30 datasets found

UCF-Crime dataset of surveillance videos

A video benchmark for binaural audio generation from video.

A large-scale video dataset with binaural audio in photo-realistic environments to better understand and learn the relation between visuals and binaural audio.

The VideoLT dataset contains 1,004 classes and about 256,218 untrimmed videos collected from YouTube, covering a wide range of human activities, including everyday life,...

A dataset for evaluating anomaly explanation methods. It contains 22,722 manually labelled frames in ShanghaiTech, Avenue, and UCSD Ped2.

This paper addresses fast semantic segmentation on video. The dataset used is Cityscapes and CamVid.

The VQ2D dataset is a subset of the Ego4D dataset, containing ground truth tracking annotations for the query object's last appearance.

The EgoLoc dataset is a reformulation of the VQ3D task and a modular pipeline that leads to significant improvements on the Ego4D VQ3D benchmark.

The MuViHand dataset is a synthetic multi-view video-based hand pose dataset with 402,000 synthetic hand images available in 4,560 videos.

A video restoring dataset

A fashion video synthesis dataset

A video synthesis dataset

The VGGSound dataset is a large-scale audio-visual dataset containing 10,000 10-second video clips with corresponding audio files.

CSL-Daily is a Chinese sign language (CSL) dataset that mainly focuses on people’s daily lives. It includes 18401, 1077, and 1176 available examples in the training, validation,...

The dataset used for training the image-to-video model consists of LAION COCO 600M and Webvid10M.

The dataset used for training the video model consists of Webvid-10M, a large-scale dataset of short videos with textual descriptions.

The dataset used for training the text-to-video model consists of 20 million videos and 600 million images.

The dataset contains real and fake face videos.

A method for unsupervised learning of equations of motion for objects in raw and optionally distorted unlabeled video.

The LSMDC movie description dataset consists of 118,081 short video clips extracted from 202 movies, each annotated with a single caption.