• Repository: https://github.com/Vision-CAIR/MiniGPT4-video
• Paper: https://arxiv.org/abs/2407.12679

BibTeX:

@misc{ataallah2024goldfishvisionlanguageunderstandingarbitrarily,
      title={Goldfish: Vision-Language Understanding of Arbitrarily Long Videos}, 
      author={Kirolos Ataallah and Xiaoqian Shen and Eslam Abdelrahman and Essam Sleiman and Mingchen Zhuge and Jian Ding and Deyao Zhu and Jürgen Schmidhuber and Mohamed Elhoseiny},
      year={2024},
      eprint={2407.12679},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2407.12679}, 
}
@misc{ataallah2024minigpt4videoadvancingmultimodalllms,
      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},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2404.03413}, 
}