search

Qinying-Liu / CASE

Accepted by ICCV2023, Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach
104 stars 3 forks source link

Feature Extraction #3

Closed EmreOzkose closed 8 months ago

EmreOzkose commented 8 months ago

Hi, congrats for the work.

Can you share a feature extraction script for testing our own videos?

Qinying-Liu commented 8 months ago

I am sorry. We use pre-processed features of the benchmark datasets provided by other methods and don't have feature extraction script. You may refer to https://github.com/piergiaj/pytorch-i3d.

EmreOzkose commented 8 months ago

pytorch-i3d repo is really hard to reproduce :). Anyway, thank you for reply