% Key papers for Video LLMs with fine-grained understanding (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2024_mvbench_24090,
  title = {{MVBench: A Comprehensive Multi-modal Video Understanding Benchmark}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31654},
}

@inproceedings{cvpr2025_video_28089,
  title = {{Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33002},
}

@inproceedings{cvpr2024_ma_24045,
  title = {{MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30043},
}

@inproceedings{cvpr2024_videollm_25231,
  title = {{VideoLLM-online: Online Video Large Language Model for Streaming Video}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29835},
}

@inproceedings{cvpr2021_look_17367,
  title = {{Look Before You Speak: Visually Contextualized Utterances}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{neurips2021_merlot_61633,
  title = {{MERLOT: Multimodal Neural Script Knowledge Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26470},
}

@inproceedings{cvpr2024_kvq_23863,
  title = {{KVQ: Kwai Video Quality Assessment for Short-form Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30360},
}

@inproceedings{cvpr2025_adaptive_25441,
  title = {{Adaptive Keyframe Sampling for Long Video Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34055},
}

@inproceedings{cvpr2022_intentvizor_19089,
  title = {{IntentVizor: Towards Generic Query Guided Interactive Video Summarization}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2024_musechat_24236,
  title = {{MuseChat: A Conversational Music Recommendation System for Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31734},
}

@inproceedings{cvpr2025_video_28091,
  title = {{Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33367},
}

@inproceedings{cvpr2024_scaling_24746,
  title = {{Scaling Up Video Summarization Pretraining with Large Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30775},
}

@inproceedings{cvpr2024_contextual_23029,
  title = {{Contextual Augmented Global Contrast for Multimodal Intent Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29803},
}

@inproceedings{aaai2025_vtg_11225,
  title = {{VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32341},
}

@inproceedings{cvpr2025_mlvu_26868,
  title = {{MLVU: Benchmarking Multi-task Long Video Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33659},
}

@inproceedings{cvpr2025_m_26828,
  title = {{M-LLM Based Video Frame Selection for Efficient Video Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34303},
}

@inproceedings{cvpr2024_mm_24066,
  title = {{MM-Narrator: Narrating Long-form Videos with Multimodal In-Context Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30881},
}

@inproceedings{cvpr2025_video_28084,
  title = {{Video Summarization with Large Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33760},
}

@inproceedings{aaai2025_v2xum_11206,
  title = {{V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32374},
}

@inproceedings{cvpr2024_bt_22813,
  title = {{BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31431},
}

@inproceedings{cvpr2025_vidhalluc_28076,
  title = {{VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34827},
}

@inproceedings{cvpr2024_mirasol3b_24152,
  title = {{Mirasol3B: A Multimodal Autoregressive Model for Time-Aligned and Contextual Modalities}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30550},
}

@inproceedings{cvpr2024_vista_25187,
  title = {{VISTA-LLAMA: Reducing Hallucination in Video Language Models via Equal Distance to Visual Tokens}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29676},
}