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

@inproceedings{cvpr2016_movieqa_11709,
  title = {{MovieQA: Understanding Stories in Movies Through Question-Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2021_next_17467,
  title = {{NExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{aaai2019_activitynet_103547,
  title = {{ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4946},
}

@inproceedings{cvpr2020_hierarchical_15642,
  title = {{Hierarchical Conditional Relation Networks for Video Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2018_motion_13387,
  title = {{Motion-Appearance Co-Memory Networks for Video Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Gao_Motion-Appearance_Co-Memory_Networks_CVPR_2018_paper.html},
}

@inproceedings{cvpr2019_audio_13877,
  title = {{Audio Visual Scene-Aware Dialog}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{aaai2020_location_103649,
  title = {{Location-Aware Graph Convolutional Networks for Video Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6737},
}

@inproceedings{aaai2020_divide_103659,
  title = {{Divide and Conquer: Question-Guided Spatio-Temporal Contextual Attention for Video Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6766},
}

@inproceedings{cvpr2023_mist_21492,
  title = {{MIST: Multi-Modal Iterative Spatial-Temporal Transformer for Long-Form Video Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22566},
}

@inproceedings{cvpr2021_sutd_17815,
  title = {{SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning Over Traffic Events}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{aaai2020_knowit_103625,
  title = {{KnowIT VQA: Answering Knowledge-Based Questions about Videos}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6713},
}

@inproceedings{cvpr2022_from_18886,
  title = {{From Representation to Reasoning: Towards Both Evidence and Commonsense Reasoning for Video Question-Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{neurips2023_egoschema_67696,
  title = {{EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/73630},
}

@inproceedings{aaai2021_dynamic_477,
  title = {{Dynamic Graph Representation Learning for Video Dialog via Multi-Modal Shuffled Transformers}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/01415-dynamic-graph-representation-learning-for-video-dialog-via-multi-modal-shuffled-transformers/},
}

@inproceedings{aaai2021_dramaqa_465,
  title = {{DramaQA: Character-Centered Video Story Understanding with Hierarchical QA}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/01166-dramaqa-character-centered-video-story-understanding-with-hierarchical-qa/},
}

@inproceedings{aaai2021_self_1362,
  title = {{Self-supervised Pre-training and Contrastive Representation Learning for Multiple-choice Video QA}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/13171-self-supervised-pre-training-and-contrastive-representation-learning-for-multiple-choice-video-qa/},
}

@inproceedings{neurips2023_self_68720,
  title = {{Self-Chained Image-Language Model for Video Localization and Question Answering}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/71124},
}

@inproceedings{cvpr2024_koala_23869,
  title = {{Koala: Key Frame-Conditioned Long Video-LLM}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31782},
}

@inproceedings{neurips2021_learning_63049,
  title = {{Learning from Inside: Self-driven Siamese Sampling and Reasoning for Video Question Answering}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28659},
}

@inproceedings{cvpr2025_videoespresso_28096,
  title = {{VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34170},
}

@inproceedings{cvpr2025_flexible_26282,
  title = {{Flexible Frame Selection for Efficient Video Reasoning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32897},
}

@inproceedings{aaai2024_video_7769,
  title = {{Video-Context Aligned Transformer for Video Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29954},
}

@inproceedings{cvpr2024_align_22746,
  title = {{Align and Aggregate: Compositional Reasoning with Video Alignment and Answer Aggregation for Video Question-Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30634},
}

@inproceedings{cvpr2025_bimba_25556,
  title = {{BIMBA: Selective-Scan Compression for Long-Range Video Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32662},
}

@inproceedings{aaai2024_ytcommentqa_7836,
  title = {{YTCommentQA: Video Question Answerability in Instructional Videos}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29906},
}

@inproceedings{aaai2024_stair_7239,
  title = {{STAIR: Spatial-Temporal Reasoning with Auditable Intermediate Results for Video Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29890},
}

@inproceedings{cvpr2025_vited_28052,
  title = {{VITED: Video Temporal Evidence Distillation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33327},
}

@inproceedings{neurips2025_tool_76899,
  title = {{Tool-Augmented Spatiotemporal Reasoning for Streamlining Video Question Answering Task}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=OFz4VDn0SO},
}

@inproceedings{aaai2026_vista_104165,
  title = {{Vista: Scene-Aware Optimization for Streaming Video Question Answering Under Post-Hoc Queries}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/37694},
}

@inproceedings{aaai2025_friendsqa_9239,
  title = {{FriendsQA: A New Large-Scale Deep Video Understanding Dataset with Fine-grained Topic Categorization for Story Videos}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32920},
}

@inproceedings{aaai2025_granularity_9360,
  title = {{Granularity-Adaptive Spatial Evidence Tokenization for Video Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32416},
}

@inproceedings{neurips2025_magnet_75863,
  title = {{MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=CwXyUdqFqW},
}

@inproceedings{icml2026_video_49851,
  title = {{Video-in-the-Loop: Span-Grounded Long Video QA with Interleaved Reasoning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=6NDxn4R4JT},
}

@inproceedings{icml2026_videoseal_51999,
  title = {{VideoSEAL: Mitigating Evidence Misalignment in Agentic Long Video Understanding by Decoupling Answer Authority}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=RsPequeaiZ},
}

@inproceedings{icml2026_reasoning_53607,
  title = {{Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=h3TLVeukMA},
}

@inproceedings{iclr2025_streaming_81018,
  title = {{Streaming Video Question-Answering with In-context Video KV-Cache Retrieval}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30750},
}

@inproceedings{iclr2026_fostering_84963,
  title = {{Fostering Video Reasoning via Next-Event Prediction}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=8nUgzuvskm},
}

@inproceedings{iclr2026_a_86669,
  title = {{A.I.R.: Enabling Adaptive, Iterative, and Reasoning-based Frame Selection For Video Question Answering}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=SZVpOKw0YD},
}