Search Results for author:
Found 19 papers, 3 papers with code
Multi-Channel Time-Series Person and Soft-Biometric Identification
On-body device (OBD) recordings of human movements are often preferred for HAR applications not only for their reliability but as an approach for identity protection, e. g., in industrial settings.
Dataset Bias in Human Activity Recognition
It is unknown what physical characteristics and/or soft-biometrics, such as age, height, and weight, need to be taken into account to train a classifier to achieve robustness towards heterogeneous populations in the training and testing data.
Video-based Pose-Estimation Data as Source for Transfer Learning in Human Activity Recognition
HAR is challenging due to the inter and intra-variance of human movements; moreover, annotated datasets from on-body devices are scarce.
Self-Training of Handwritten Word Recognition for Synthetic-to-Real Adaptation
Performances of Handwritten Text Recognition (HTR) models are largely determined by the availability of labeled and representative training samples.
Recognition-free Question Answering on Handwritten Document Collections
In recent years, considerable progress has been made in the research area of Question Answering (QA) on document images.
UQGAN: A Unified Model for Uncertainty Quantification of Deep Classifiers trained via Conditional GANs
We present an approach to quantifying both aleatoric and epistemic uncertainty for deep neural networks in image classification, based on generative adversarial networks (GANs).
Out of Distribution (OOD) Detection
Uncertainty Quantification
Human Activity Recognition using Attribute-Based Neural Networks and Context Information
Here, we show how such context information can be integrated systematically into a deep neural network-based HAR system.
Detection and Retrieval of Out-of-Distribution Objects in Semantic Segmentation
When deploying deep learning technology in self-driving cars, deep neural networks are constantly exposed to domain shifts.
Annotation-free Learning of Deep Representations for Word Spotting using Synthetic Data and Self Labeling
Word spotting is a popular tool for supporting the first exploration of historic, handwritten document collections.
Exploring Confidence Measures for Word Spotting in Heterogeneous Datasets
In recent years, convolutional neural networks (CNNs) took over the field of document analysis and they became the predominant model for word spotting.
Exploring Architectures for CNN-Based Word Spotting
The goal in word spotting is to retrieve parts of document images which are relevant with respect to a certain user-defined query.
Learning Attribute Representation for Human Activity Recognition
Attribute representations became relevant in image recognition and word spotting, providing support under the presence of unbalance and disjoint datasets.
Weakly Supervised Object Detection with Pointwise Mutual Information
It is shown that the combination of pointwise mutual information and a cosine loss eases the learning process and thus improves the accuracy.
Learning Deep Representations for Word Spotting Under Weak Supervision
Convolutional Neural Networks have made their mark in various fields of computer vision in recent years.
Neuron Pruning for Compressing Deep Networks using Maxout Architectures
Furthermore, it will be shown that neuron pruning can be combined with subsequent weight pruning, reducing the size of the LeNet-5 and VGG16 up to $92\%$ and $80\%$ respectively.
Weakly-supervised localization of diabetic retinopathy lesions in retinal fundus images
Although these approaches could help to build trust in the CNNs predictions, they are only slightly shown to work with medical image data which often poses a challenge as the decision for a class relies on different lesion areas scattered around the entire image.
Optimistic and Pessimistic Neural Networks for Scene and Object Recognition
A novel method for adjusting the network's predictions based on uncertainty information is introduced.
Zero-shot object prediction using semantic scene knowledge
This work focuses on the semantic relations between scenes and objects for visual object recognition.
PHOCNet: A Deep Convolutional Neural Network for Word Spotting in Handwritten Documents
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.
General Classification
Word Spotting In Handwritten Documents
