3 datasets found

Human Attribute Recognition (HAR) is a challenging task due to large variations of body gestures, external occlusions, lighting conditions, image resolutions and blurrinesses.

The VOC2012 dataset is a multi-label image recognition dataset. It contains 11,540 train-val images and 10,991 test images.

Large scale datasets [18, 17, 27, 6] boosted text conditional image generation quality. However, in some domains it could be difficult to make such datasets and usually it could...