Jinheng Xie

It has been found that there are some bugs in the code for bounding boxes generation and I have figured them out.

about train loss

3

can you tell me the ultimate loss（train/val） in your training？：）

Adding paper to the repository

1

Hi, Would you like to add this paper to the awesome list: Learning Visual Prior via Generative Pre-Training (NeurIPS 2023) code: https://github.com/Sierkinhane/VisorGPT paper: https://openreview.net/pdf?id=LUT4b9gOtS Best regards

hello jinyu, 感觉可以加一个播放视频的功能