Sound events in daily life carry rich information about the objective wo...
Verbal and non-verbal human reaction generation is a challenging task, a...
The Multi-modal Multiple Appropriate Facial Reaction Generation Challeng...
In dyadic interaction, predicting the listener's facial reactions is
cha...
As a promising non-password authentication technology, radio frequency (...
The available evidence suggests that dynamic functional connectivity (dF...
This paper presents our Facial Action Units (AUs) recognition submission...
Graph is powerful for representing various types of real-world data. The...
Recent mainstream weakly supervised semantic segmentation (WSSS) approac...
Traditional pixel-wise image attack algorithms suffer from poor robustne...
The introduction of multiple viewpoints inevitably increases the bitrate...
The activations of Facial Action Units (AUs) mutually influence one anot...
Current adversarial attack research reveals the vulnerability of
learnin...
Pre-trained language models achieves high performance on machine reading...
In open-domain conversational systems, it is important but challenging t...
Distributed deep learning workloads include throughput-intensive trainin...
The generation of humor is an under-explored and challenging problem.
Pr...
This paper presents a neural document expansion approach (NeuDEF) that
e...
Stock prediction aims to predict the future trends of a stock in order t...
Learning to rank with biased click data is a well-known challenge. A var...
When observations are organized into groups where commonalties exist amo...
Time-varying mixture densities occur in many scenarios, for example, the...