IEEE

A Novel Approach to Deepfake Detection: Leveraging Fused Facial and Body Dynamics With a CNN–Transformer Hybrid Network

Abstract: The rapid advancement of generative models like Generative Adversarial Networks (GANs) has contributed significantly to the creation of deep-fake videos. These synthetic videos pose serious ...
IEEE

A Comprehensive Review of Object Detection Using Deep Learning

Abstract: Abstract: In recent times, deep learning has emerged as one of the powerful tools in the process of object detection. The deep learning algorithms that are used in object detection are ...
IEEE

Optimizing Accuracy and Efficiency in Brain Tumor Detection: CNN with Moth Flame Optimization vs. EfficientNet V2-B20

Abstract: The identification of brain tumors using the Magnetic Resonance Imaging (MRI) is an essential operation in medical diagnostics, whose early and precise detection can greatly influence the ...
IEEE

MonoGSDet: Monocular 3D Object Detection With Gaussian Splatting in Autonomous Driving

Abstract: Monocular 3D object detection has gained considerable attention because of its cost-effectiveness and practical applicability, particularly in autonomous driving and robotics. Most of ...
IEEE

EFAF-YOLO: A Novel Enhanced Framework for Small-Object Detection

Abstract: Remote sensing platforms provide crucial data for applications such as urban planning and traffic monitoring. However, detecting small objects remains challenging due to low resolution, ...
IEEE

DPLR-DETR: Small Object Detection Model for UAV Aerial Imagery

Abstract: Small object detection in UAV aerial imagery presents significant challenges due to limited pixel coverage and complex backgrounds. This paper introduces DPLR-DETR (Dynamic Position Large ...
IEEE

Building a CNN Based Pest Detection System for Off Grid Hydroponic Farming in Rural South Africa

Subsistence farming plays a crucial role in the South African economic sector, supporting around 60 % of households [1]. However, food insecurity persists due to severe and unpredictable climate ...
IEEE

Open-World Objectness Modeling Unifies Novel Object Detection

Abstract: The challenge in open-world object detection, similarly to few- and zero-shot learning, is to generalize beyond the class distribution of the training data. In this paper, we propose a ...
IEEE

Camouflaged Object Detection via Frequency-aware Localization Perception and Boundary-aware Detail Enhancement

Abstract: Although existing camouflaged object detection (COD) approaches have developed various strategies to improve performance, there remains plenty of room for further improvement. The primary ...
IEEE

A CNN-RNN System for Real Time Credit Card Fraud Detection Using Three-Way Classification to Reduce False Positives /Negatives and Detect Fraud Across All Transaction Values

Abstract: Financial institutions and consumers whose accounts are compromised suffer financial loss from credit card fraud caused by traditional fraud detection systems which rely on static, ...
IEEE

Deepshield34: Frame Level Deepfake Detection Using CNN with ResNet34 Backbone

Abstract: As deepfakes become more common on digital platforms, reliable detection is vital. For this study, we propose a hybrid ResNet-34-based deepfake detection model with a preprocessing pipeline ...
IEEE

Efficient Event-Based Object Detection: A Hybrid Neural Network with Spatial and Temporal Attention

Abstract: Event cameras offer high temporal resolution and dynamic range with minimal motion blur, making them promising for robust object detection. While Spiking Neural Networks (SNNs) on ...