Alvin-Zeng / PGCN

Graph Convolutional Networks for Temporal Action Localization (ICCV2019)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

ActivityNet feature.

JackyTown opened this issue · comments

Hello, Alvin!

Thank you very much for sharing the code and feature!

However, when using ActivityNet feature, I run into a problem that the number of directories for RGB and Flow frames are different.

Why the number of directories for ActivityNet RGB (13811) and Flow (14938) frames are different?
Does it mean that we can only use the intersection?

Hello?

Another question, is P-GCN dependent on feature with large recepetive fields like I3D feature?
What is the performance of P-GCN on TSN feature?

Look forward to your favourable reply !!!

same question. Hope for reply

Same question