25 citations · 45 across the 8 of their papers we have counts for
12 papers
Generating Synthetic Handwritten Historical Documents With OCR Constrained GANs
Lars Vögtlin, Manuel Drazyk, Vinaychandran Pondenkandath +2
We present a framework to generate synthetic historical documents with precise ground truth using nothing more than a collection of unlabeled historical images. Obtaining large lab…
Labeling, Cutting, Grouping: an Efficient Text Line Segmentation Method for Medieval Manuscripts
Michele Alberti, Lars Vögtlin, Vinaychandran Pondenkandath +3
This paper introduces a new way for text-line extraction by integrating deep-learning based pre-classification and state-of-the-art segmentation methods. Text-line extraction in co…
Improving Reproducible Deep Learning Workflows with DeepDIVA
Michele Alberti, Vinaychandran Pondenkandath, Lars Vögtlin +3
The field of deep learning is experiencing a trend towards producing reproducible research. Nevertheless, it is still often a frustrating experience to reproduce scientific results…
Survey of Artificial Intelligence for Card Games and Its Application to the Swiss Game Jass
Joel Niklaus, Michele Alberti, Vinaychandran Pondenkandath +2
In the last decades we have witnessed the success of applications of Artificial Intelligence to playing games. In this work we address the challenging field of games with hidden in…
A Comprehensive Study of ImageNet Pre-Training for Historical Document Image Analysis
Linda Studer, Michele Alberti, Vinaychandran Pondenkandath +5
Automatic analysis of scanned historical documents comprises a wide range of image analysis tasks, which are often challenging for machine learning due to a lack of human-annotated…
Leveraging Random Label Memorization for Unsupervised Pre-Training
Vinaychandran Pondenkandath, Michele Alberti, Sammer Puran +2
We present a novel approach to leverage large unlabeled datasets by pre-training state-of-the-art deep neural networks on randomly-labeled datasets. Specifically, we train the neur…
Offline Signature Verification by Combining Graph Edit Distance and Triplet Networks
Paul Maergner, Vinaychandran Pondenkandath, Michele Alberti +4
Biometric authentication by means of handwritten signatures is a challenging pattern recognition task, which aims to infer a writer model from only a handful of genuine signatures.…
Are You Tampering With My Data?
Michele Alberti, Vinaychandran Pondenkandath, Marcel Würsch +4
We propose a novel approach towards adversarial attacks on neural networks (NN), focusing on tampering the data used for training instead of generating attacks on trained models. O…
DeepDIVA: A Highly-Functional Python Framework for Reproducible Experiments
Michele Alberti, Vinaychandran Pondenkandath, Marcel Würsch +2
We introduce DeepDIVA: an infrastructure designed to enable quick and intuitive setup of reproducible experiments with a large range of useful analysis functionality. Reproducing s…
Identifying Cross-Depicted Historical Motifs
Vinaychandran Pondenkandath, Michele Alberti, Nicole Eichenberger +2
Cross-depiction is the problem of identifying the same object even when it is depicted in a variety of manners. This is a common problem in handwritten historical documents image a…
Historical Document Image Segmentation with LDA-Initialized Deep Neural Networks
Michele Alberti, Mathias Seuret, Vinaychandran Pondenkandath +2
In this paper, we present a novel approach to perform deep neural networks layer-wise weight initialization using Linear Discriminant Analysis (LDA). Typically, the weights of a de…
Transforming Sensor Data to the Image Domain for Deep Learning - an Application to Footstep Detection
Monit Shah Singh, Vinaychandran Pondenkandath, Bo Zhou +2
Convolutional Neural Networks (CNNs) have become the state-of-the-art in various computer vision tasks, but they are still premature for most sensor data, especially in pervasive a…