search

OpenGVLab / VideoMAEv2

[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking
https://arxiv.org/abs/2303.16727
MIT License
524 stars 63 forks source link

could you please provide the weights of VideoMAEv2 pre-trained on Kinetics-400? #25

Closed fmthoker closed 1 year ago

fmthoker commented 1 year ago

Hi, Thanks for sharing this great work. I am doing an evaluation of VIT models on specific video benchmarks and would like to include videomaev2. To make the comparison fair with other video SSL works, I need the weights of the ViT-B model pretrained on the Kinetics-400 dataset with the videomae2 loss function. Is it possible to share the corresponding weights? My email is fmthoker@gmail.com

congee524 commented 1 year ago

Hi, VideoMAE v2 uses the same loss function MSE Loss as v1. We also only pre-trained on the UnlabeledHybrid dataset, there's no version trained on k400.

congee524 commented 1 year ago

the model weight has been shared via email.