1 code implementation • 15 Apr 2024 • Omar Ikne, Benjamin Allaert, Ioan Marius Bilasco, Hazem Wannous
Considering the motion induced by head variation as noise and the motion induced by facial expression as the relevant information, our model is trained to filter out the noisy motion in order to retain only the motion related to facial expression.
Facial Expression Recognition Facial Expression Recognition (FER)
no code implementations • 22 Sep 2023 • Mireille El-Assal, Pierre Tirilly, Ioan Marius Bilasco
In this work, we use CSNNs trained in an unsupervised manner with the Spike Timing-Dependent Plasticity (STDP) rule, and we introduce, for the first time, Spiking Separated Spatial and Temporal Convolutions (S3TCs) for the sake of reducing the number of parameters required for video analysis.
no code implementations • 4 Aug 2023 • Gaspard Goupy, Pierre Tirilly, Ioan Marius Bilasco
Then, we introduce a training architecture called Paired Competing Neurons (PCN) to further enhance the learning capabilities of our classification layer trained with S2-STDP.
no code implementations • 23 Jun 2023 • Mireille El-Assal, Pierre Tirilly, Ioan Marius Bilasco
Implementing this model with unsupervised STDP-based CSNNs allows us to further study the performance of these networks with video analysis.
no code implementations • 3 Mar 2023 • Amira Guesmi, Ioan Marius Bilasco, Muhammad Shafique, Ihsen Alouani
Physical adversarial attacks pose a significant practical threat as it deceives deep learning systems operating in the real world by producing prominent and maliciously designed physical perturbations.
no code implementations • 26 May 2022 • Mireille El-Assal, Pierre Tirilly, Ioan Marius Bilasco
We compare the performance of this model to those of a 2D STDP-based SNN when challenged with the KTH and Weizmann datasets.
no code implementations • 24 Dec 2020 • Delphine Poux, Benjamin Allaert, Nacim Ihaddadene, Ioan Marius Bilasco, Chaabane Djeraba, Mohammed Bennamoun
To handle occlusions, solutions based on the reconstruction of the occluded part of the face have been proposed.
Dynamic Facial Expression Recognition Facial Expression Recognition +2
no code implementations • 24 Feb 2020 • Pierre Falez, Pierre Tirilly, Ioan Marius Bilasco
Experiments on CIFAR-10 show that whitening allows STDP to learn visual features that are closer to the ones learned with standard neural networks, with a significantly increased classification performance as compared to DoG filtering.
no code implementations • 26 May 2019 • Romain Belmonte, Benjamin Allaert, Pierre Tirilly, Ioan Marius Bilasco, Chaabane Djeraba, Nicu Sebe
Although facial landmark localization (FLL) approaches are becoming increasingly accurate for characterizing facial regions, one question remains unanswered: what is the impact of these approaches on subsequent related tasks?
no code implementations • 30 Apr 2019 • Delphine Poux, Benjamin Allaert, Jose Mennesson, Nacim Ihaddadene, Ioan Marius Bilasco, Chaabane Djeraba
The main innovation brought by this contribution consists in exploiting the specificities of facial movement propagation for recognizing expressions in presence of important occlusions.
no code implementations • 25 Apr 2019 • Benjamin Allaert, Isaac Ronald Ward, Ioan Marius Bilasco, Chaabane Djeraba, Mohammed Bennamoun
Optical flow techniques are becoming increasingly performant and robust when estimating motion in a scene, but their performance has yet to be proven in the area of facial expression recognition.
no code implementations • 3 Apr 2019 • Pierre Falez, Pierre Tirilly, Ioan Marius Bilasco, Philippe Devienne, Pierre Boulet
Spiking neural networks (SNNs) are good candidates to produce ultra-energy-efficient hardware.
no code implementations • 14 Jan 2019 • Pierre Falez, Pierre Tirilly, Ioan Marius Bilasco, Philippe Devienne, Pierre Boulet
Spiking neural networks (SNNs) equipped with latency coding and spike-timing dependent plasticity rules offer an alternative to solve the data and energy bottlenecks of standard computer vision approaches: they can learn visual features without supervision and can be implemented by ultra-low power hardware architectures.