Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Kaïs OuniSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works69 from public data
- Drone Deep Reinforcement Learning: A Review309
The state of the art of one subset of these algorithms: the deep reinforcement learning (DRL) techniques, designed to ensure stable and smooth UAV navigation by training computer-simulated environments are described.
- Car Detection using Unmanned Aerial Vehicles: Comparison between Faster R-CNN and YOLOv3305
This paper investigates the performance of two state-of-the art CNN algorithms, namely Faster R-CNN and YOLOv3, in the context of car detection from aerial images, and demonstrates in this paper that Yolov3 outperforms FasterR-CNN in sensitivity and processing time, although they are comparable in the precision metric.
- Deep Learning Approach for Car Detection in UAV Imagery296
An automatic solution to the problem of detecting and counting cars in unmanned aerial vehicle (UAV) images that outperforms the state-of-the-art methods, both in terms of accuracy and computational time.
- Vision Transformers in Image Restoration: A Survey148
It is noted that incorporating ViT in the new architectures for image restoration is becoming a rule, due to some advantages compared to CNN, such as better efficiency, especially when more data are fed to the network, robustness in feature extraction, and a better feature learning approach that sees better the variances and characteristics of the input.
- Convolutional Neural Networks for Electrocardiogram Classification123
This approach relies on a deep convolutional neural network pretrained on an auxiliary domain with very large labelled images coupled with an additional network composed of fully connected layers to achieve better results for the detection of ventricular ectopic beats and supraventricular ectopy beats compared to state-of-the-art methods.
- Vehicle Detection from Aerial Images Using Deep Learning: A Comparative Study104
This paper assesses the performance of three state-of-the-art CNN algorithms, namely Faster R-CNN, which is the most popular region-based algorithm, as well as Y OLOv3 and YOLOv4, which are known to be the fastest detection algorithms.
- A Novel Hybrid Machine Learning Classification for the Detection of Bruxism Patients Using Physiological Signals73
The results show that more accurate bruxism detection is achieved by exploiting the electroencephalogram signal (C4-P4) and the present work can be applied for home monitoring systems for bruXism detection.
- A Multi-Stage Deep-Learning-Based Vehicle and License Plate Recognition System with Real-Time Edge Inference71
A novel multi-stage, real-time, deep learning-based vehicle identification and license plate recognition system based on a set of algorithms that efficiently integrate two object detectors, an image classifier, and a multi-object tracker to recognize car models and license plates.
- 70
- TAU: A framework for video-based traffic analytics leveraging artificial intelligence and unmanned aerial systems55
This paper uses the use of Artificial Intelligence (AI) and Unmanned Aerial Vehicles (UAVs) to develop an AI-integrated video analytics framework, called TAU (Traffic Analysis from UAVs), for automated traffic analytics and understanding.
- TESR: Two-Stage Approach for Enhancement and Super-Resolution of Remote Sensing Images54
A new architecture called TESR (Two-stage approach for Enhancement and super-resolution), leveraging the power of Vision Transformers and the Diffusion Model to increase the resolution of RS images artificially, which outperforms state-of-the-art architectures on super- Resolution of remote sensing images on the UCMerced benchmark dataset.
- COVID-19 Diagnosis in Chest X-rays Using Deep Learning and Majority Voting47
This paper finds that using the Majority Voting approach is an adequate strategy to adopt in general cases for this task and may achieve an average accuracy up to 99.314%.
- Data-Efficient Domain Adaptation for Semantic Segmentation of Aerial Imagery Using Generative Adversarial Networks45
This paper proposed a new algorithm that uses Generative Adversarial Networks (GAN) architecture to minimize the domain shift and increase the ability of the model to work on new targeted domains, and proposed a methodology to use these labeled data efficiently.
- A Machine Learning Approach Involving Functional Connectivity Features to Classify Rest-EEG Psychogenic Non-Epileptic Seizures from Healthy Controls44
An intrinsic organization of functional brain networks that reflects a dysfunctional level of integration across brain regions, which can provide new insights into the pathophysiological mechanisms of PNES is hypothesized.
