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...
Textual adversarial attacks can discover models' weaknesses by adding
se...
Large language models (LLMs) have recently shown great potential for
in-...
In this paper, we propose a joint generative and contrastive representat...
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...
Adversarial training has been demonstrated to be the most effective appr...
Scene text image super-resolution (STISR) aims to simultaneously increas...
Out-Of-Distribution (OOD) detection has received broad attention over th...
Contrastive Language-Image Pre-trained (CLIP) models have zero-shot abil...
Conditioned diffusion models have demonstrated state-of-the-art text-to-...
Despite of the superb performance on a wide range of tasks, pre-trained
...
Capturing emotions within a conversation plays an essential role in mode...
Out-of-distribution (OOD) detection is a critical task for ensuring the
...
Adversarial Training (AT), which is commonly accepted as one of the most...
Building a deep learning model for a Question-Answering (QA) task requir...
Due to the vulnerability of deep neural networks (DNNs) to adversarial
e...
In multimodal tasks, we find that the importance of text and image modal...
In fine-grained image recognition (FGIR), the localization and amplifica...
Recent advances on Vision Transformers (ViT) have shown that
self-attent...
We study the query-based attack against image retrieval to evaluate its
...
The remarkable success in face forgery techniques has received considera...
Despite that deep neural networks (DNNs) have achieved enormous success ...
Intellectual property protection(IPP) have received more and more attent...
Adversarial attack is a technique for deceiving Machine Learning (ML) mo...
Purpose: To develop a convolutional neural network (CNN) solution for ro...
With the rapid development of facial manipulation techniques, face forge...
We study the problem of deep recall model in industrial web search, whic...
Adversarial examples are perturbed inputs which can cause a serious thre...
Localizing thoracic diseases on chest X-ray plays a critical role in cli...
This paper strives to learn fine-grained fashion similarity. In this
sim...
With the success of deep neural networks, Neural Architecture Search (NA...
Few-shot image classification requires the classifier to robustly cope w...
Deep neural networks have been shown to be vulnerable to adversarial
exa...
Deep Neural Networks (DNNs) are known to be vulnerable to the maliciousl...
Recent work has demonstrated that neural networks are vulnerable to
adve...
Few-shot image classification aims to classify unseen classes with limit...
Recent development of quantitative myocardial blood flow (MBF) mapping a...
Quantification of myocardial perfusion has the potential to improve dete...
Graph Convolutional Network (GCN) has attracted intensive interests rece...
High accuracy video label prediction (classification) models are attribu...
The task of Language-Based Image Editing (LBIE) aims at generating a tar...
Deep neural network models have recently draw lots of attention, as it
c...