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

@inproceedings{cvpr2024_ego_23346,
  title = {{Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29859},
}

@inproceedings{cvpr2017_jointly_12374,
  title = {{Jointly Learning Energy Expenditures and Activities Using Egocentric Multimodal Signals}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2024_abductive_22698,
  title = {{Abductive Ego-View Accident Video Understanding for Safe Driving Perception}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29959},
}

@inproceedings{cvpr2022_episodic_18770,
  title = {{Episodic Memory Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2024_grounded_23644,
  title = {{Grounded Question-Answering in Long Egocentric Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29213},
}

@inproceedings{cvpr2025_egolife_26110,
  title = {{EgoLife: Towards Egocentric Life Assistant}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33009},
}

@inproceedings{cvpr2024_summarize_24912,
  title = {{Summarize the Past to Predict the Future: Natural Language Descriptions of Context Boost Multimodal Object Interaction Anticipation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30633},
}

@inproceedings{cvpr2025_egotextvqa_26112,
  title = {{EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/35056},
}

@inproceedings{cvpr2023_egocentric_20907,
  title = {{Egocentric Video Task Translation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21986},
}

@inproceedings{neurips2022_egotaskqa_66243,
  title = {{EgoTaskQA: Understanding Human Tasks in Egocentric Videos}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55772},
}

@inproceedings{cvpr2025_omnia_27130,
  title = {{Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33032},
}

@inproceedings{cvpr2023_relational_22027,
  title = {{Relational Space-Time Query in Long-Form Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21249},
}

@inproceedings{neurips2023_learning_68030,
  title = {{Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/71749},
}

@inproceedings{neurips2023_single_66600,
  title = {{Single-Stage Visual Query Localization in Egocentric Videos}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/73018},
}

@inproceedings{neurips2023_egodistill_67969,
  title = {{EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/71805},
}

@inproceedings{cvpr2025_egolm_26109,
  title = {{EgoLM: Multi-Modal Language Model of Egocentric Motions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33242},
}

@inproceedings{neurips2023_egoenv_69646,
  title = {{EgoEnv: Human-centric environment representations from egocentric video}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70290},
}

@inproceedings{neurips2025_egoexobench_77445,
  title = {{EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=Tpb7uKAN3H},
}

@inproceedings{aaai2026_exo2ego_105488,
  title = {{Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/38244},
}

@inproceedings{cvpr2025_sound_27708,
  title = {{Sound Bridge: Associating Egocentric and Exocentric Videos via Audio Cues}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34806},
}

@inproceedings{neurips2025_egothinker_75570,
  title = {{EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=9Zwl2Ly28N},
}

@inproceedings{aaai2026_egocross_102644,
  title = {{EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/37589},
}

@inproceedings{cvpr2024_a_22640,
  title = {{A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectives}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30973},
}

@inproceedings{cvpr2025_bootstrap_25612,
  title = {{Bootstrap Your Own Views: Masked Ego-Exo Modeling for Fine-grained View-invariant Video Representations}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33703},
}

@inproceedings{neurips2025_in_77865,
  title = {{In the Eye of MLLM: Benchmarking Egocentric Video Intent Understanding with Gaze-Guided Prompting}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=YLxwj5YLb7},
}

@inproceedings{aaai2026_multiple_102611,
  title = {{Multiple Human Motion Understanding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/37556},
}

@inproceedings{cvpr2025_div_25828,
  title = {{DIV-FF: Dynamic Image-Video Feature Fields For Environment Understanding in Egocentric Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33936},
}

@inproceedings{icml2026_keep_52318,
  title = {{Keep It in Mind: User Centric Continual Spatial Intelligence Reasoning in Egocentric Video Streams}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=UfVYPA9VnD},
}

@inproceedings{icml2026_reason_52509,
  title = {{Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=WikPLZyyrT},
}