search

mbzuai-oryx / Video-ChatGPT

[ACL 2024 🔥] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotemporal video representation. We also introduce a rigorous 'Quantitative Evaluation Benchmarking' for video-based conversational models.
https://mbzuai-oryx.github.io/Video-ChatGPT
Creative Commons Attribution 4.0 International
1.05k stars 92 forks source link

GoogleDrive of Clip-Features #112

Closed xiaokj37 closed 4 days ago

xiaokj37 commented 2 weeks ago

Could you please provide the Google Drive link of ActivityNet_Train_Video-ChatGPT_Clip-L14_Features.zip? Sharepoint does not allow downloading using wget.

mmaaz60 commented 1 week ago

Hi @SeuXiao,

I appreciate your interest in our work. You can find the google drive links to download the videos here.

Thanks

xiaokj37 commented 1 week ago

Thanks for you reply. What I want to know is that why not fine tune the LLM.

mmaaz60 commented 1 week ago

Hi @SeuXiao,

Thank you for your interest in our work. At the development time, we do not have enough resources to fine-tune complete LLM. However, it would be interesting to see how the model performs when finetuning the LLM as well.

Please do share if you get some results. Good Luck!