2 citations · 3 across the 26 of their papers we have counts for
27 papers
HalluTruthQA-4K: A Fine-Grained Corpus and Annotation Process for Arabic Hallucination Detection and Truth Verification
Salah Eddine Bekhouche, Abdessalam Bouchekif, Hichem Telli +2
Large language models can generate fluent Arabic answers while introducing factual errors that are difficult to identify and verify. Existing Arabic hallucination resources often a…
HalluTruthQA: A Fine-Grained Benchmark for Hallucination Detection, Localization, and Explanation in Arabic Question Answering
Abdessalam Bouchekif, Mohammed-En-Nadhir Zighem, Salah Eddine Bekhouche +9
Large language models (LLMs) can generate fluent Arabic answers, yet factual errors remain difficult to detect, localize, explain, and verify. Existing hallucination benchmarks oft…
AffectFlow-DINO: Uncertainty-Aware Multi-Task Affect Estimation via Conditional Rectified Flow
Salah Eddine Bekhouche, Abdellah Zakaria Sellam, Fadi Dornaika +1
We present \textbf{AffectFlow-DINO}, a multi-task learning system for the 11th ABAW challenge that extends a standard deterministic architecture with a conditional rectified-flow h…
Can Visual Mamba Improve AI-Generated Image Detection? An In-Depth Investigation
Mamadou Keita, Wassim Hamidouche, Hessen Bougueffa Eutamene +3
In recent years, computer vision has witnessed remarkable progress, fueled by the development of innovative architectures such as Convolutional Neural Networks (CNNs), Generative A…
SPARK-IL: Spectral Retrieval-Augmented RAG for Knowledge-driven Deepfake Detection via Incremental Learning
Hessen Bougueffa Eutamene, Abdellah Zakaria Sellam, Abdelmalik Taleb-Ahmed +1
Detecting AI-generated images remains a significant challenge because detectors trained on specific generators often fail to generalize to unseen models; however, while pixel-level…
RF-HiT: Rectified Flow Hierarchical Transformer for General Medical Image Segmentation
Ahmed Marouane Djouamaa, Abir Belaala, Abdellah Zakaria Sellam +3
Accurate medical image segmentation requires both long-range contextual reasoning and precise boundary delineation, a task where existing transformer- and diffusion-based paradigms…
Conflict-Aware Multimodal Fusion for Ambivalence and Hesitancy Recognition
Salah Eddine Bekhouche, Hichem Telli, Azeddine Benlamoudi +3
Ambivalence and hesitancy (A/H) are subtle affective states where a person shows conflicting signals through different channels -- saying one thing while their face or voice tells…
Decoding Matters: Efficient Mamba-Based Decoder with Distribution-Aware Deep Supervision for Medical Image Segmentation
Fares Bougourzi, Fadi Dornaika, Abdenour Hadid
Deep learning has achieved remarkable success in medical image segmentation, often reaching expert-level accuracy in delineating tumors and tissues. However, most existing approach…
VP-Hype: A Hybrid Mamba-Transformer Framework with Visual-Textual Prompting for Hyperspectral Image Classification
Abdellah Zakaria Sellam, Fadi Abdeladhim Zidi, Salah Eddine Bekhouche +4
Accurate classification of hyperspectral imagery (HSI) is often frustrated by the tension between high-dimensional spectral data and the extreme scarcity of labeled training sample…
VLM-PAR: A Vision Language Model for Pedestrian Attribute Recognition
Abdellah Zakaria Sellam, Salah Eddine Bekhouche, Fadi Dornaika +2
Pedestrian Attribute Recognition (PAR) involves predicting fine-grained attributes such as clothing color, gender, and accessories from pedestrian imagery, yet is hindered by sever…
C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Car Damage Detection
Abdellah Zakaria Sellam, Ilyes Benaissa, Salah Eddine Bekhouche +3
Fine-grained object detection in challenging visual domains, such as vehicle damage assessment, presents a formidable challenge even for human experts to resolve reliably. While Di…
CVPD at QIAS 2025 Shared Task: An Efficient Encoder-Based Approach for Islamic Inheritance Reasoning
Salah Eddine Bekhouche, Abdellah Zakaria Sellam, Hichem Telli +2
