no code implementations • 16 Apr 2024 • Arnab Kumar Mondal, Stefano Alletto, Denis Tome
Understanding human motion from video is essential for a range of applications, including pose estimation, mesh recovery and action recognition.
no code implementations • CVPR 2022 • Salvador Medina, Denis Tome, Carsten Stoll, Mark Tiede, Kevin Munhall, Alexander G. Hauptmann, Iain Matthews
In this work, we introduce a large-scale speech and mocap dataset that focuses on capturing tongue, jaw, and lip motion.
1 code implementation • 2 Nov 2020 • Denis Tome, Thiemo Alldieck, Patrick Peluse, Gerard Pons-Moll, Lourdes Agapito, Hernan Badino, Fernando de la Torre
The quantitative evaluation, on synthetic and real-world datasets, shows that our strategy leads to substantial improvements in accuracy over state of the art egocentric approaches.
no code implementations • ICCV 2019 • Denis Tome, Patrick Peluse, Lourdes Agapito, Hernan Badino
Our quantitative evaluation, both on synthetic and real-world datasets, shows that our strategy leads to substantial improvements in accuracy over state of the art egocentric pose estimation approaches.
Ranked #7 on Egocentric Pose Estimation on GlobalEgoMocap Test Dataset (using extra training data)
1 code implementation • 4 Aug 2018 • Denis Tome, Matteo Toso, Lourdes Agapito, Chris Russell
We propose a CNN-based approach for multi-camera markerless motion capture of the human body.
Ranked #201 on 3D Human Pose Estimation on Human3.6M
11 code implementations • CVPR 2017 • Denis Tome, Chris Russell, Lourdes Agapito
We propose a unified formulation for the problem of 3D human pose estimation from a single raw RGB image that reasons jointly about 2D joint estimation and 3D pose reconstruction to improve both tasks.
Ranked #22 on Weakly-supervised 3D Human Pose Estimation on Human3.6M