Farhan Hussain

HSV-2 Acute Retinal Necrosis Complicated by Persistent Vitreous Opacities and Cystoid Macular Edema: A Case Report

Abhinav Ankem, Katherine Jaje, Farhan Hussain

us (code pays fourni par la source)

Remote Sensing Image Captioning via Self-Supervised DINOv3 and Transformer Fusion

Maryam Mehmood, Ahsan Shahzad, Farhan Hussain, Lismer Andres Caceres-Najarro et autres

Effective interpretation of coherent and usable information from aerial images (e.g., satellite imagery or high-altitude drone photography) can greatly reduce human effort in many situations, both natural (e.g., earthquakes, forest fires, tsunamis) and man-made (e.g., highway pile-ups, traffic congestion), particularly in disaster …

pk, kr, se (code pays fourni par la source)

RSDhazer: Residual Shallow‐Deep Network for Efficient Single‐Image Dehazing

Syeda Rabail Zahra, Farhan Hussain, Tehseen Mazhar, Muhammad Danish Ali et autres

ABSTRACT Single‐image dehazing remains a challenging problem due to non‐uniform haze distribution, which often leads to degraded visual quality and incomplete reconstruction in existing deep learning approaches. We propose RSDhazer, a residual shallow‐deep dehazer network designed to address these challenges through complementary …

pk, sa, bd, my (code pays fourni par la source)

Generating Textual Descriptions for Remote Sensing Images

Maryam Mehmood, Ahsan Shahzad, Amin Ullah, Farhan Hussain et autres

Generating descriptive and semantically meaningful captions for remote sensing images remains a challenging task due to the inherent complexity of aerial scenes, characterized by diverse spatial arrangements, scale variations, and ambiguous semantics. To address these challenges, this study introduces a hybrid deep …

pk, ae (code pays fourni par la source)

RABNet: A Residual Attention‐Based Network for Visibility Restoration in Hazy Images

Syeda Rabail Zahra, Farhan Hussain, Ali Hassan, Tehseen Mazhar et autres

Image dehazing enhances visibility and image quality, enabling better decision‐making in critical applications such as surveillance, remote sensing, and autonomous driving. However, single‐image dehazing remains challenging due to the need for smoothness in homogeneous regions, accurate edge preservation, texture fidelity, and artifact‐free …

RSDNet: Residual Shallow–Deep Attention Network for Single Image Dehazing

Syeda Rabail Zahra, Farhan Hussain, Sadia Ismail, ASIA ZAMAN et autres

Single-image dehazing still faces challenges of uneven haze distribution and loss of information in reconstructed images. We develop RSDNet, a Residual Shallow-Deep Attention Network that restores high-quality haze-free images while maintaining low computational cost. The network integrates three complementary modules; Multi-Activated Attention …

pk, my (code pays fourni par la source)

CAM-Net: enhancing visibility in hazy images with convolutional attention mechanisms

Syeda Rabail Zahra, Farhan Hussain

pk (code pays fourni par la source)

Classification of Remote Sensing Datasets with Different Deep Learning Architectures

Maryam Mehmood, Farhan Hussain, Ahsan Shahzad, Nouman Ali

Remote sensing image classification has great advantages in the areas of environmental monitoring, urban planning, disaster management and many others. Unmanned Aerial Vehicles (UAVs) have revolutionized remote sensing by providing high-resolution imagery. In this context, effective image classification is crucial for extracting …

pk (code pays fourni par la source)

Clasificación de grupos de datos de detección remota con diferentes arquitecturas de aprendizaje profundo

Maryam Mehmood, Farhan Hussain, Ahsan Shahzad, Nouman Ali

Remote sensing image classification has great advantages in the areas of environmental monitoring, urban planning, disaster management and many others. Unmanned Aerial Vehicles (UAVs) have revolutionized remote sensing by providing high-resolution imagery. In this context, effective image classification is crucial for extracting …

pk (code pays fourni par la source)

Scene and Aerial Image Classification Based on Advanced Deep Learning Technique

Maryam Mehmood, Farhan Hussain, Asad Ijaz

pk (code pays fourni par la source)

AI-CADR: Artificial Intelligence Based Risk Stratification of Coronary Artery Disease Using Novel Non-Invasive Biomarkers

Ali Hassan, Dilshad Ahmed Khan, Shoab Ahmed Khan, Asim Dilawar Bakhshi et autres

Coronary artery disease (CAD) is one of the most common causes of sudden cardiac arrest, accounting for a large percentage of global mortality. A timely diagnosis and detection may save a person's life. The research suggests a methodological framework for non-invasive risk …

pk, sa (code pays fourni par la source)

Enhanced Spatial Stream of Two-Stream Network Using Optical Flow for Human Action Recognition

Shahbaz Ali Khan, Ali Hassan, Farhan Hussain, Aqib Perwaiz et autres

Introduction: Convolutional neural networks (CNNs) have maintained their dominance in deep learning methods for human action recognition (HAR) and other computer vision tasks. However, the need for a large amount of training data always restricts the performance of CNNs. Method: This paper …

pk, gb, sa (code pays fourni par la source)