Supervised learning models are challenged by the intrinsic complexities ...
Language-guided human motion synthesis has been a challenging task due t...
DeepFakes have raised serious societal concerns, leading to a great surg...
The prominent progress in generative models has significantly improved t...
Face-swap DeepFake is an emerging AI-based face forgery technique that c...
A critical yet frequently overlooked challenge in the field of deepfake
...
Despite the development of effective deepfake detection models in recent...
Advancements in AI-synthesized human voices have created a growing threa...
Recent advancements in language-image models have led to the development...
Adversarial machine learning (AML) studies the adversarial phenomenon of...
The advancements of AI-synthesized human voices have introduced a growin...
With the rapid development of deep generative models (such as Generative...
The vulnerability of face recognition systems to morphing attacks has po...
The COVID pandemic has led to the wide adoption of online video calls in...
Object Re-IDentification (ReID), one of the most significant problems in...
Recent works have revealed an essential paradigm in designing loss funct...
This paper presents the summary report on our DFGC 2022 competition. The...
With the development of the Generative Adversarial Networks (GANs) and
D...
AI-created face-swap videos, commonly known as Deepfakes, have attracted...
Graph Convolutional Networks (GCNs) have been widely used to model the
h...
Stochastic gradient descent ascent (SGDA) and its variants have been the...
Top-k multi-label learning, which returns the top-k predicted labels fro...
In forming learning objectives, one oftentimes needs to aggregate a set ...
This paper presents a summary of the DFGC 2021 competition. DeepFake
tec...
To promote the developments of object detection, tracking and counting
a...
In recent years, the advent of deep learning-based techniques and the
si...
The recent development of Deep Neural Networks (DNN) has significantly
i...
Recently, backdoor attacks pose a new security threat to the training pr...
Face synthesis is an important problem in computer vision with many
appl...
In forming learning objectives, one oftentimes needs to aggregate a set ...
Sophisticated generative adversary network (GAN) models are now able to
...
In this paper, we study the problem of salient object detection (SOD) fo...
Prior knowledge of face shape and location plays an important role in fa...
The majority of existing human parsing methods formulate the task as sem...
This paper proposes a space-time multi-scale attention network (STANet) ...
In this paper, we describe a fast and light-weight portrait segmentation...
Improving the efficiency of portrait segmentation is of great importance...
AI-synthesized face swapping videos, commonly known as the DeepFakes, ha...
Object detection and counting are related but challenging problems,
espe...
Recent years have seen fast development in synthesizing realistic human ...
Existing hand detection methods usually follow the pipeline of multiple
...
Automatic Check-Out (ACO) receives increased interests in recent years. ...
Generative adversary networks (GANs) have recently led to highly realist...
In this paper, we propose Object-driven Attentive Generative Adversarial...
Training of deep learning models for computer vision requires large imag...
The majority of Multi-Object Tracking (MOT) algorithms based on the
trac...
Video style transfer is a useful component for applications such as augm...
In this paper, we propose a new method to expose AI-generated fake face
...
In this work, we describe a new deep learning based method that can
effe...
Deep neural networks have been proven vulnerable against adversarial
per...