Vision transformers have emerged as powerful tools for many computer vis...
Given enough annotated training data, 3D human pose estimation models ca...
While road obstacle detection techniques have become increasingly effect...
Supervised approaches to 3D pose estimation from single images are remar...
The Skinned Multi-Person Linear (SMPL) model can represent a human body ...
Relating animal behaviors to brain activity is a fundamental goal in
neu...
A fundamental goal in neuroscience is to understand the relationship bet...
State-of-the-art semantic or instance segmentation deep neural networks
...
Vehicles can encounter a myriad of obstacles on the road, and it is not
...
In this paper, we introduce an unsupervised feature extraction method th...
We present a lightweight solution to recover 3D pose from multi-view ima...
Model quantization is leveraged to reduce the memory consumption and the...
In this paper, we explore new approaches to combining information encode...
This paper discusses how distribution matching losses, such as those use...
We present an unsupervised approach for learning to estimate three
dimen...
In this paper, we strive to answer two questions: What is the current st...
We present two techniques to improve landmark localization from partiall...
In this work, we investigate a novel training procedure to learn a gener...
Theano is a Python library that allows to define, optimize, and evaluate...
We present techniques for improving performance driven facial animation,...
Deep neural networks with alternating convolutional, max-pooling and
dec...