Felix Schneider, Sven Sickert, Phillip Brandes, Sophie Marshall, Joachim Denzler:
Hard is the Task, the Samples are Few: A German Chiasmus Dataset.
Language Technology Conference: Human Language Technologies as a Challenge for Computer Science and Linguistics (LTC).
2023.
(accepted)
[bibtex]
[abstract]
In this work we present a novel German language dataset for the detection of the stylistic device called chiasmus collected from German dramas. The dataset includes phrases labeled as chiasmi, antimetaboles, semantically unrelated inversions, and various edge cases. The dataset was created by collecting examples from the GerDraCor dataset. We test different approaches for chiasmus detection on the samples and report an average precision of 0.74 for the best method. Additionally, we give an overview about related approaches and the current state of the research on chiasmus detection.
Tim Büchner, Sven Sickert, Gerd F. Volk, Christoph Anders, Orlando Guntinas-Lichius, Joachim Denzler:
Let’s Get the FACS Straight - Reconstructing Obstructed Facial Features.
International Conference on Computer Vision Theory and Applications (VISAPP).
Pages 727-736.
2023.
[bibtex]
[web]
[doi]
[abstract]
The human face is one of the most crucial parts in interhuman communication. Even when parts of the face are hidden or obstructed the underlying facial movements can be understood. Machine learning approaches often fail in that regard due to the complexity of the facial structures. To alleviate this problem a common approach is to fine-tune a model for such a specific application. However, this is computational intensive and might have to be repeated for each desired analysis task. In this paper, we propose to reconstruct obstructed facial parts to avoid the task of repeated fine-tuning. As a result, existing facial analysis methods can be used without further changes with respect to the data. In our approach, the restoration of facial features is interpreted as a style transfer task between different recording setups. By using the CycleGAN architecture the requirement of matched pairs, which is often hard to fullfill, can be eliminated. To proof the viability of our approach, we compare our reconstructions with real unobstructed recordings. We created a novel data set in which 36 test subjects were recorded both with and without 62 surface electromyography sensors attached to their faces. In our evaluation, we feature typical facial analysis tasks, like the computation of Facial Action Units and the detection of emotions. To further assess the quality of the restoration, we also compare perceptional distances. We can show, that scores similar to the videos without obstructing sensors can be achieved.
Felix Schneider, Sven Sickert, Phillip Brandes, Sophie Marshall, Joachim Denzler:
Metaphor Detection for Low Resource Languages: From Zero-Shot to Few-Shot Learning in Middle High German.
LREC Workshop on Multiword Expression (LREC-WS).
Pages 75-80.
2022.
[bibtex]
[web]
[code]
[abstract]
In this work, we present a novel unsupervised method for adjective-noun metaphor detection on low resource languages. We propose two new approaches: First, a way of artificially generating metaphor training examples and second, a novel way to find metaphors relying only on word embeddings. The latter enables application for low resource languages. Our method is based on a transformation of word embedding vectors into another vector space, in which the distance between the adjective word vector and the noun word vector represents the metaphoricity of the word pair. We train this method in a zero-shot pseudo-supervised manner by generating artificial metaphor examples and show that our approach can be used to generate a metaphor dataset with low annotation cost. It can then be used to finetune the system in a few-shot manner. In our experiments we show the capabilities of the method in its unsupervised and in its supervised version. Additionally, we test it against a comparable unsupervised baseline method and a supervised variation of it.
Tim Büchner, Sven Sickert, Gerd F. Volk, Orlando Guntinas-Lichius, Joachim Denzler:
Automatic Objective Severity Grading of Peripheral Facial Palsy Using 3D Radial Curves Extracted from Point Clouds.
Challenges of Trustable AI and Added-Value on Health.
Pages 179-183.
2022.
