S
Sheraz Ahmed
Researcher at German Research Centre for Artificial Intelligence
Publications - 177
Citations - 2773
Sheraz Ahmed is an academic researcher from German Research Centre for Artificial Intelligence. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 19, co-authored 130 publications receiving 1477 citations. Previous affiliations of Sheraz Ahmed include Kaiserslautern University of Technology.
Papers
More filters
Journal ArticleDOI
DeepAnT: A Deep Learning Approach for Unsupervised Anomaly Detection in Time Series
TL;DR: A novel deep learning-based anomaly detection approach (DeepAnT) for time series data, which is equally applicable to the non-streaming cases and outperforms the state-of-the-art anomaly detection methods in most of the cases, while performing on par with others.
Proceedings ArticleDOI
DeepDeSRT: Deep Learning for Detection and Structure Recognition of Tables in Document Images
TL;DR: In contrast to most existing table detection and structure recognition methods, which are applicable only to PDFs, DeepDeSRT processes document images, which makes it equally suitable for born-digital PDFs as well as even harder problems, e.g. scanned documents.
Posted Content
TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network.
TL;DR: The TAC-GAN model is trained on the Oxford-102 dataset of flowers, and the discriminability of the generated images with Inception-Score, as well as their diversity using the Multi-Scale Structural Similarity Index (MS-SSIM).
Journal ArticleDOI
Two-stage framework for optic disc localization and glaucoma classification in retinal fundus images using deep learning
Muhammad Naseer Bajwa,Muhammad Naseer Bajwa,Muhammad Imran Malik,Shoaib Ahmed Siddiqui,Shoaib Ahmed Siddiqui,Andreas Dengel,Andreas Dengel,Faisal Shafait,Wolfgang Neumeier,Sheraz Ahmed +9 more
TL;DR: A two-stage framework that first detects and localizes optic disc and then classifies it into healthy or glaucomatous and a rule-based semi-automatic ground truth generation method that provides necessary annotations for training RCNN based model for automated disc localization is developed.
Proceedings ArticleDOI
Improved Automatic Analysis of Architectural Floor Plans
TL;DR: This paper proposes a novel complete system for automated floor plan analysis that outperforms previous systems and introduces novel preprocessing methods, e.g., the differentiation between thick, medium, and thin lines and the removal of components outside the convex hull of the outer walls.