4 datasets found

Video Diffusion Models have been developed for video generation, usually integrating text and image conditioning to enhance control over the generated content.

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...

The dataset used in the paper for text-to-video diffusion models

The authors used the pre-trained diffusion-based text-to-video (T2V) generation model without additional fine-tuning.