[bibtex]
[web]
[doi]
[code]
[abstract]
Peripheral facial palsy is an illness in which a one-sided ipsilateral paralysis of the facial muscles occurs due to nerve damage. Medical experts utilize visual severity grading methods to estimate this damage. Our algorithm-based method provides an objective grading using 3D point clouds. We extract from static 3D recordings facial radial curves to measure volumetric differences between both sides of the face. We analyze five patients with chronic complete peripheral facial palsy to evaluate our method by comparing changes over several recording sessions. We show that our proposed method allows an objective assessment of facial palsy.
Martin Thümmel, Sven Sickert, Joachim Denzler:
Facial Behavior Analysis using 4D Curvature Statistics for Presentation Attack Detection.
IEEE International Workshop on Biometrics and Forensics (IWBF).
Pages 1-6.
2021.
[bibtex]
[web]
[doi]
[code]
[abstract]
The human face has a high potential for biometric identification due to its many individual traits. At the same time, such identification is vulnerable to biometric copies. These presentation attacks pose a great challenge in unsupervised authentication settings. As a countermeasure, we propose a method that automatically analyzes the plausibility of facial behavior based on a sequence of 3D face scans. A compact feature representation measures facial behavior using the temporal curvature change. Finally, we train our method only on genuine faces in an anomaly detection scenario. Our method can detect presentation attacks using elastic 3D masks, bent photographs with eye holes, and monitor replay-attacks. For evaluation, we recorded a challenging database containing such cases using a high-quality 3D sensor. It features 109 4D face scans including eleven different types of presentation attacks. We achieve error rates of 11% and 6% for APCER and BPCER, respectively.
Anish Raj, Oliver Mothes, Sven Sickert, Gerd F. Volk, Orlando Guntinas-Lichius, Joachim Denzler:
Automatic and Objective Facial Palsy Grading Index Prediction using Deep Feature Regression.
Annual Conference on Medical Image Understanding and Analysis (MIUA).
Pages 253-266.
2020.
[bibtex]
[web]
[doi]
[abstract]
One of the main reasons for a half-sided facial paralysis is caused by a dysfunction of the facial nerve. Physicians have to assess such a unilateral facial palsy with the help of standardized grading scales to evaluate the treatment. However, such assessments are usually very subjective and they are prone to variance and inconsistency between physicians regarding their experience. We propose an automatic non-biased method using deep features combined with a linear regression method for facial palsy grading index prediction. With an extension of the free software tool Auto-eFace we annotated images of facial palsy patients and healthy subjects according to a common facial palsy grading scale. In our experiments, we obtained an average grading error of 11%
Jhonatan Contreras, Sven Sickert, Joachim Denzler:
Region-based Edge Convolutions with Geometric Attributes for the Semantic Segmentation of Large-scale 3D Point Clouds.
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.
13 (1) :
pp. 2598-2609.
2020.
[bibtex]
[pdf]
[web]
[doi]
[abstract]
In this paper, we present a semantic segmentation framework for large-scale 3D point clouds with high spatial resolution. For such data with huge amounts of points, the classification of each individual 3D point is an intractable task. Instead, we propose to segment the scene into meaningful regions as a first step. Afterward, we classify these segments using a combination of PointNet and geometric deep learning. This two-step approach resembles object-based image analysis. As an additional novelty, we apply surface normalization techniques and enrich features with geometric attributes. Our experiments show the potential of this approach for a variety of outdoor scene analysis tasks. In particular, we are able to reach 89.6\% overall accuracy and 64.4\% average intersection over union (IoU) in the Semantic3D benchmark. Furthermore, we achieve 66.7\% average IoU on Paris-Lille-3D. We also successfully apply our approach to the automatic semantic analysis of forestry data.
Jhonatan Contreras, Sven Sickert, Joachim Denzler:
Automatically Estimating Forestal Characteristics in 3D Point Clouds using Deep Learning.
iDiv Annual Conference.
2019.
