Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension

@misc{yang2024videoragvisuallyalignedretrievalaugmented,
      title={Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension}, 
      author={Xiao Yang and Rongrong Ji and Xiawu Zheng and Jiebo Luo and Jinfa Huang and Jiayi Ji and Fei Chao and Guilin Li and Haojia Lin and Yongdong Luo},
      year={2024},
      eprint={2411.13093},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2411.13093}, 
}