-
UCF-Crime dataset
UCF-Crime dataset of surveillance videos -
SimBinaural
A large-scale video dataset with binaural audio in photo-realistic environments to better understand and learn the relation between visuals and binaural audio. -
GSVNET: GUIDED SPATIALLY-VARYING CONVOLUTION FOR FAST SEMANTIC SEGMENTATION O...
This paper addresses fast semantic segmentation on video. The dataset used is Cityscapes and CamVid. -
Video Restoration
A video restoring dataset -
Fashion Video Synthesis
A fashion video synthesis dataset -
Pixabay100
A video synthesis dataset -
Webvid-10M
The dataset used for training the video model consists of Webvid-10M, a large-scale dataset of short videos with textual descriptions. -
LAION COCO 600M
The dataset used for training the text-to-video model consists of 20 million videos and 600 million images. -
The Deepfake Detection Challenge (DFDC) Dataset
The dataset contains real and fake face videos. -
Symbolic Pregression: Discovering Physical Laws from Distorted Video
A method for unsupervised learning of equations of motion for objects in raw and optionally distorted unlabeled video.