- 42
- Early detection of red palm weevil infestations using deep learning classification of acoustic signals39
The proposed approach is based on RPW sound activities being recorded and analyzed and outperformed existing techniques for public datasets for early detection of RPW.
- A Hybrid Privacy-Preserving Deep Learning Approach for Object Classification in Very High-Resolution Satellite Images35
A hybrid PPDL approach for object classification for very-high-resolution satellite images that combines Paillier homomorphic encryption (PHE) and somewhat homomorphicryption (SHE) while ensuring a good runtime and high object classification accuracy is proposed.
- Helping the Visually Impaired See via Image Multi-labeling Based on SqueezeNet CNN35
The proposed deep CNN is an effective solution for predicting the presence of objects in a scene and can be successfully used as a module within BlindSys, a larger system that assists the visually impaired in an indoor environment.
- The Tenth NTIRE 2025 Image Denoising Challenge Report34
An overview of the NTIRE 2025 Image Denoising Challenge is presented, highlighting the proposed methodologies and corresponding results, providing insights into the current state-of-the-art in image denoising.
- 33
- Activity Monitoring of Islamic Prayer (Salat) Postures using Deep Learning32
This work addresses the problem of the recognition of the basic gestures of Islamic prayer using Convolutional Neural Networks (CNN), and is the first work that addresses human activity recognition of Salat using deep learning.
- NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild29
This report provides a comprehensive overview of the NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild, describes the proposed solutions, and can be used as a valuable reference for researchers and practitioners in increasing the robustness of the detection models to real-world transformations.
- NTIRE 2025 Challenge on Low Light Image Enhancement: Methods and Results29
This paper thoroughly evaluates the state-of-the-art advancements in LLIE, showcasing the significant progress.
- 29
- 28
- Robust Deepfake Detection, NTIRE 2026 Challenge: Report26
This report presents the competition setting, dataset preparation, as well as details and performance of methods, which rely on large foundation models, ensembles, and degradation training to combine generality and robustness in deepfake detection.
- Spinal Cord Segmentation in Ultrasound Medical Imagery25
This task is useful for neurosurgeons to analyze the spinal cord movement during and after the laminectomy surgical operation and it is found that the best solution for this task is Fully Convolutional DenseNets if the spinal Cord is already in the train set, and U-Net is the best.
- The Fourth Challenge on Image Super-Resolution ($\times$4) at NTIRE 2026: Benchmark Results and Method Overview24
The NTIRE 2026 image super-resolution ($\times$4) challenge, one of the associated competitions of the NTIRE 2026 Workshop at CVPR 2026, provides a unified benchmark and offers insights into current progress and future directions in image super-resolution.
- Low Light Image Enhancement Challenge at NTIRE 202623
This paper thoroughly evaluates the state-of-the-art advances in (joint denoising and) low-light image enhancement, showcasing the significant progress in the field, while leveraging samples of the authors' novel dataset.
- 23
- NTIRE 2025 Challenge on Image Super-Resolution ($\times 4$): Methods and Results23
The NTIRE 2025 image super-resolution ($\times 4$) challenge, one of the associated competitions of the 10th NTIRE Workshop at CVPR 2025, aims to recover high-resolution images from low-resolution counterparts generated through bicubic downsampling with a $\times 4$ scaling factor.
- Ntire 2025 Image Shadow Removal Challenge Report22
This work examines the findings of the NTIRE 2025 Shadow Removal Challenge, with 17 teams successfully submitting their solutions during the final evaluation phase, and one focusing on reconstruction fidelity and the other on visual perception through a user study.
- 22
- NTIRE 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results21
An overview of the NTIRE 2026 Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images demonstrates the growing progress in this challenging task.
- NTIRE 2026 Challenge on Single Image Reflection Removal in the Wild: Datasets, Results, and Methods20
The NTIRE 2026 challenge on single-image reflection removal (SIRR) in the wild is reviewed, with the top-ranked methods advanced the state-of-the-art reflection removal performance and earned unanimous recognition from five experts in the field.
- 20
- Streamlined Global and Local Features Combinator (SGLC) for High Resolution Image Dehazing19
The Streamlined Global and Local Features Combinator (SGLC) is proposed to solve the issues and to optimize the application of any Dehazing model to High-Resolution images.