Poster
[bibtex]
[web]
[abstract]
Biodiversity changes can be monitored using georeferenced and multitempo-ral data. Those changes refer to the process of automatically identifying differ-ences in the measurements computed over time. The height and the Diameterat Breast Height of the trees can be measured at different times. The mea-surements of individual trees can be tracked over the time resulting in growthrates, tree survival, among other possibles applications. We propose a deeplearning-based framework for semantic segmentation, which can manage largepoint clouds of forest areas with high spatial resolution. Our method divides apoint cloud into geometrically homogeneous segments. Then, a global feature isobtained from each segment, applying a deep learning network called PointNet.Finally, the local information of the adjacent segments is included through anadditional sub-network which applies edge convolutions. We successfully trainand test in a data set which covers an area with multiple trees. Two addi-tional forest areas were also tested. The semantic segmentation accuracy wastested using F1-score for four semantic classes:leaves(F1 = 0.908),terrain(F1 = 0.921),trunk(F1 = 0.848) anddead wood(F1 = 0.835). Furthermore,we show how our framework can be extended to deal with forest measurementssuch as measuring the height of the trees and the DBH.
Marie Arlt, Jack Peter, Sven Sickert, Clemens-Alexander Brust, Joachim Denzler, Andreas Stallmach:
Automated Polyp Differentiation on Coloscopic Data using Semantic Segmentation with CNNs.
Endoscopy.
51 (04) :
pp. 4.
2019.
[bibtex]
[web]
[doi]
[abstract]
Interval carcinomas are a commonly known problem in endoscopic adenoma detection, especially when they follow negative index colonoscopy. To prevent patients from these carcinomas and support the endoscopist, we reach for a live assisted system in the future, which helps to remark polyps and increase adenoma detection rate. We present our first results of polyp recognition using a machine learning approach.
Andreas Dittberner, Sven Sickert, Joachim Denzler, Orlando Guntinas-Lichius, Thomas Bitter, Sven Koscielny:
Development of an Automatic Image Analysis Method by Deep Learning Methods for the Detection of Head and Neck Cancer Based on Standard Real-Time Near-Infrared ICG Fluorescence Endoscopy Images (NIR-ICG-FE).
Laryngo-Rhino-Otologie.
97 (S02) :
pp. 97.
2018.
[bibtex]
[web]
[doi]
[abstract]
Improving the gold standard in the diagnosis of head and neck cancer using white light and invasive biopsy with digital image recognition procedures, there is a need for a development of new technologies. In the sense of an "optical biopsy", they in vivo and online should provide additional objective information for decision making for the head and neck surgeon. Artificial neural networks in combination with machine learning might be a helpful and fast approach.
Niclas Schmitt, Sven Sickert, Orlando Guntinas-Lichius, Thomas Bitter, Joachim Denzler:
Automated MRI Volumetry of the Olfactory Bulb.
Laryngo-Rhino-Otologie.
97 (S02) :
pp. 36.
2018.
[bibtex]
[web]
[doi]
[abstract]
The olfactory bulb (OB) as part of the olfactory pathway plays a central role in odor perception. Several studies have already established a connection between an olfactory impairment and the occurrence of neurodegenerative diseases (Parkinson's disease, Alzheimer's disease, etc.). This impairment is often detectable years before further symptoms. Moreover, it is connected to a volume loss of the OB. Therefore, in future the volume of the OB could contribute as a marker for detection and diagnosis of such diseases. Despite this great importance, there is currently no standard procedure for the volumetric analysis of the OB and above all no objective investigator-independent measurement methods.
Sven Sickert, Joachim Denzler:
Semantic Segmentation of Outdoor Areas using 3D Moment Invariants and Contextual Cues.
German Conference on Pattern Recognition (GCPR).
Pages 165-176.
2017.
[bibtex]
[pdf]
[doi]
[abstract]
In this paper, we propose an approach for the semantic segmentation of a 3D point cloud using local 3D moment invariants and the integration of contextual information. Specifically, we focus on the task of analyzing forestal and urban areas which were recorded by terrestrial LiDAR scanners. We demonstrate how 3D moment invariants can be leveraged as local features and that they are on a par with established descriptors. Furthermore, we show how an iterative learning scheme can increase the overall quality by taking neighborhood relationships between classes into account. Our experiments show that the approach achieves very good results for a variety of tasks including both binary and multi-class settings.
