N
Nassim Ammour
Researcher at King Saud University
Publications - 30
Citations - 689
Nassim Ammour is an academic researcher from King Saud University. The author has contributed to research in topics: Feature extraction & Deep learning. The author has an hindex of 10, co-authored 25 publications receiving 384 citations.
Papers
More filters
Journal ArticleDOI
Deep Learning Approach for Car Detection in UAV Imagery
TL;DR: 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.
Journal ArticleDOI
Classification of Remote Sensing Images Using EfficientNet-B3 CNN Model With Attention
TL;DR: Wang et al. as discussed by the authors proposed a deep attention convolutional neural network (CNN) for scene classification in remote sensing, which computes a new feature map as a weighted average of these original feature maps.
Journal ArticleDOI
Siamese-GAN: Learning Invariant Representations for Aerial Vehicle Image Categorization
Laila Bashmal,Yakoub Bazi,Haikel Alhichri,Mohamad Mahmoud Alrahhal,Nassim Ammour,Naif Alajlan +5 more
TL;DR: A new algorithm for cross-domain classification in aerial vehicle images based on generative adversarial networks (GANs), called Siamese-GAN, learns invariant feature representations for both labeled and unlabeled images coming from two different domains.
Journal ArticleDOI
Asymmetric Adaptation of Deep Features for Cross-Domain Classification in Remote Sensing Imagery
TL;DR: An asymmetric adaptation neural network (AANN) method for cross-domain classification in remote sensing images by feeding features obtained from a pretrained convolutional neural network to a denoising autoencoder to perform dimensionality reduction.
Journal ArticleDOI
Rhythm-based heartbeat duration normalization for atrial fibrillation detection
TL;DR: The proposed normalization method of heartbeat duration of rhythm-based normalization was found useful for improving performance and robustness of AF detection and it was consistent for a wide range of sensitivity and specificity for use of different thresholds.