-
MSR-VTT and UCF-101
The dataset used in the paper is MSR-VTT and UCF-101, two public datasets for video-text generation. MSR-VTT contains 4,900 videos with 20 manually annotated captions for each... -
UCF-101, ERA, and BAR datasets
This paper uses the UCF-101, Event Recognition in Aerial videos (ERA), and Biased Action Recognition (BAR) datasets for image classification tasks.