Clemens-Alexander Brust, Sven Sickert, Marcel Simon, Erik Rodner, Joachim Denzler:
Neither Quick Nor Proper -- Evaluation of QuickProp for Learning Deep Neural Networks.
2016.
Technical Report TR-FSU-INF-CV-2016-01
[bibtex]
[pdf]
[abstract]
Neural networks and especially convolutional neural networks are of great interest in current computer vision research. However, many techniques, extensions, and modifications have been published in the past, which are not yet used by current approaches. In this paper, we study the application of a method called QuickProp for training of deep neural networks. In particular, we apply QuickProp during learning and testing of fully convolutional networks for the task of semantic segmentation. We compare QuickProp empirically with gradient descent, which is the current standard method. Experiments suggest that QuickProp can not compete with standard gradient descent techniques for complex computer vision tasks like semantic segmentation.
Gianluca Tramontana, Martin Jung, Christopher R. Schwalm, Kazuhito Ichii, Gustau Camps-Valls, Botond Raduly, Markus Reichstein, M. Altaf Arain, Alessandro Cescatti, Gerard Kiely, Lutz Merbold, Penelope Serrano-Ortiz, Sven Sickert, Sebastian Wolf, and Dario Papale:
Predicting Carbon Dioxide and Energy Fluxes Across Global FLUXNET Sites with Regression Algorithms.
Biogeosciences.
13 (14) :
pp. 4291-4313.
2016.
[bibtex]
[web]
[doi]
[abstract]
Spatio-temporal fields of land–atmosphere fluxes derived from data-driven models can complement simulations by process-based land surface models. While a number of strategies for empirical models with eddy-covariance flux data have been applied, a systematic intercomparison of these methods has been missing so far. In this study, we performed a cross-validation experiment for predicting carbon dioxide, latent heat, sensible heat and net radiation fluxes across different ecosystem types with 11 machine learning (ML) methods from four different classes (kernel methods, neural networks, tree methods, and regression splines). We applied two complementary setups: (1) 8-day average fluxes based on remotely sensed data and (2) daily mean fluxes based on meteorological data and a mean seasonal cycle of remotely sensed variables. The patterns of predictions from different ML and experimental setups were highly consistent. There were systematic differences in performance among the fluxes, with the following ascending order: net ecosystem exchange (R2 < 0.5), ecosystem respiration (R2 > 0.6), gross primary production (R2> 0.7), latent heat (R2 > 0.7), sensible heat (R2 > 0.7), and net radiation (R2 > 0.8). The ML methods predicted the across-site variability and the mean seasonal cycle of the observed fluxes very well (R2 > 0.7), while the 8-day deviations from the mean seasonal cycle were not well predicted (R2 < 0.5). Fluxes were better predicted at forested and temperate climate sites than at sites in extreme climates or less represented by training data (e.g., the tropics). The evaluated large ensemble of ML-based models will be the basis of new global flux products.
Sven Sickert, Erik Rodner, Joachim Denzler:
Semantic Volume Segmentation with Iterative Context Integration for Bio-medical Image Stacks.
Pattern Recognition and Image Analysis. Advances in Mathematical Theory and Applications (PRIA).
26 (1) :
pp. 197-204.
2016.
[bibtex]
[pdf]
[abstract]
Automatic recognition of biological structures like membranes or synapses is important to analyze organic processes and to understand their functional behavior. To achieve this, volumetric images taken by electron microscopy or computer tomography have to be segmented into meaningful semantic regions. We are extending iterative context forests which were developed for 2D image data to image stack segmentation. In particular, our method is able to learn high-order dependencies and import contextual information, which often can not be learned by conventional Markov random field approaches usually used for this task. Our method is tested on very different and challenging medical and biological segmentation tasks.
