Joya Chen

Results 2 issues of Joya Chen

Hi kuanfang, thank you for your excellent work. I found that the "resize_points" function seems to be confusing width and height: https://github.com/kuanfang/opra/blob/b4649e32abdb6b60d75160d88a88c1722dfc60cb/utils/dataset.py#L17-L22 Here shape[0], [1] should be width, height, respectively....

Thanks for your great work! If possible, could you consider adding VideoLLM-online: Online Large Language Model for Streaming Video (CVPR 2024) We have released code, data, checkpoints, demo at: https://showlab.github.io/videollm-online/