@article{240403413v1,
  title = {MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens},
  author = {Kirolos Ataallah and Xiaoqian Shen and Eslam Abdelrahman and Essam Sleiman and Deyao Zhu and Jian Ding and Mohamed Elhoseiny},
  year = {2024},
  eprint = {2404.03413},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.03413v1},
}