search

rese1f / MovieChat

[CVPR 2024] MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
https://rese1f.github.io/MovieChat/
BSD 3-Clause "New" or "Revised" License
534 stars 41 forks source link

Have you release the model weights #2

Closed HaoZhang534 closed 1 year ago

HaoZhang534 commented 1 year ago

Thank you for your great work! I find the pre-trained weight link is pointed to the weight of video-llama. Have you released the model weights of this work?

Espere-1119-Song commented 1 year ago

Our method is training-free, you can implement this mechanism in any model.We use videollama as the base model, so the pre-trained weight link is pointed to the weight of video-llama.