82 citations · 106 across the 12 of their papers we have counts for
18 papers
Self-Training of Handwritten Word Recognition for Synthetic-to-Real Adaptation
Fabian Wolf, Gernot A. Fink
Performances of Handwritten Text Recognition (HTR) models are largely determined by the availability of labeled and representative training samples. However, in many application sc…
Recognition-free Question Answering on Handwritten Document Collections
Oliver Tüselmann, Friedrich Müller, Fabian Wolf +1
In recent years, considerable progress has been made in the research area of Question Answering (QA) on document images. Current QA approaches from the Document Image Analysis comm…
UQGAN: A Unified Model for Uncertainty Quantification of Deep Classifiers trained via Conditional GANs
Philipp Oberdiek, Gernot A. Fink, Matthias Rottmann
We present an approach to quantifying both aleatoric and epistemic uncertainty for deep neural networks in image classification, based on generative adversarial networks (GANs). Wh…
Human Activity Recognition using Attribute-Based Neural Networks and Context Information
Stefan Lüdtke, Fernando Moya Rueda, Waqas Ahmed +2
We consider human activity recognition (HAR) from wearable sensor data in manual-work processes, like warehouse order-picking. Such structured domains can often be partitioned into…
Detection and Retrieval of Out-of-Distribution Objects in Semantic Segmentation
Philipp Oberdiek, Matthias Rottmann, Gernot A. Fink
When deploying deep learning technology in self-driving cars, deep neural networks are constantly exposed to domain shifts. These include, e.g., changes in weather conditions, time…
Annotation-free Learning of Deep Representations for Word Spotting using Synthetic Data and Self Labeling
Fabian Wolf, Gernot A. Fink
Word spotting is a popular tool for supporting the first exploration of historic, handwritten document collections. Today, the best performing methods rely on machine learning tech…
Exploring Confidence Measures for Word Spotting in Heterogeneous Datasets
Fabian Wolf, Philipp Oberdiek, Gernot A. Fink
In recent years, convolutional neural networks (CNNs) took over the field of document analysis and they became the predominant model for word spotting. Especially attribute CNNs, w…
Exploring Architectures for CNN-Based Word Spotting
Eugen Rusakov, Sebastian Sudholt, Fabian Wolf +1
The goal in word spotting is to retrieve parts of document images which are relevant with respect to a certain user-defined query. The recent past has seen attribute-based Convolut…
Learning Attribute Representation for Human Activity Recognition
Fernando Moya Rueda, Gernot A. Fink
Attribute representations became relevant in image recognition and word spotting, providing support under the presence of unbalance and disjoint datasets. However, for human activi…
Weakly Supervised Object Detection with Pointwise Mutual Information
Rene Grzeszick, Sebastian Sudholt, Gernot A. Fink
In this work a novel approach for weakly supervised object detection that incorporates pointwise mutual information is presented. A fully convolutional neural network architecture…
Learning Deep Representations for Word Spotting Under Weak Supervision
Neha Gurjar, Sebastian Sudholt, Gernot A. Fink
Convolutional Neural Networks have made their mark in various fields of computer vision in recent years. They have achieved state-of-the-art performance in the field of document an…
Attribute CNNs for Word Spotting in Handwritten Documents
Sebastian Sudholt, Gernot Fink
Word spotting has become a field of strong research interest in document image analysis over the last years. Recently, AttributeSVMs were proposed which predict a binary attribute…
Neuron Pruning for Compressing Deep Networks using Maxout Architectures
Fernando Moya Rueda, Rene Grzeszick, Gernot A. Fink
This paper presents an efficient and robust approach for reducing the size of deep neural networks by pruning entire neurons. It exploits maxout units for combining neurons into mo…
Weakly-supervised localization of diabetic retinopathy lesions in retinal fundus images
Waleed M. Gondal, Jan M. Köhler, René Grzeszick +2
Convolutional neural networks (CNNs) show impressive performance for image classification and detection, extending heavily to the medical image domain. Nevertheless, medical expert…
Optimistic and Pessimistic Neural Networks for Scene and Object Recognition
Rene Grzeszick, Sebastian Sudholt, Gernot A. Fink
In this paper the application of uncertainty modeling to convolutional neural networks is evaluated. A novel method for adjusting the network's predictions based on uncertainty inf…
Zero-shot object prediction using semantic scene knowledge
Rene Grzeszick, Gernot A. Fink
This work focuses on the semantic relations between scenes and objects for visual object recognition. Semantic knowledge can be a powerful source of information especially in scena…
PHOCNet: A Deep Convolutional Neural Network for Word Spotting in Handwritten Documents
Sebastian Sudholt, Gernot A. Fink
In recent years, deep convolutional neural networks have achieved state of the art performance in various computer vision task such as classification, detection or segmentation. Du…
Multi-Modal Human-Machine Communication for Instructing Robot Grasping Tasks
P. C. McGuire, J. Fritsch, J. J. Steil +5
A major challenge for the realization of intelligent robots is to supply them with cognitive abilities in order to allow ordinary users to program them easily and intuitively. One…