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
1.36k stars 135 forks source link

About preparing SthV2 #39

Closed klinic closed 1 year ago

klinic commented 2 years ago

Hi, Thank you for your work!

I read your 'DATASET.md'.

Are there two key points in processing sthv2 datasets: the first is to change the suffix to MP4, the second is to reduce the short side to 320p? (and can only videos with an original height of 240p be zoomed out?) 中文：处理sthv2数据集是不是就2个核心要义：第一个是将后缀改为.mp4，第二个是将短边放缩至320p？（而且是不是只有原始高度为240p的视频才能被选中，然后再去放缩？）

congee524 commented 1 year ago

resizing the video just to reduce the IO overhead.