To bridge the physical and virtual worlds for rapidly developed VR/AR
ap...
This paper proposes a novel module called middle spectrum grouped convol...
Convenient 4D modeling of human-object interactions is essential for num...
LBP is a successful hand-crafted feature descriptor in computer vision.
...
Developing lightweight Deep Convolutional Neural Networks (DCNNs) and Vi...
Motion capture from a monocular video is fundamental and crucial for us
...
Efficiency and robustness are increasingly needed for applications on 3D...
Face recognition is one of the most active tasks in computer vision and ...
4D modeling of human-object interactions is critical for numerous
applic...
Binary neural networks (BNNs) constrain weights and activations to +1 or...
Recently, deep Convolutional Neural Networks (CNNs) can achieve human-le...
High-quality 4D reconstruction of human performance with complex interac...
Binary neural networks (BNNs), where both weights and activations are
bi...
Replacing normal convolutions with group convolutions can significantly
...
Face anti-spoofing (FAS) plays a vital role in face recognition systems....