search

MCG-NJU / VideoMAE

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
https://arxiv.org/abs/2203.12602
Other
1.32k stars 131 forks source link

About pre-trained models #91

Open 972821054 opened 1 year ago

972821054 commented 1 year ago

Hello, thank you for your contribution to the field of video large models. I see that you have the performance of trying to crop a 320x320 image, but your model library does not provide the relevant training model. Can you provide the relevant model? I would be very grateful if I could!