Multi-person Hierarchical Sports Video Dataset for Fine-grained Action Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30906},
}

@inproceedings{aaai2025_hierarchical_9440,
  title = {{Hierarchical Vector Quantization for Unsupervised Action Segmentation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32751},
}

@inproceedings{cvpr2024_genhowto_23585,
  title = {{GenHowTo: Learning to Generate Actions and State Transformations from Instructional Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29366},
}

@inproceedings{aaai2024_semi_7312,
  title = {{Semi-supervised Active Learning for Video Action Detection}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28292},
}

@inproceedings{cvpr2024_efficient_23342,
  title = {{Efficient and Effective Weakly-Supervised Action Segmentation via Action-Transition-Aware Boundary Alignment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29648},
}

@inproceedings{cvpr2024_coherent_22990,
  title = {{Coherent Temporal Synthesis for Incremental Action Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31599},
}

@inproceedings{aaai2025_stable_10832,
  title = {{Stable Mean Teacher for Semi-supervised Video Action Detection}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32465},
}

@inproceedings{cvpr2025_understanding_27991,
  title = {{Understanding Multi-Task Activities from Single-Task Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33562},
}

@inproceedings{aaai2025_stitch_10842,
  title = {{Stitch, Contrast, and Segment: Learning a Human Action Segmentation Model Using Trimmed Skeleton Videos}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32792},
}

@inproceedings{cvpr2025_condensing_25761,
  title = {{Condensing Action Segmentation Datasets via Generative Network Inversion}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33322},
}

@inproceedings{neurips2025_hopadiff_80216,
  title = {{HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person Scenarios}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=xOqCKB8XIl},
}

@inproceedings{aaai2024_open_6857,
  title = {{Open-Vocabulary Video Relation Extraction}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28328},
}

@inproceedings{iclr2024_learning_34263,
  title = {{Learning to Act from Actionless Videos through Dense Correspondences}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18812},
}

@inproceedings{aaai2026_object_107071,
  title = {{Object-Centric Latent Action Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/39423},
}