Fast Adversarial Training (FAT) not only improves the model robustness b...
Practical object detection application can lose its effectiveness on ima...
Developing a practically-robust automatic speech recognition (ASR) is
ch...
With the rapid evolution of large language models (LLMs), there is a gro...
Deep learning-based recommender systems (DRSs) are increasingly and wide...
Recent studies have shown that higher accuracy on ImageNet usually leads...
In a transfer-based attack against Automatic Speech Recognition (ASR)
sy...
With the development of deep learning technology, the facial manipulatio...
Delivering customer services through video communications has brought ne...
The field of Question Answering (QA) has made remarkable progress in rec...
Out-Of-Distribution (OOD) detection has received broad attention over th...
Contrastive Language-Image Pre-trained (CLIP) models have zero-shot abil...
Despite of the superb performance on a wide range of tasks, pre-trained
...
Out-of-distribution (OOD) detection is a critical task for ensuring the
...
Adversarial Training (AT), which is commonly accepted as one of the most...
Imbalanced training data is a significant challenge for medical image
cl...
Neural passage retrieval is a new and promising approach in open retriev...
Deep learning models exhibit a preference for statistical fitting over
l...
Cross-modal retrieval aims to enable flexible retrieval experience by
co...
Despite that deep neural networks (DNNs) have achieved enormous success ...
Intellectual property protection(IPP) have received more and more attent...
In this article, we develop a least–squares/fictitious domain method for...
End-to-end question answering (QA) requires both information retrieval (...
Answer validation in machine reading comprehension (MRC) consists of
ver...
Transfer learning techniques are particularly useful in NLP tasks where ...
Tax evasion is a serious economic problem for many countries, as it can
...
The synthetic workload is essential and critical to the performance
eval...
We introduce TechQA, a domain-adaptation question answering dataset for ...
With increasing popularity in online learning, a surge of E-learning
pla...
High accuracy video label prediction (classification) models are attribu...
Liver lesion segmentation is a difficult yet critical task for medical i...
Simulation systems have become an essential component in the development...
Deep neural network models have recently draw lots of attention, as it
c...
Recent research has shown that each apnea episode results in a significa...
Continuous and noninvasive monitoring of blood pressure has numerous cli...
We propose a regularized zero-forcing transmit precoding (RZF-TPC) aided...
The ever-increasing demand for broadband Internet access has motivated t...
In recent years, China, the United States and other countries, Google an...
In order to meet the demands of `Internet above the clouds', we propose ...
To improve the efficiency of elderly assessments, an influence-based fas...