Gestures are non-verbal but important behaviors accompanying people's sp...
Transformer-based models achieve favorable performance in artistic style...
This paper proposes an anchor-based deformation model, namely AnchorDEF,...
This paper presents a novel approach for estimating human body shape and...
We present a simple yet effective method for skeleton-free motion
retarg...
A good motion retargeting cannot be reached without reasonable considera...
Reconstructing two hands from monocular RGB images is challenging due to...
In this work, we investigate a simple and must-known conditional generat...
Human-Object Interaction (HOI) detection is a core task for high-level i...
Data augmentation has been proved effective in training deep models. Exi...
Conventional 3D human pose estimation relies on first detecting 2D body
...
Zero-Shot Learning (ZSL) targets at recognizing unseen categories by
lev...
Data mixing augmentation has proved effective in training deep models. R...
This work addresses the challenging problem of unconstrained 3D hand pos...
The main problems of few-shot learning are how to learn a generalized
re...
Not all the human body parts have the same degree of freedom (DOF) due t...
A well-designed fine-grained categorization system usually has three
con...
In the context of fine-grained visual categorization, the ability to
int...