3 papers
stat.ML2023
Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis
Victor Letzelter, Mathieu Fontaine, Mickaël Chen +3
We introduce Resilient Multiple Choice Learning (rMCL), an extension of the MCL approach for conditional distribution estimation in regression settings where multiple targets may b…
cs.CV2023
A Pytorch Reproduction of Masked Generative Image Transformer
Victor Besnier, Mickael Chen
In this technical report, we present a reproduction of MaskGIT: Masked Generative Image Transformer, using PyTorch. The approach involves leveraging a masked bidirectional transfor…
cs.CV2023
DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusion
Cédric Rommel, Eduardo Valle, Mickaël Chen +4
We present an innovative approach to 3D Human Pose Estimation (3D-HPE) by integrating cutting-edge diffusion models, which have revolutionized diverse fields, but are relatively un…