Clemens-Alexander Brust, Sven Sickert, Marcel Simon, Erik Rodner, Joachim Denzler:
Convolutional Patch Networks with Spatial Prior for Road Detection and Urban Scene Understanding.
International Conference on Computer Vision Theory and Applications (VISAPP).
Pages 510-517.
2015.
[bibtex]
[pdf]
[doi]
[abstract]
Classifying single image patches is important in many different applications, such as road detection or scene understanding. In this paper, we present convolutional patch networks, which are convolutional networks learned to distinguish different image patches and which can be used for pixel-wise labeling. We also show how to incorporate spatial information of the patch as an input to the network, which allows for learning spatial priors for certain categories jointly with an appearance model. In particular, we focus on road detection and urban scene understanding, two application areas where we are able to achieve state-of-the-art results on the KITTI as well as on the LabelMeFacade dataset. Furthermore, our paper offers a guideline for people working in the area and desperately wandering through all the painstaking details that render training CNs on image patches extremely difficult.
Clemens-Alexander Brust, Sven Sickert, Marcel Simon, Erik Rodner, Joachim Denzler:
Clemens-Alexander Brust, Sven Sickert, Marcel Simon, Erik Rodner, Joachim Denzler.
2015.
Poster presentation and extended abstract
[bibtex]
[pdf]
[abstract]
In this paper, we present convolutional patch networks, which are convolutional (neural) networks (CNN) learned to distinguish different image patches and which can be used for pixel-wise labeling. We show how to easily learn spatial priors for certain categories jointly with their appearance. Experiments for urban scene understanding demonstrate state-of-the-art results on the LabelMeFacade dataset. Our approach is implemented as a new CNN framework especially designed for semantic segmentation with fully-convolutional architectures.
Martin Jung, Kazuhito Ichii, Gustau Camps-Valls, Dario Papale, Gianluca Tramontana, Sven Sickert, Christopher Schwalm, Markus Reichstein:
An ensemble of global high-resolution products of energy fluxes over land.
International Scientific Conference on the Global Water and Energy Cycle (GEWEX).
2014.
Poster
[bibtex]
[abstract]
We present an ensemble of global high-resolution energy flux products over land derived from upscaling FLUXNET eddy covariance observations with multiple machine learning methods using an array of remote sensing data. The products cover latent heat, sensible heat, ground heat fluxes, as well as net radiation over the period 2001-2012 at 8 daily temporal and 0.0833 degree spatial resolution. To account for the energy balance closure gap of eddy covariance measurements, five different energy balance correction techniques were used that correspond to different hypothesis of the causes of the energy balance closure gap. Hence, in total six different variants of sensible and latent heat flux products are available that allow quantifying uncertainties. We evaluate our products using cross-validation at site level and against various independent observation based data streams including latent and sensible heat fluxes derived from runoff, precipitation, and net radiation data from large river basins. Our products are a valuable source to evaluate or calibrate global land surface models. In conjunction with a complementary set of products for global carbon fluxes, our products are suitable to better understand the global variability of the land water, energy, and carbon cycles especially with regard to their co-variations and interactions.
Sven Sickert, Erik Rodner, Joachim Denzler:
Semantic Volume Segmentation with Iterative Context Integration.
Open German-Russian Workshop on Pattern Recognition and Image Understanding (OGRW).
Pages 220-225.
2014.
[bibtex]
[pdf]
[web]
[abstract]
Automatic recognition of biological structures like membranes or synapses is important to analyze organic processes and to understand their functional behavior. To achieve this, volumetric images taken by electron microscopy or computed tomography have to be segmented into meaningful regions. We are extending iterative context forests which were developed for 2D image data for image stack segmentation. In particular, our method s able to learn high order dependencies and import contextual information, which often can not be learned by conventional Markov random field approaches usually used for this task. Our method is tested for very different and challenging medical and biological segmentation tasks.
