Deep neural networks (DNNs) have been proven extremely susceptible to
ad...
Multi-task learning (MTL), a learning paradigm to learn multiple related...
Due to limited camera capacities, digital images usually have a narrower...
Conditional diffusion models have demonstrated impressive performance in...
Text-to-image diffusion models have advanced towards more controllable
g...
Generalizable neural surface reconstruction techniques have attracted gr...
This work explores the use of 3D generative models to synthesize trainin...
Neural implicit surface learning has shown significant progress in multi...
Deep neural networks suffer from significant performance deterioration w...
In this work, we study the continual semantic segmentation problem, wher...
In this paper, we present a novel approach to synthesize realistic image...
Real-world data often exhibit imbalanced distributions, where certain ta...
Traditional convolution-based generative adversarial networks synthesize...
Blind inpainting is a task to automatically complete visual contents wit...
Digital face manipulation has become a popular and fascinating way to to...
We propose a principled convolutional neural pyramid (CNP) framework for...
The challenge of person re-identification (re-id) is to match individual...
Feature representation and metric learning are two critical components i...