Human pose estimation aims to locate the human body parts and build human body
representation (eg, body skeleton) from input data such as images and videos. It has drawn …

Estimation of the human pose from a monocular camera has been an emerging research
topic in the computer vision community with many applications. Recently, benefiting from the …

Deep learning-based methods for video pedestrian detection and tracking require large
volumes of training data to achieve good performance. However, data acquisition in …

We present an approach for 3D global human mesh recovery from monocular videos
recorded with dynamic cameras. Our approach is robust to severe and long-term occlusions …

Inferring human pose from a monocular RGB image remains an interesting field of research
in computer vision. It serves as a fundamental key for many real-world applications …

We present a new trainable system for physically plausible markerless 3D human motion
capture, which achieves state-of-the-art results in a broad range of challenging scenarios …

While the voxel-based methods have achieved promising results for multi-person 3D pose
estimation from multi-cameras, they suffer from heavy computation burdens, especially for …

Due to the mutual occlusion, severe scale variation, and complex spatial distribution, the
current multi-person mesh recovery methods cannot produce accurate absolute body poses …

We consider the challenging multi-person 3D body mesh estimation task in this work.
Existing methods are mostly two-stage based--one stage for person localization and the …

Most of the existing 3D human pose estimation approaches mainly focus on predicting 3D
positional relationships between the root joint and other human joints (local motion) instead …