Transformers have emerged as the superior choice for face recognition ta...
In this paper, we tackle the challenging problem of 3D keypoint estimati...
Compared with the feature-based distillation methods, logits distillatio...
This paper presents a framework for efficient 3D clothed avatar
reconstr...
Extracting parametric edge curves from point clouds is a fundamental pro...
The function of constructing the hierarchy of objects is important to th...
The ability to discover abstract physical concepts and understand how th...
Human parsing is a key topic in image processing with many applications,...
In offline reinforcement learning (RL), one detrimental issue to policy
...
In 3D face reconstruction, orthogonal projection has been widely employe...
To achieve accurate and robust object detection in the real-world scenar...
Capsule networks are designed to present the objects by a set of parts a...
3D human pose and shape recovery from a monocular RGB image is a challen...
One of the challenges of logo recognition lies in the diversity of forms...
We study the problem of safe offline reinforcement learning (RL), the go...
Offline reinforcement learning (RL) enables learning policies using
pre-...
Thermal power generation plays a dominant role in the world's electricit...
Vehicle re-identification is a challenging task due to high intra-class
...
Long-tailed problem has been an important topic in face recognition task...
Face anti-spoofing is critical to the security of face recognition syste...
Facial landmark localization is a very crucial step in numerous face rel...
Recently, deep learning based facial landmark detection has achieved gre...
Generating plausible hair image given limited guidance, such as sparse
s...
Face anti-spoofing is crucial for the security of face recognition syste...
In many face recognition applications, there is large amount of face dat...
In the application of face recognition, eyeglasses could significantly
d...
Face alignment, which fits a face model to an image and extracts the sem...
Scene text detection is a challenging problem in computer vision. In thi...
In this paper, we propose a novel method called Rotational Region CNN (R...
Person re-identification is challenging due to the large variations of p...
Person re-identification is an important technique towards automatic sea...