AIGC (AI-Generated Content) has achieved tremendous success in many
appl...
Watermarking is a crucial tool for safeguarding copyrights and can serve...
In this paper, we investigate the adversarial robustness of vision
trans...
The ability to scene understanding in adverse visual conditions, e.g.,
n...
Large Language Models (LLMs) can generate texts that carry the risk of
v...
LLMs now exhibit human-like skills in various fields, leading to worries...
With basic Semi-Supervised Object Detection (SSOD) techniques, one-stage...
We present Diversity-Aware Meta Visual Prompting (DAM-VP), an efficient ...
Nowadays, social media has become the preferred communication platform f...
Event cameras are bio-inspired sensors that capture the per-pixel intens...
Nowadays, two-dimensional (2D) barcodes have been widely used in various...
In the past few years, the widespread use of 3D printing technology enab...
With the rapid development of classical and quantum machine learning, a ...
Recent studies have shown that CLIP has achieved remarkable success in
p...
Copy-Paste is a simple and effective data augmentation strategy for inst...
Audio watermarking is widely used for leaking source tracing. The robust...
Deep 3D point cloud models are sensitive to adversarial attacks, which p...
Whereas cryptography easily arouses attacks by means of encrypting a sec...
Notwithstanding the prominent performance achieved in various applicatio...
This paper presents a simple yet effective framework MaskCLIP, which
inc...
We propose bootstrapped masked autoencoders (BootMAE), a new approach fo...
With recent advances in machine learning, researchers are now able to so...
Digital watermarking has been widely studied for the protection of
intel...
Face privacy-preserving is one of the hotspots that arises dramatic inte...
Adversary and invisibility are two fundamental but conflict characters o...
In this work we propose Identity Consistency Transformer, a novel face
f...
The fast evolution and widespread of deepfake techniques in real-world
s...
Text content created by humans or language models is often stolen or mis...
Hair editing is an interesting and challenging problem in computer visio...
This paper explores a better codebook for BERT pre-training of vision
tr...
As an effective method for intellectual property (IP) protection, model
...
Nowadays, people are sharing their pictures on online social networks (O...
Robust 3D mesh watermarking is a traditional research topic in computer
...
Based on the powerful feature extraction ability of deep learning
archit...
Recent research shows deep neural networks are vulnerable to different t...
The intellectual property (IP) of Deep neural networks (DNNs) can be eas...
We present CSWin Transformer, an efficient and effective Transformer-bas...
Three-dimensional (3-D) meshes are commonly used to represent virtual
su...
This paper studies the problem of StyleGAN inversion, which plays an
ess...
Deep convolutional neural networks have made outstanding contributions i...
Real-world data usually have high dimensionality and it is important to
...
Despite the tremendous success, deep neural networks are exposed to seri...
Face forgery by deepfake is widely spread over the internet and has rais...
The remarkable success in face forgery techniques has received considera...
Data hiding is the art of concealing messages with limited perceptual
ch...
Deep neural networks have been proved that they are vulnerable to advers...
Image matting is a fundamental and challenging problem in computer visio...
DeepFake detection has so far been dominated by “artifact-driven” method...
Deep neural networks have made tremendous progress in 3D point-cloud
rec...
Despite tremendous success in many application scenarios, deep learning ...