Islamic inheritance law (Ilm al-Mawarith) requires precise identification of heirs and calculation of shares, which poses a challenge for AI. In this paper, we present a lightweigh…
RAVID: Retrieval-Augmented Visual Detection: A Knowledge-Driven Approach for AI-Generated Image Identification
Mamadou Keita, Wassim Hamidouche, Hessen Bougueffa Eutamene +2
In this paper, we introduce RAVID, the first framework for AI-generated image detection that leverages visual retrieval-augmented generation (RAG). While RAG methods have shown pro…
Enhanced Arabic Text Retrieval with Attentive Relevance Scoring
Salah Eddine Bekhouche, Azeddine Benlamoudi, Yazid Bounab +2
Arabic poses a particular challenge for natural language processing (NLP) and information retrieval (IR) due to its complex morphology, optional diacritics and the coexistence of M…
SAViL-Det: Semantic-Aware Vision-Language Model for Multi-Script Text Detection
Mohammed-En-Nadhir Zighem, Abdenour Hadid
Detecting text in natural scenes remains challenging, particularly for diverse scripts and arbitrarily shaped instances where visual cues alone are often insufficient. Existing met…
SegDT: A Diffusion Transformer-Based Segmentation Model for Medical Imaging
Salah Eddine Bekhouche, Gaby Maroun, Fadi Dornaika +1
Medical image segmentation is crucial for many healthcare tasks, including disease diagnosis and treatment planning. One key area is the segmentation of skin lesions, which is vita…
Recent Advances in Medical Imaging Segmentation: A Survey
Fares Bougourzi, Abdenour Hadid
Medical imaging is a cornerstone of modern healthcare, driving advancements in diagnosis, treatment planning, and patient care. Among its various tasks, segmentation remains one of…
DeeCLIP: A Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images
Mamadou Keita, Wassim Hamidouche, Hessen Bougueffa Eutamene +2
This paper introduces DeeCLIP, a novel framework for detecting AI-generated images using CLIP-ViT and fusion learning. Despite significant advancements in generative models capable…
PE-CLIP: A Parameter-Efficient Fine-Tuning of Vision Language Models for Dynamic Facial Expression Recognition
Ibtissam Saadi, Abdenour Hadid, Douglas W. Cunningham +2
Vision-Language Models (VLMs) like CLIP offer promising solutions for Dynamic Facial Expression Recognition (DFER) but face challenges such as inefficient full fine-tuning, high co…
Shuffle Vision Transformer: Lightweight, Fast and Efficient Recognition of Driver Facial Expression
Ibtissam Saadi, Douglas W. Cunningham, Taleb-ahmed Abdelmalik +2
Existing methods for driver facial expression recognition (DFER) are often computationally intensive, rendering them unsuitable for real-time applications. In this work, we introdu…
TG-PhyNN: An Enhanced Physically-Aware Graph Neural Network framework for forecasting Spatio-Temporal Data
Zakaria Elabid, Lena Sasal, Daniel Busby +1
Accurately forecasting dynamic processes on graphs, such as traffic flow or disease spread, remains a challenge. While Graph Neural Networks (GNNs) excel at modeling and forecastin…
FIDAVL: Fake Image Detection and Attribution using Vision-Language Model
Mamadou Keita, Wassim Hamidouche, Hessen Bougueffa Eutamene +2
We introduce FIDAVL: Fake Image Detection and Attribution using a Vision-Language Model. FIDAVL is a novel and efficient mul-titask approach inspired by the synergies between visio…
TempoKGAT: A Novel Graph Attention Network Approach for Temporal Graph Analysis
Lena Sasal, Daniel Busby, Abdenour Hadid
Graph neural networks (GNN) have shown significant capabilities in handling structured data, yet their application to dynamic, temporal data remains limited. This paper presents a…
Bi-LORA: A Vision-Language Approach for Synthetic Image Detection
Mamadou Keita, Wassim Hamidouche, Hessen Bougueffa Eutamene +2
Advancements in deep image synthesis techniques, such as generative adversarial networks (GANs) and diffusion models (DMs), have ushered in an era of generating highly realistic im…