Recognizing human activities from video sequences or still images is a challenging task due
to problems, such as background clutter, partial occlusion, changes in scale, viewpoint …

Spatiotemporal human representation based on 3D visual perception data is a rapidly
growing research area. Representations can be broadly categorized into two groups …

Most of the existing deep learning-based methods for 3D hand and human pose estimation
from a single depth map are based on a common framework that takes a 2D depth map and …

We explore 3D human pose estimation from a single RGB image. While many approaches
try to directly predict 3D pose from image measurements, we explore a simple architecture …

We present an unsupervised learning approach to re-cover 3D human pose from 2D
skeletal joints extracted from a single image. Our method does not require any multi-view …

For 3D hand and body pose estimation task in depth image, a novel anchor-based approach
termed Anchor-to-Joint regression network (A2J) with the end-to-end learning ability is …

We propose an approach to estimate 3D human pose in real world units from a single RGBD
image and show that it exceeds performance of monocular 3D pose estimation approaches …

We propose a viewpoint invariant model for 3D human pose estimation from a single depth
image. To achieve this, our discriminative model embeds local regions into a learned …

The past decade has evinced a boom of computer-based approaches to aid movement
assessment in early infancy. Increasing interests have been dedicated to develop AI driven …

Abstract 3D pose estimation from a single image is a challenging task in computer vision.
We present a weakly supervised approach to estimate 3D pose points, given only 2D pose …