Search Results for author:
Found 1 papers, 1 papers with code
CAST: Cross-Attention in Space and Time for Video Action Recognition
In this work, we propose a novel two-stream architecture, called Cross-Attention in Space and Time (CAST), that achieves a balanced spatio-temporal understanding of videos using only RGB input.
Ranked #7 on
Action Recognition
on EPIC-KITCHENS-100
Cannot find the paper you are looking for? You can
Submit a new open access paper.
