-
Kinetics-400, Something-Something V2, Epic-Kitchens-100, HMDB51, and UCF101
The dataset used in the paper is a video recognition benchmark, specifically Kinetics-400, Something-Something V2, Epic-Kitchens-100, HMDB51, and UCF101. -
HACS and Epic-Kitchens-100
The authors used the HACS and Epic-Kitchens-100 datasets for action localization tasks. -
Kinetics-400, Something-Something-V2, and Epic-Kitchens-100
The authors used the Kinetics-400, Something-Something-V2, and Epic-Kitchens-100 datasets for video understanding tasks.