7 datasets found

The dataset used for testing the HandVoxNet approach for 3D hand shape and pose estimation from a single depth map.

A hand, which is an articulated object, is composed of six local parts: the palm and five independent fingers.

The NYU Hand Pose Dataset comprises 70,000 images captured with a depth sensor in VGA resolution accompanied by ground truth annotations of positions of hand joints.

The Clothing dataset contains metadata, text descriptions, and images of the clothing items, with the review score as the label.

The dataset is used for depth auto-encoding and contains depth images.

The dataset is used for indoor scene understanding and contains RGB and depth images.

Multi-task learning (MTL) research is broadly divided into two categories: one is to learn the correlation between tasks through model structures, and the other is to balance...