Inspired by the success of volumetric 3D pose estimation, some recent hu...
Human pose is typically represented by a coordinate vector of body joint...
Multi-object tracking in videos requires to solve a fundamental problem ...
As an important upstream task for many medical applications, supervised
...
While the voxel-based methods have achieved promising results for
multi-...
While monocular 3D pose estimation seems to have achieved very accurate
...
Robustness and discrimination power are two fundamental requirements in
...
We present a Siamese-like Dual-branch network based on solely Transforme...
Multi-camera tracking systems are gaining popularity in applications tha...
Convolution has been arguably the most important feature transform for m...
We present VoxelTrack for multi-person 3D pose estimation and tracking f...
Estimating 3D human pose from a single image suffers from severe ambigui...
Person search generally involves three important parts: person detection...
Semi-supervised learning aims to boost the accuracy of a model by explor...
We present an approach to estimate 3D poses of multiple people from mult...
There has been remarkable progress on object detection and re-identifica...
Cross view feature fusion is the key to address the occlusion problem in...
We present an approach to recover absolute 3D human poses from multi-vie...
We address the problem of detecting objects in videos with the interest ...
We present a new model which represents data as a mixture of simplices.
...
Human pose estimation is a key step to action recognition. We propose a
...