no code implementations • 2 Oct 2023 • Haozhe Sun, Isabelle Guyon, Felix Mohr, Hedi Tabia
It has become mainstream in computer vision and other machine learning domains to reuse backbone networks pre-trained on large datasets as preprocessors.
no code implementations • 11 Apr 2023 • Alexandre Heuillet, Ahmad Nasser, Hichem Arioui, Hedi Tabia
In the past few years, Differentiable Neural Architecture Search (DNAS) rapidly imposed itself as the trending approach to automate the discovery of deep neural network architectures.
no code implementations • 20 Feb 2023 • M. Amine Mahmoudi, Aladine Chetouani, Fatma Boufera, Hedi Tabia
This paper investigates the usage of kernel functions at the different layers in a convolutional neural network.
no code implementations • 1 Feb 2023 • Marie-Morgane Paumard, Hedi Tabia, David Picard
Solving jigsaw puzzles requires to grasp the visual features of a sequence of patches and to explore efficiently a solution space that grows exponentially with the sequence length.
1 code implementation • 31 Jan 2023 • Alexandre Heuillet, Hedi Tabia, Hichem Arioui
In this article, we present NASiam, a novel approach that uses for the first time differentiable NAS to improve the multilayer perceptron projector and predictor (encoder/predictor pair) architectures inside siamese-networks-based contrastive learning frameworks (e. g., SimCLR, SimSiam, and MoCo) while preserving the simplicity of previous baselines.
no code implementations • 24 Sep 2021 • Tarek Ben Charrada, Hedi Tabia, Aladine Chetouani, Hamid Laga
It is composed of of (1) a Vertex Generation Network (VGN), which predicts the initial 3D locations of the object's vertices from an input RGB image, (2) a differentiable triangulation layer, which learns in a non-supervised manner, using a novel reinforcement learning algorithm, the best triangulation of the object's vertices, and finally, (3) a hierarchical mesh refinement network that uses graph convolutions to refine the initial mesh.
1 code implementation • 20 Aug 2021 • Alexandre Heuillet, Hedi Tabia, Hichem Arioui, Kamal Youcef-Toumi
This approach is accompanied by a novel metric that measures the distance between architectures inside our custom search space.
no code implementations • 22 Sep 2020 • M. Amine Mahmoudi, Aladine Chetouani, Fatma Boufera, Hedi Tabia
Fully connected layer is an essential component of Convolutional Neural Networks (CNNs), which demonstrates its efficiency in computer vision tasks.
Facial Expression Recognition Facial Expression Recognition (FER)
no code implementations • 4 Sep 2020 • Diogo Luvizon, Hedi Tabia, David Picard
In this paper we propose a highly scalable convolutional neural network, end-to-end trainable, for real-time 3D human pose regression from still RGB images.
Ranked #60 on 3D Human Pose Estimation on MPI-INF-3DHP
no code implementations • 26 May 2020 • Marie-Morgane Paumard, David Picard, Hedi Tabia
We use a two-step method to obtain the reassemblies: 1) a neural network predicts the positions of the fragments despite the gaps between them; 2) a graph that leads to the best reassemblies is made from these predictions.
1 code implementation • 15 Dec 2019 • Diogo C. Luvizon, Hedi Tabia, David Picard
In this work, we propose a multi-task framework for jointly estimating 2D or 3D human poses from monocular color images and classifying human actions from video sequences.
Ranked #142 on 3D Human Pose Estimation on Human3.6M
1 code implementation • 21 Nov 2019 • Diogo C. Luvizon, Hedi Tabia, David Picard
3D human pose estimation is frequently seen as the task of estimating 3D poses relative to the root body joint.
Ranked #69 on 3D Human Pose Estimation on Human3.6M
no code implementations • ECCV 2018 • Marie-Morgane Paumard, David Picard, Hedi Tabia
This paper addresses the problem of reassembling images from disjointed fragments.
no code implementations • 5 Jul 2018 • Marie-Morgane Paumard, David Picard, Hedi Tabia
Archaeologists are in dire need of automated object reconstruction methods.
2 code implementations • CVPR 2018 • Diogo C. Luvizon, David Picard, Hedi Tabia
Action recognition and human pose estimation are closely related but both problems are generally handled as distinct tasks in the literature.
Ranked #1 on Action Recognition In Videos on NTU RGB+D
1 code implementation • 6 Oct 2017 • Diogo C. Luvizon, Hedi Tabia, David Picard
In this paper, we propose an end-to-end trainable regression approach for human pose estimation from still images.
Ranked #11 on Pose Estimation on Leeds Sports Poses
no code implementations • CVPR 2014 • Hedi Tabia, Hamid Laga, David Picard, Philippe-Henri Gosselin
We evaluate the performance of the proposed Bag of Covariance Matrices framework on 3D shape matching and retrieval applications and demonstrate its superiority compared to descriptor-based techniques.