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

@inproceedings{cvpr2017_temporal_12688,
  title = {{Temporal Convolutional Networks for Action Segmentation and Detection}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2018_ava_12817,
  title = {{AVA: A Video Dataset of Spatio-Temporally Localized Atomic Visual Actions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Gu_AVA_A_Video_CVPR_2018_paper.html},
}

@inproceedings{cvpr2019_ms_14494,
  title = {{MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2016_end_11526,
  title = {{End-To-End Learning of Action Detection From Frame Glimpses in Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2020_g_15575,
  title = {{G-TAD: Sub-Graph Localization for Temporal Action Detection}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2017_sst_12599,
  title = {{SST: Single-Stream Temporal Action Proposals}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2016_a_11369,
  title = {{A Multi-Stream Bi-Directional Recurrent Neural Network for Fine-Grained Action Detection}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2016_fast_11549,
  title = {{Fast Temporal Activity Proposals for Efficient Detection of Human Actions in Untrimmed Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2017_re_12566,
  title = {{Re-Sign: Re-Aligned End-To-End Sequence Modelling With Deep Recurrent CNN-HMMs}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2019_temporal_14902,
  title = {{Temporal Cycle-Consistency Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2016_temporal_11910,
  title = {{Temporal Action Detection Using a Statistical Language Model}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2023_tridet_22419,
  title = {{TriDet: Temporal Action Detection With Relative Boundary Modeling}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21956},
}

@inproceedings{cvpr2018_temporal_13637,
  title = {{Temporal Deformable Residual Networks for Action Segmentation in Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Lei_Temporal_Deformable_Residual_CVPR_2018_paper.html},
}

@inproceedings{aaai2020_fast_103708,
  title = {{Fast Learning of Temporal Action Proposal via Dense Boundary Generator}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6815},
}

@inproceedings{cvpr2021_temporal_17985,
  title = {{Temporal Context Aggregation Network for Temporal Action Proposal Refinement}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2019_step_14765,
  title = {{STEP: Spatio-Temporal Progressive Learning for Video Action Detection}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{aaai2020_progressive_103722,
  title = {{Progressive Boundary Refinement Network for Temporal Action Detection}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6829},
}

@inproceedings{cvpr2020_counting_15299,
  title = {{Counting Out Time: Class Agnostic Video Repetition Counting in the Wild}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{aaai2018_end_104028,
  title = {{End-to-End United Video Dehazing and Detection}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/12287},
}

@inproceedings{cvpr2022_ms_19298,
  title = {{MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2024_end_23364,
  title = {{End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30581},
}

@inproceedings{cvpr2024_te_24938,
  title = {{TE-TAD: Towards Full End-to-End Temporal Action Detection via Time-Aligned Coordinate Expression}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31123},
}

@inproceedings{cvpr2024_adapting_22721,
  title = {{Adapting Short-Term Transformers for Action Detection in Untrimmed Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30639},
}

@inproceedings{cvpr2024_benchmarking_22829,
  title = {{Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30850},
}

@inproceedings{cvpr2025_context_25771,
  title = {{Context-Enhanced Memory-Refined Transformer for Online Action Detection}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33044},
}

@inproceedings{neurips2024_onlinetas_72946,
  title = {{OnlineTAS: An Online Baseline for Temporal Action Segmentation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94466},
}

@inproceedings{aaai2025_prediction_10348,
  title = {{Prediction-Feedback DETR for Temporal Action Detection}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32448},
}

@inproceedings{aaai2025_action_8009,
  title = {{Action-Agnostic Point-Level Supervision for Temporal Action Detection}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33037},
}

@inproceedings{neurips2024_actfusion_71857,
  title = {{ActFusion: a Unified Diffusion Model for Action Segmentation and Anticipation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95443},
}

@inproceedings{neurips2024_does_72011,
  title = {{Does Video-Text Pretraining Help Open-Vocabulary Online Action Detection?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95303},
}

@inproceedings{aaai2026_finetec_104311,
  title = {{FineTec: Fine-Grained Action Recognition Under Temporal Corruption via Skeleton Decomposition and Sequence Completion}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/37838},
}

@inproceedings{cvpr2026_ms_96224,
  title = {{MS-Temba: Multi-Scale Temporal Mamba for Understanding Long Untrimmed Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Sinha_MS-Temba_Multi-Scale_Temporal_Mamba_for_Understanding_Long_Untrimmed_Videos_CVPR_2026_paper.html},
}

@inproceedings{aaai2026_scene_100545,
  title = {{Scene-Aware Spatiotemporal Generalization: Towards Robust Temporal Action Detection Across Domains}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/37392},
}

@inproceedings{neurips2025_mamba_76887,
  title = {{Mamba Only Glances Once (MOGO): A Lightweight Framework for Efficient Video Action Detection}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=O880k3JoC8},
}

@inproceedings{iclr2026_invert4tvg_86483,
  title = {{Invert4TVG: A Temporal Video Grounding Framework with Inversion Tasks Preserving Action Understanding Ability}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=QQCrZXWG9s},
}

@inproceedings{cvpr2026_frame2freq_97045,
  title = {{Frame2Freq: Spectral Adapters for Fine-Grained Video Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Ponbagavathi_Frame2Freq_Spectral_Adapters_for_Fine-Grained_Video_Understanding_CVPR_2026_paper.html},
}

@inproceedings{cvpr2026_lady_98285,
  title = {{LaDy: Lagrangian-Dynamic Informed Network for Skeleton-based Action Segmentation via Spatial-Temporal Modulation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Ji_LaDy_Lagrangian-Dynamic_Informed_Network_for_Skeleton-based_Action_Segmentation_via_Spatial-Temporal_CVPR_2026_paper.html},
}

@inproceedings{aaai2026_light_99854,
  title = {{Light but Sharp: SlimSTAD for Real-Time Action Detection from Sensor Data}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/36975},
}

@inproceedings{aaai2026_defb_100564,
  title = {{DeFB: Decomposed Feature Learning for Real-Time Multi-Person Eyeblink Detection in Untrimmed In-the-Wild Videos}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/37411},
}

@inproceedings{aaai2026_backtrace_105267,
  title = {{Backtrace Mamba: Reviving Critical Temporal Contexts via Hierarchical Memory Compression for Online Action Detection}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/38139},
}