Egocentric, multi-modal data as available on future augmented reality (A...
Communication lays the foundation for cooperation in human society and i...
While current face animation methods can manipulate expressions individu...
Talking-head video editing aims to efficiently insert, delete, and subst...
Artistic style transfer aims to transfer the style of an artwork to a
ph...
Efficiently generating a free-style 3D portrait with high quality and
co...
The privacy and security of face data on social media are facing
unprece...
The congestion game is a powerful model that encompasses a range of
engi...
We introduce a transformation framework that can be utilized to develop
...
Scaling to arbitrarily large bundle adjustment problems requires data an...
Detecting maliciously falsified facial images and videos has attracted
e...
Text-driven image manipulation remains challenging in training or infere...
This work presents RiDDLE, short for Reversible and Diversified
De-ident...
Robust, high-precision global localization is fundamental to a wide rang...
GAN inversion has been exploited in many face manipulation tasks, but 2D...
Exemplar-based image translation refers to the task of generating images...
Recently 3D-aware GAN methods with neural radiance field have developed
...
Deep-learning based face-swap videos, also known as deep fakes, are beco...
Reinforcement learning (RL) has exceeded human performance in many synth...
We present Theseus, an efficient application-agnostic open source librar...
This paper presents the summary report on our DFGC 2022 competition. The...
This paper investigates the problem of regret minimization in linear
tim...
Adversarial attacks seriously threaten the high accuracy of face
anti-sp...
Many organizations have access to abundant data but lack the computation...
The phenomenon of data distribution evolving over time has been observed...
We present iSDF, a continual learning system for real-time signed distan...
When implementing Markov Chain Monte Carlo (MCMC) algorithms, perturbati...
We study the convergence of the actor-critic algorithm with nonlinear
fu...
In reinforcement learning (RL), offline learning decoupled learning from...
Temporal difference (TD) learning is a widely used method to evaluate
po...
In recent years, facial makeup transfer has attracted growing attention ...
Motivated by the common strategic activities in crowdsourcing labeling, ...
With the identity information in face data more closely related to perso...
This paper presents a summary of the DFGC 2021 competition. DeepFake
tec...
Deep neural networks have shown their vulnerability to adversarial attac...
Privacy protection on human biological information has drawn increasing
...
This paper studies differential privacy (DP) and local
differential priv...
Maliciously-manipulated images or videos - so-called deep fakes - especi...
In recent years, virtual makeup applications have become more and more
p...
Simultaneous localization and mapping (SLAM) is a crucial functionality ...
We study the problem of combinatorial multi-armed bandits (CMAB) under
s...
Images synthesized by powerful generative adversarial network (GAN) base...
We study a cooperative multi-agent multi-armed bandits with M agents and...
Pose-guided person image generation usually involves using paired
source...
In this work we propose a tightly-coupled Extended Kalman Filter framewo...
Langevin diffusion is a powerful method for nonconvex optimization, whic...
Langevin diffusion (LD) is one of the main workhorses for sampling probl...
Learning to reconstruct 3D shapes using 2D images is an active research
...
Gait recognition has a broad application in social security due to its
a...
Gradient descent (GD) is known to converge quickly for convex objective
...