Given a classifier, the inherent property of semantic Out-of-Distributio...
In this paper, we introduce FITS, a lightweight yet powerful model for t...
Continuous monitoring of human vital signs using non-contact mmWave rada...
In this paper, we study teacher-student learning from the perspective of...
Data augmentation (DA) has become a de facto solution to expand training...
Deep Active Learning (DAL) has been advocated as a promising method to r...
The bi-encoder structure has been intensively investigated in code-switc...
Distinguishing between computer-generated (CG) and natural photographic ...
Deep Neural Networks (DNNs) have achieved excellent performance in vario...
This paper proposes a novel out-of-distribution (OOD) detection framewor...
Dual-encoder structure successfully utilizes two language-specific encod...
We study the Representative Volume Element (RVE) method, which is a meth...
Recently, there has been a surge of Transformer-based solutions for the ...
This paper proposes a simple baseline framework for video-based 2D/3D hu...
Adversarial examples (AEs) pose severe threats to the applications of de...
When analyzing human motion videos, the output jitters from existing pos...
Time series (TS) anomaly detection (AD) plays an essential role in vario...
XORNet-based low power controller is a popular technique to reduce circu...
Applying deep learning (DL) techniques in the electronic design automati...
Various deep learning techniques have been proposed to solve the single-...
The selective visual attention mechanism in the human visual system (HVS...
Time series is a special type of sequence data, a set of observations
co...
In Graph Neural Networks (GNNs), the embedding of each node is obtained ...
Deep learning (DL) has achieved unprecedented success in a variety of ta...
This paper presents AppealNet, a novel edge/cloud collaborative architec...
Video action recognition (VAR) is a primary task of video understanding,...
Sensor-based time series analysis is an essential task for applications ...
In this paper, we observe that modern mobile apps come with a large numb...
Deep neural networks (DNNs) have become one of the enabling technologies...
Human poses that are rare or unseen in a training set are challenging fo...
The massive upload of text on the internet creates a huge inverted index...
Considering the attacks against industrial control system are mostly
org...
In this paper, we propose a two-stage fully 3D network, namely
DeepFuse,...
Deep neural networks (DNNs) are shown to be susceptible to adversarial
e...
Machine learning systems based on deep neural networks (DNNs) produce
st...
Robust detection and tracking of objects is crucial for the deployment o...
In this paper, we propose a novel structure-aware 3D hourglass network f...
Machine learning systems based on deep neural networks (DNNs) have gaine...
Neural approximate computing gains enormous energy-efficiency at the cos...
Deep learning has become the de-facto computational paradigm for various...
Machine learning systems based on deep neural networks, being able to pr...