We propose a novel task for generating 3D dance movements that simultane...
We present OmniAvatar, a novel geometry-guided 3D head synthesis model
t...
While substantial progresses have been made in automated 2D portrait
sty...
Unsupervised generation of clothed virtual humans with various appearanc...
Class Incremental Learning (CIL) aims at learning a multi-class classifi...
Visual recognition has been dominated by convolutional neural networks (...
In this paper, we present Vision Permutator, a conceptually simple and d...
Modern pre-trained language models are mostly built upon backbones stack...
This paper provides a strong baseline for vision transformers on the Ima...
Pre-trained language models like BERT and its variants have recently ach...
Training a neural network model that can quickly adapt to a new task is
...
Recent powerful pre-trained language models have achieved remarkable
per...
3D face reconstruction from a single 2D image is a challenging problem w...