Heatmap regression methods have dominated face alignment area in recent years while
they ignore the inherent relation between different landmarks. In this paper, we propose a …

Recently, deep learning-based facial landmark detection has achieved significant
improvement. However, the semantic ambiguity problem degrades detection performance …

Cascaded computation, whereby predictions are recurrently refined over several stages, has
been a persistent theme throughout the development of landmark detection models. In this …

In human and hand pose estimation, heatmaps are a crucial intermediate representation for
a body or hand keypoint. Two popular methods to decode the heatmap into a final joint …

Top-performing landmark estimation algorithms are based on exploiting the excellent ability
of large convolutional neural networks (CNNs) to represent local appearance. However, it is …

The occlusion problem heavily degrades the localization performance of face alignment.
Most current solutions for this problem focus on annotating new occlusion data, introducing …

Human tends to locate the facial landmarks with heavy occlusion by their relative position to
the easily identified landmarks. The clue is defined as the landmark inherent relation while it …

At present, deep neural network methods have played a dominant role in face alignment
field. However, they generally use predefined network structures to predict landmarks, which …

Using a loss function with appropriate properties to supervise the training of the neural
network can substantially improve its accuracy and speed. A majority of loss functions …

Real-time eyeblink detection in the wild is a recently emerged challenging task that suffers
from dramatic variations in face attribute, pose, illumination, camera view and distance, etc …