search

OpenGVLab / VideoMAEv2

[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking
https://arxiv.org/abs/2303.16727
MIT License
445 stars 45 forks source link

Extracting Features from Frame Level Data #43

Closed n1791348200 closed 3 months ago

n1791348200 commented 7 months ago

Can you provide code for extracting features from frame level datasets？Thank you very much！！

congee524 commented 3 months ago

You can write one yourself based on our script https://github.com/OpenGVLab/VideoMAEv2/blob/master/extract_tad_feature.py.