Search Results for author: Kévin Bailly

Found 8 papers, 0 papers with code

Multi-Task Transformer with uncertainty modelling for Face Based Affective Computing

no code implementations6 Aug 2022 Gauthier Tallec, Jules Bonnard, Arnaud Dapogny, Kévin Bailly

From a learning point of view we use an uncertainty weighted loss for modelling the difference of stochasticity between the three tasks annotations.

Privileged Attribution Constrained Deep Networks for Facial Expression Recognition

no code implementations24 Mar 2022 Jules Bonnard, Arnaud Dapogny, Ferdinand Dhombres, Kévin Bailly

Facial Expression Recognition (FER) is crucial in many research domains because it enables machines to better understand human behaviours.

Facial Expression Recognition Facial Expression Recognition (FER)

DeeSCo: Deep heterogeneous ensemble with Stochastic Combinatory loss for gaze estimation

no code implementations15 Apr 2020 Edouard Yvinec, Arnaud Dapogny, Kévin Bailly

In this paper, we introduce a deep, end-to-end trainable ensemble of heatmap-based weak predictors for 2D/3D gaze estimation.

Gaze Estimation

DeCaFA: Deep Convolutional Cascade for Face Alignment In The Wild

no code implementations ICCV 2019 Arnaud Dapogny, Kévin Bailly, Matthieu Cord

Face Alignment is an active computer vision domain, that consists in localizing a number of facial landmarks that vary across datasets.

Face Alignment

Face Alignment with Cascaded Semi-Parametric Deep Greedy Neural Forests

no code implementations5 Mar 2017 Arnaud Dapogny, Kévin Bailly, Séverine Dubuisson

GNF appears as an ideal regressor for face alignment, as it combines differentiability, high expressivity and fast evaluation runtime.

Face Alignment

Confidence-Weighted Local Expression Predictions for Occlusion Handling in Expression Recognition and Action Unit detection

no code implementations21 Jul 2016 Arnaud Dapogny, Kévin Bailly, Séverine Dubuisson

Furthermore, labelling expressions is a time-consuming process that is prone to subjectivity, thus the variability may not be fully covered by the training data.

Action Unit Detection Descriptive +3

Dynamic Pose-Robust Facial Expression Recognition by Multi-View Pairwise Conditional Random Forests

no code implementations21 Jul 2016 Arnaud Dapogny, Kévin Bailly, Séverine Dubuisson

As such, our approach appears as a natural extension of Random Forests for learning spatio-temporal patterns, potentially from multiple viewpoints.

Facial Expression Recognition Facial Expression Recognition (FER) +1

Cannot find the paper you are looking for? You can Submit a new open access paper.