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

@inproceedings{cvpr2019_long_14479,
  title = {{Long-Term Feature Banks for Detailed Video Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2024_moviechat_24198,
  title = {{MovieChat: From Dense Token to Sparse Memory for Long Video Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29526},
}

@inproceedings{cvpr2022_revisiting_19744,
  title = {{Revisiting the "Video" in Video-Language Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2024_timechat_25018,
  title = {{TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30015},
}

@inproceedings{aaai2018_multimodal_104060,
  title = {{Multimodal Keyless Attention Fusion for Video Classification}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/12319},
}

@inproceedings{cvpr2021_towards_18025,
  title = {{Towards Long-Form Video Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2023_selective_22149,
  title = {{Selective Structured State-Spaces for Long-Form Video Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21775},
}

@inproceedings{cvpr2021_temporal_17987,
  title = {{Temporal Query Networks for Fine-Grained Video Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2017_a_12002,
  title = {{A Dataset and Exploration of Models for Understanding Video Data Through Fill-In-The-Blank Question-Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{neurips2022_st_66276,
  title = {{ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54566},
}

@inproceedings{cvpr2020_violin_16453,
  title = {{Violin: A Large-Scale Dataset for Video-and-Language Inference}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2021_visual_18131,
  title = {{Visual Semantic Role Labeling for Video Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{neurips2024_longvideobench_70336,
  title = {{LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97862},
}

@inproceedings{cvpr2025_videotree_28107,
  title = {{VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34160},
}

@inproceedings{neurips2024_one_72929,
  title = {{One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94482},
}

@inproceedings{neurips2025_video_77997,
  title = {{Video-R1: Reinforcing Video Reasoning in MLLMs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=a2JTVVvcEl},
}

@inproceedings{cvpr2023_test_22326,
  title = {{Test of Time: Instilling Video-Language Models With a Sense of Time}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21817},
}

@inproceedings{cvpr2024_towards_25046,
  title = {{Towards Language-Driven Video Inpainting via Multimodal Large Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29810},
}

@inproceedings{cvpr2022_a_18204,
  title = {{A Large-Scale Comprehensive Dataset and Copy-Overlap Aware Evaluation Protocol for Segment-Level Video Copy Detection}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2025_the_27856,
  title = {{The Devil is in Temporal Token: High Quality Video Reasoning Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33488},
}

@inproceedings{cvpr2025_glus_26363,
  title = {{GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32431},
}

@inproceedings{neurips2024_streaming_72886,
  title = {{Streaming Long Video Understanding with Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94520},
}

@inproceedings{cvpr2025_drvideo_25999,
  title = {{DrVideo: Document Retrieval Based Long Video Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34066},
}

@inproceedings{cvpr2025_samwise_27500,
  title = {{SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34510},
}

@inproceedings{cvpr2025_re_27382,
  title = {{Re-thinking Temporal Search for Long-Form Video Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34465},
}

@inproceedings{cvpr2025_bolt_25561,
  title = {{BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34323},
}

@inproceedings{icml2024_videoprism_45358,
  title = {{VideoPrism: A Foundational Visual Encoder for Video Understanding}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33093},
}

@inproceedings{neurips2024_hourvideo_71200,
  title = {{HourVideo: 1-Hour Video-Language Understanding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97793},
}

@inproceedings{neurips2024_mmbench_72106,
  title = {{MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97696},
}

@inproceedings{neurips2025_time_78591,
  title = {{Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=gJ05Gm5VxQ},
}

@inproceedings{cvpr2025_on_27133,
  title = {{On the Consistency of Video Large Language Models in Temporal Comprehension}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34579},
}

@inproceedings{cvpr2025_hierarq_26508,
  title = {{HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33455},
}