Graph Convolutional Networks for Temporal Action Localization (ICCV2019)
Geek Repo:Geek Repo
Github PK Tool:Github PK Tool
Hanqer opened this issue 3 years ago · comments
There are total 413 videos in this dataset, including training and testing. The number of provided RGB features is 413, but the number of provided flow features is 412. Why there is someone is missing?