Sound events in daily life carry rich information about the objective wo...
Verbal and non-verbal human reaction generation is a challenging task, a...
In dyadic interaction, predicting the listener's facial reactions is
cha...
This paper presents our Facial Action Units (AUs) recognition submission...
Graph is powerful for representing various types of real-world data. The...
Traditional pixel-wise image attack algorithms suffer from poor robustne...
A long-term video, such as a movie or TV show, is composed of various sc...
The activations of Facial Action Units (AUs) mutually influence one anot...
Current adversarial attack research reveals the vulnerability of
learnin...
The vanilla convolutional neural network (CNN) is vulnerable to images w...
Considering the scarcity of medical data, most datasets in medical image...
We propose a geometry constrained network, termed GC-Net, for weakly
sup...
In this paper, we propose a novel retinal layer boundary model for
segme...
Although real-coded differential evolution (DE) algorithms can perform w...