AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understanding

@misc{tao2025omniadavideoragomnicontextualadaptive,
      title={Omni-AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented for  Efficient Long Video Understanding},
      author={Dacheng Tao and Yong Liu and Xiangtai Li and Jiangning Zhang and Zhucun Xue and Yuxuan Cai and Xurong Xie},
      year={2025},
      eprint={2506.13589},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2506.13589},
}