110 citations · 334 across the 23 of their papers we have counts for
23 papers
Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models
Nikolai Röhrich, Julian Gleißner, Ahmed H. A. Ibrahim +2
Semantic segmentation models struggle with data sparsity and rare or visually diverse regions, e.g., dense regions or small objects in aerial or autonomous mobility data. While syn…
Video Joint-Embedding Predictive Architectures for Facial Expression Recognition
Lennart Eing, Cristina Luna-Jiménez, Silvan Mertes +1
This paper introduces a novel application of Video Joint-Embedding Predictive Architectures (V-JEPAs) for Facial Expression Recognition (FER). Departing from conventional pre-train…
VoiceX: A Text-To-Speech Framework for Custom Voices
Silvan Mertes, Daksitha Withanage Don, Otto Grothe +3
Modern TTS systems are capable of creating highly realistic and natural-sounding speech. Despite these developments, the process of customizing TTS voices remains a complex task, m…
Relevant Irrelevance: Generating Alterfactual Explanations for Image Classifiers
Silvan Mertes, Tobias Huber, Christina Karle +4
In this paper, we demonstrate the feasibility of alterfactual explanations for black box image classifiers. Traditional explanation mechanisms from the field of Counterfactual Thin…
The AffectToolbox: Affect Analysis for Everyone
Silvan Mertes, Dominik Schiller, Michael Dietz +2
In the field of affective computing, where research continually advances at a rapid pace, the demand for user-friendly tools has become increasingly apparent. In this paper, we pre…
Giving Robots a Voice: Human-in-the-Loop Voice Creation and open-ended Labeling
Pol van Rijn, Silvan Mertes, Kathrin Janowski +3
Speech is a natural interface for humans to interact with robots. Yet, aligning a robot's voice to its appearance is challenging due to the rich vocabulary of both modalities. Prev…
The STOIC2021 COVID-19 AI challenge: applying reusable training methodologies to private data
Luuk H. Boulogne, Julian Lorenz, Daniel Kienzle +35
Challenges drive the state-of-the-art of automated medical image analysis. The quantity of public training data that they provide can limit the performance of their solutions. Publ…
Towards Automated COVID-19 Presence and Severity Classification
Dominik Müller, Niklas Schröter, Silvan Mertes +6
COVID-19 presence classification and severity prediction via (3D) thorax computed tomography scans have become important tasks in recent times. Especially for capacity planning of…
GANonymization: A GAN-based Face Anonymization Framework for Preserving Emotional Expressions
Fabio Hellmann, Silvan Mertes, Mohamed Benouis +5
In recent years, the increasing availability of personal data has raised concerns regarding privacy and security. One of the critical processes to address these concerns is data an…
ForDigitStress: A multi-modal stress dataset employing a digital job interview scenario
Alexander Heimerl, Pooja Prajod, Silvan Mertes +7
We present a multi-modal stress dataset that uses digital job interviews to induce stress. The dataset provides multi-modal data of 40 participants including audio, video (motion c…
GANterfactual-RL: Understanding Reinforcement Learning Agents' Strategies through Visual Counterfactual Explanations
Tobias Huber, Maximilian Demmler, Silvan Mertes +2
Counterfactual explanations are a common tool to explain artificial intelligence models. For Reinforcement Learning (RL) agents, they answer "Why not?" or "What if?" questions by i…
Wish You Were Here: Mental and Physiological Effects of Remote Music Collaboration in Mixed Reality
Ruben Schlagowski, Dariia Nazarenko, Yekta Can +4
With face-to-face music collaboration being severely limited during the recent pandemic, mixed reality technologies and their potential to provide musicians a feeling of "being the…
An Overview of Affective Speech Synthesis and Conversion in the Deep Learning Era
Andreas Triantafyllopoulos, Björn W. Schuller, Gökçe İymen +9
Speech is the fundamental mode of human communication, and its synthesis has long been a core priority in human-computer interaction research. In recent years, machines have manage…
An Efficient Multitask Learning Architecture for Affective Vocal Burst Analysis
Tobias Hallmen, Silvan Mertes, Dominik Schiller +1
Affective speech analysis is an ongoing topic of research. A relatively new problem in this field is the analysis of vocal bursts, which are nonverbal vocalisations such as laughs…
Alterfactual Explanations -- The Relevance of Irrelevance for Explaining AI Systems
Silvan Mertes, Christina Karle, Tobias Huber +3
Explanation mechanisms from the field of Counterfactual Thinking are a widely-used paradigm for Explainable Artificial Intelligence (XAI), as they follow a natural way of reasoning…
"GAN I hire you?" -- A System for Personalized Virtual Job Interview Training
Alexander Heimerl, Silvan Mertes, Tanja Schneeberger +6
Job interviews are usually high-stakes social situations where professional and behavioral skills are required for a satisfactory outcome. Professional job interview trainers give…
Alternative Data Augmentation for Industrial Monitoring using Adversarial Learning
Silvan Mertes, Andreas Margraf, Steffen Geinitz +1
Visual inspection software has become a key factor in the manufacturing industry for quality control and process monitoring. Semantic segmentation models have gained importance sin…
Intercategorical Label Interpolation for Emotional Face Generation with Conditional Generative Adversarial Networks
Silvan Mertes, Dominik Schiller, Florian Lingenfelser +4
Generative adversarial networks offer the possibility to generate deceptively real images that are almost indistinguishable from actual photographs. Such systems however rely on th…
VoiceMe: Personalized voice generation in TTS
Pol van Rijn, Silvan Mertes, Dominik Schiller +5
Novel text-to-speech systems can generate entirely new voices that were not seen during training. However, it remains a difficult task to efficiently create personalized voices fro…
Dynamic Difficulty Adjustment in Virtual Reality Exergames through Experience-driven Procedural Content Generation
Tobias Huber, Silvan Mertes, Stanislava Rangelova +2
Virtual Reality (VR) games that feature physical activities have been shown to increase players' motivation to do physical exercise. However, for such exercises to have a positive…
Exploring emotional prototypes in a high dimensional TTS latent space
Pol van Rijn, Silvan Mertes, Dominik Schiller +4
Recent TTS systems are able to generate prosodically varied and realistic speech. However, it is unclear how this prosodic variation contributes to the perception of speakers' emot…
GANterfactual - Counterfactual Explanations for Medical Non-Experts using Generative Adversarial Learning
Silvan Mertes, Tobias Huber, Katharina Weitz +2
With the ongoing rise of machine learning, the need for methods for explaining decisions made by artificial intelligence systems is becoming a more and more important topic. Especi…
Embedded Emotions -- A Data Driven Approach to Learn Transferable Feature Representations from Raw Speech Input for Emotion Recognition
Dominik Schiller, Silvan Mertes, Elisabeth André
Traditional approaches to automatic emotion recognition are relying on the application of handcrafted features. More recently however the advent of deep learning enabled algorithms…