54 citations · 87 across the 2 of their papers we have counts for
4 papers · 1 filter
Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformers
Angel Martínez-González, Michael Villamizar, Jean-Marc Odobez
We propose to leverage Transformer architectures for non-autoregressive human motion prediction. Our approach decodes elements in parallel from a query sequence, instead of conditi…
Residual Pose: A Decoupled Approach for Depth-based 3D Human Pose Estimation
Angel Martínez-González, Michael Villamizar, Olivier Canévet +1
We propose to leverage recent advances in reliable 2D pose estimation with Convolutional Neural Networks (CNN) to estimate the 3D pose of people from depth images in multi-person H…
Efficient Convolutional Neural Networks for Depth-Based Multi-Person Pose Estimation
Angel Martínez-González, Michael Villamizar, Olivier Canévet +1
Achieving robust multi-person 2D body landmark localization and pose estimation is essential for human behavior and interaction understanding as encountered for instance in HRI set…
Real-time Convolutional Networks for Depth-based Human Pose Estimation
Angel Martínez-González, Michael Villamizar, Olivier Canévet +1
We propose to combine recent Convolutional Neural Networks (CNN) models with depth imaging to obtain a reliable and fast multi-person pose estimation algorithm applicable to Human…