Search Results for author: Aladine Chetouani

Found 25 papers, 5 papers with code

Insights into Classifying and Mitigating LLMs' Hallucinations

no code implementations14 Nov 2023 Alessandro Bruno, Pier Luigi Mazzeo, Aladine Chetouani, Marouane Tliba, Mohamed Amine Kerkouri

The widespread adoption of large language models (LLMs) across diverse AI applications is proof of the outstanding achievements obtained in several tasks, such as text mining, text generation, and question answering.

Hallucination Machine Translation +2

Transformer with Selective Shuffled Position Embedding and Key-Patch Exchange Strategy for Early Detection of Knee Osteoarthritis

no code implementations17 Apr 2023 Zhe Wang, Aladine Chetouani, Mohamed Jarraya, Didier Hans, Rachid Jennane

In this paper, we propose a novel approach based on the Vision Transformer (ViT) model with original Selective Shuffled Position Embedding (SSPE) and key-patch exchange strategies to obtain different input sequences as a method of data augmentation for early detection of KOA (KL-0 vs KL-2).

Data Augmentation Position +1

A Confident Labelling Strategy Based on Deep Learning for Improving Early Detection of Knee OsteoArthritis

no code implementations23 Mar 2023 Zhe Wang, Aladine Chetouani, Rachid Jennane

Knee OsteoArthritis (KOA) is a prevalent musculoskeletal disorder that causes decreased mobility in seniors.

Quality evaluation of point clouds: a novel no-reference approach using transformer-based architecture

no code implementations15 Mar 2023 Marouane Tliba, Aladine Chetouani, Giuseppe Valenzise, Frederic Dufaux

With the increased interest in immersive experiences, point cloud came to birth and was widely adopted as the first choice to represent 3D media.

Key-Exchange Convolutional Auto-Encoder for Data Augmentation in Early Knee OsteoArthritis Classification

no code implementations26 Feb 2023 Zhe Wang, Aladine Chetouani, Rachid Jennane

In this paper, we propose a learning model based on the convolutional Auto-Encoder and a hybrid loss strategy to generate new data for early KOA (KL-0 vs KL-2) diagnosis.

Data Augmentation valid

Kernel function impact on convolutional neural networks

no code implementations20 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.

Objective quality assessment of medical images and videos: Review and challenges

no code implementations14 Dec 2022 Rafael Rodrigues, Lucie Lévêque, Jesús Gutiérrez, Houda Jebbari, Meriem Outtas, Lu Zhang, Aladine Chetouani, Shaymaa Al-Juboori, Maria Martini, Antonio M. G. Pinheiro

Quality assessment is a key element for the evaluation of hardware and software involved in image and video acquisition, processing, and visualization.

PCQA-GRAPHPOINT: Efficients Deep-Based Graph Metric For Point Cloud Quality Assessment

no code implementations4 Nov 2022 Marouane Tliba, Aladine Chetouani, Giuseppe Valenzise, Frederic Dufaux

Following the advent of immersive technologies and the increasing interest in representing interactive geometrical format, 3D Point Clouds (PC) have emerged as a promising solution and effective means to display 3D visual information.

Point Cloud Quality Assessment

End-to-end deep multi-score model for No-reference stereoscopic image quality assessment

1 code implementation ICIP2022 2022 Oussama Messai, Aladine Chetouani

Unlike existing stereoscopic IQA measures which focus mainly on estimating a global human score, we suggest incorporating left, right, and stereoscopic objective scores to extract the corresponding properties of each view, and so forth estimating stereoscopic image quality without reference.

Stereoscopic image quality assessment

A domain adaptive deep learning solution for scanpath prediction of paintings

no code implementations22 Sep 2022 Mohamed Amine Kerkouri, Marouane Tliba, Aladine Chetouani, Alessandro Bruno

Cultural heritage understanding and preservation is an important issue for society as it represents a fundamental aspect of its identity.

Scanpath prediction

Self Supervised Scanpath Prediction Framework for Painting Images

no code implementations CVPR 2022 Marouane Tliba, Mohamed Amine Kerkouri, Aladine Chetouani, Alessandro Bruno

In our paper, we propose a novel strategy to learn distortion invariant latent representation from painting pictures for visual attention modelling downstream task.

Scanpath prediction

SalyPath360: Saliency and Scanpath Prediction Framework for Omnidirectional Images

no code implementations1 Jan 2022 Mohamed Amine Kerkouri, Marouane Tliba, Aladine Chetouani, Mohamed Sayeh

The key setup of our architecture is the simultaneous prediction of the saliency map and a corresponding scanpath for a given stimulus.

Scanpath prediction

A Simple and efficient deep Scanpath Prediction

no code implementations8 Dec 2021 Mohamed Amine Kerkouri, Aladine Chetouani

Visual scanpath is the sequence of fixation points that the human gaze travels while observing an image, and its prediction helps in modeling the visual attention of an image.

Scanpath prediction

Learnable Triangulation for Deep Learning-based 3D Reconstruction of Objects of Arbitrary Topology from Single RGB Images

no code implementations24 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.

3D Object Reconstruction 3D Reconstruction +2

A deep perceptual metric for 3D point clouds

1 code implementation25 Feb 2021 Maurice Quach, Aladine Chetouani, Giuseppe Valenzise, Frederic Dufaux

In addition, we propose a novel truncated distance field voxel grid representation and find that it leads to sparser latent spaces and loss functions that are more correlated with perceived visual quality compared to a binary representation.

Kernelized dense layers for facial expression recognition

no code implementations22 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)

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