12 datasets found

The LIVE-VQA dataset is a video quality assessment dataset, consisting of 1,000 video sequences with accompanying MOS values.

Walking pedestrians dataset containing 5 video sequences with 1536 pedestrians.

The dataset consists of 100 video sequences of a micro-particle in a 2-dimensional space. Each video sequence has a duration of 30 µs with one frame per µs.

The dataset used in the paper for future semantic segmentation prediction.

The MOTS Challenge dataset is a real-world video dataset consisting of pedestrian tracking and segmentation.

RICH is an in-the-wild and indoor multi-view dataset for 3D human body reconstruction, containing 2D keypoints and 3D body mesh annotations.

The LiveNetflix-II Database is a dataset of video sequences with accompanying audio, used for testing the proposed audio-visual quality metric.

The UnB-AVQ database is a large dataset of audio-visual stimuli (video sequences with accompanying audio) with their corresponding quality scores.

The KoNViD-1k dataset is a video quality assessment dataset, consisting of 1,200 video sequences with accompanying MOS values.

A dataset for boundary detection, containing 100 short binocular video sequences of natural scenes.

Deepfakes have become a critical social problem, and detecting them is of utmost importance. The FaceForensics++ dataset offers fake video datasets. Most of the detection...

The Cityscapes dataset is a large and famous city street scene semantic segmentation dataset. 19 classes of which 30 classes of this dataset are considered for training and...