VideoMAE-Action-Detection
VideoMAE-Action-Detection copied to clipboard
[NeurIPS 2022 Spotlight] VideoMAE for Action Detection
Thank you for your job! How can I use pre-trained model to detect action directly? Looking forward to your reply.
Thanks for your work After fine-tuning, the performance of the model on the verification set is obtained, but how to get the accuracy of the model on the test set?...
Hi authors, I found that the input video resolution was set to 16x224x224 while the video resolution used during the validation was 16x256x352. I might read it wrong, but I...
Do you plan to release ViT-L/H model checkpoint for AVA dataset?
@wanglimin @yztongzhan Thanks for your great job on video action detection. I use ViT-B finetuned weights test on my own video. The performance is so-so. Could you provide AVA2.2 finetuned...