4 papers
ConvFormer: Parameter Reduction in Transformer Models for 3D Human Pose Estimation by Leveraging Dynamic Multi-Headed Convolutional Attention
Alec Diaz-Arias, Dmitriy Shin
Recently, fully-transformer architectures have replaced the defacto convolutional architecture for the 3D human pose estimation task. In this paper we propose \textbf{\textit{ConvF…
and -superrigidity results for coinduced groups
Ionut Chifan, Alec Diaz-Arias, Daniel Drimbe
In this paper we explore a generic notion of superrigidity for von Neumann algebras and reduced -algebras associated with countable discrete groups . This…
On the role of depth predictions for 3D human pose estimation
Alec Diaz-Arias, Mitchell Messmore, Dmitriy Shin +1
Following the successful application of deep convolutional neural networks to 2d human pose estimation, the next logical problem to solve is 3d human pose estimation from monocular…
New examples of W and C-superrigid groups
Ionut Chifan, Alec Diaz-Arias, Daniel Drimbe
A group is called -superrigid (resp. -superrigid) if it is completely recognizable from its von Neumann algebra (resp. reduced -algebra ). Devel…