- DiffPlate: A Diffusion Model for Super-Resolution of License Plate Images17
Through DiffPlate, a novel Diffusion Model specifically tailored for license plate super-resolution is presented, demonstrating significant potential for adoption in real-world surveillance systems and empirical analysis substantiates that DiffPlate markedly eclipses state-of-the-art alternatives.
- 16
- Machine Learning Analytic-Based Two-Staged Data Management Framework for Internet of Things15
A new framework for data management of IoT applications is designed and implemented called MLADCF (Machine Learning Analytics-based Data Classification Framework) that combines a regression model and a Hybrid Resource Constrained KNN (HRCKNN).
- Prompting Robotic Modalities (PRM): A structured architecture for centralizing language models in complex systems14
It is argued that the next generation of robots can be commanded using only Language Models' prompts and this paper applies this PRM design pattern in building a new robotic framework named ROSGPT_Vision, which enables controlling robots using only prompts.
- 14
- 11
- DM–AHR: A Self-Supervised Conditional Diffusion Model for AI-Generated Hairless Imaging for Enhanced Skin Diagnosis Applications10
The architecture of DM–AHR is elaborate on the architecture of DM–AHR and its effective performance in removing hair while preserving critical details of skin lesions is demonstrated, showing an enhancement in the accuracy of skin lesion analysis when compared to existing techniques.
- 10
- 9
- Parking Analytics Framework using Deep Learning7
A methodology to monitor car parking areas and to analyze their occupancy in real-time using the Ray Tracing algorithm, based on a combination between image analysis and deep learning techniques to optimize the use of parking areas.
- Multiple Object Scene Description for the Visually Impaired Using Pre-trained Convolutional Neural Networks6
A new method for multiple object scene description as part of a system to guide the visually impaired in an indoor environment based on the extraction of powerful features using pre-trained convolutional neural networks, then training a Neural Network regression to predict the content of any unknown scene based on its CNN feature.
- 5
- 4
- Guided Frequency Loss for Image Restoration4
The Guided Frequency Loss (GFL), which helps the model to learn in a balanced way the image's frequency content alongside the spatial content, aggregates three major components that work in parallel to enhance learning efficiency.
- 3
- 3
- 2
- 2
- Learning the Arabic Dialect Continuum as a Continuous Space: A Regression Approach to Speaker Origin Prediction1
This work presents a regression-based approach to Arabic dialect geolocation that models dialectal variation as a continuous geographic space rather than discrete categories and establishes continuous geographic modeling as a principled framework for Arabic dialect geolocation.
- 1
- 1
- Cybersecurity advancements for medical image transmission: a hybrid optical-based cryptosystem harnessing chaos, DNA sequences, and mandelbrot keys1
This study introduces a novel hybrid cryptosystem, drawing on the unique qualities of the optical Arnold chaotic map, DNA (DeoxyriboNucleic Acid) sequences, and Mandelbrot keys, providing a fortified approach to the secure streaming of medical images.
- Signatures of Brain Network Alteration in Psychogenic Non-Epileptic Seizures: A Rest-EEG Study Based on Power Spectral Density and Phase Lag Index1
The findings look into new evidence of the intrinsic organization of functional brain networks that reflects a dysfunctional level of integration of local activity across brain regions, which can provide new insights into the pathophysiological mechanisms of PNES.
- Trust-SSL: Additive-Residual Selective Invariance for Robust Aerial Self-Supervised Learning–
This study proposes a training strategy and architectural modification to enhance SSL robustness to such corruptions by introducing a per-sample, per-factor trust weight into the alignment objective, combined with the base contrastive loss as an additive residual.
- HARNES: Heuristic Algorithm for Routing and Network Efficiency Using SDN in Intelligent Transportation Systems–
Simulation results demonstrate that the cluster-based cluster-based <inline-formula> achieves up to 42% reduction in computation time, 88% fewer discovery messages, and 47% fewer expanded nodes, while maintaining near-optimal path quality within 3.1% of optimality.
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.