-
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... -
ActivityNet, MSR-VTT, and MSVD
The dataset used in the paper is ActivityNet, MSR-VTT, and MSVD. The authors used these datasets for text-to-video retrieval tasks.