Understanding 3d human interactions is fundamental for fine-grained scen...
Autonomous driving is an exciting new industry, posing important researc...
We present PhoMoH, a neural network methodology to construct generative
...
We introduce Structured 3D Features, a model based on a novel implicit 3...
We present BlazePose GHUM Holistic, a lightweight neural network pipelin...
We present PHORHUM, a novel, end-to-end trainable, deep neural network
m...
Advances in the state of the art for 3d human sensing are currently limi...
We present THUNDR, a transformer-based deep neural network methodology t...
Monocular estimation of three dimensional human self-contact is fundamen...
We present deep neural network methodology to reconstruct the 3d pose an...
Generating good quality and geometrically plausible synthetic images of
...
We propose a deep multitask architecture for fully automatic 2d and 3d
h...
Automatic video captioning is challenging due to the complex interaction...