A5019419833- Neural dynamics and brain function
- Neural Networks and Applications
- Image Retrieval and Classification Techniques
- Aesthetic Perception and Analysis
- Face Recognition and Perception
- Visual Attention and Saliency Detection
- Generative Adversarial Networks and Image Synthesis
- Visual perception and processing mechanisms
- Artificial Intelligence in Games
- Evolutionary Algorithms and Applications
- Advanced Image and Video Retrieval Techniques
- Gaze Tracking and Assistive Technology
- Reinforcement Learning in Robotics
- Digital Media Forensic Detection
- Color Science and Applications
- Speech and Audio Processing
- Action Observation and Synchronization
- Radiomics and Machine Learning in Medical Imaging
- Domain Adaptation and Few-Shot Learning
- Face recognition and analysis
- Glioma Diagnosis and Treatment
- Cultural Heritage Materials Analysis
- Video Surveillance and Tracking Methods
- Deception detection and forensic psychology
- Advanced Neural Network Applications
Tilburg University
2014-2025
Arq Psychotrauma Expert Group
2020-2023
Jeroen Bosch Ziekenhuis
2021
Radboud University Nijmegen
2021
Radboud University Medical Center
2021
Sint Maartenskliniek
2021
Institute for Cognitive Science Studies
2018-2019
Maastricht University
2000-2011
Japan External Trade Organization
1991-2006
Research Institute for Knowledge Systems
2003-2005
A survey of the literature reveals that image processing tools aimed at supplementing art historian's toolbox are currently in earliest stages development. To jump-start development such methods, Van Gogh and Kroller-Muller museums The Netherlands agreed to make a data set 101 high-resolution gray-scale scans paintings within their collections available groups researchers from several different universities. This article describes approaches brushwork analysis artist identification developed...
Convolutional Neural Networks (CNNs) require large image corpora to be trained on classification tasks. The variation in resolutions, sizes of objects and patterns depicted, scales, hampers CNN training performance, because the task-relevant information varies over spatial scales. Previous work attempting deal with such scale variations focused encouraging scale-invariant representations. However, representations are incomplete images, images contain scale-variant as well. This paper...
Abstract Quantifying plastic pollution on surface water is essential to understand and mitigate the impact of environment. Current monitoring methods such as visual counting are labor intensive. This limits feasibility scaling long‐term at multiple locations. We present an automated method for that overcomes this limitation. Floating macroplastics detected from images using deep learning. perform experimental evaluation our bridge‐mounted cameras five different river locations across...
Author attribution through the recognition of visual characteristics is a commonly used approach by art experts. By studying vast number artworks, experts acquire ability to recognize unique artists. In this article, we present an that uses same principles discover characteristic features determine artist?s touch. training convolutional neural network (PigeoNET) on large collection digitized artworks perform task automatic artist attribution, encouraged artist-specific features. The trained...
To compare the performance of a convolutional neural network (CNN) to that 11 radiologists in detecting scaphoid bone fractures on conventional radiographs hand, wrist, and scaphoid.At two hospitals (hospitals A B), three datasets consisting were retrospectively retrieved: dataset 1039 (775 patients [mean age, 48 years ± 23 {standard deviation}; 505 female patients], period: 2017-2019, B) for developing segmentation CNN, 3000 (1846 42 22; 937 2003-2019, hospital fracture detection 190 (190...
In this conceptual paper, we demonstrate how modern data science techniques can advance our understanding of important decisions in the context entrepreneurship that involve social interactions. We know individuals’ decision-making is strongly affected by nonverbal behavior. The emerging domain signal processing aims at accurate computerized analysis such Behavioral cues stemming from, for example, gestures, posture, facial expressions, and vocal expressions now be detected analyzed...
In this paper, we elaborate on how AI can support diversity and inclusion exemplify research projects conducted in that direction. We start by looking at the challenges progress making large language models (LLMs) more transparent, inclusive, aware of social biases. Even though LLMs like ChatGPT have impressive abilities, they struggle to understand different cultural contexts engage meaningful, human conversations. A key issue is biases processing, especially machine translation, reinforce...
Abstract Introduction Patients with a glioma often suffer from cognitive impairments both before and after anti-tumor treatment. Ideally, clinicians can rely on predictions of post-operative functioning for individual patients based information obtainable surgery. Such would facilitate selecting the optimal treatment considering patients’ onco-functional balance. Method Cognitive three months surgery was predicted 317 across eight tests. Nine multivariate Bayesian regression models were used...
Surface texture is a critical feature in the manufacture, marketing, and use of photographic paper. Raking light reveals through stark rendering highlights shadows. Though close-up raking images effectively document surface features paper, sheer number diversity textures used for historic papers prohibits efficient visual classification. This work provides evidence that automatic, computer-based classification documented with feasible by demonstrating an encouraging degree success sorting...
Previous research has shown that Artificial Intelligence is capable of distinguishing between authentic paintings by a given artist and human-made forgeries with remarkable accuracy, provided sufficient training. However, the limited amount existing known forgeries, augmentation methods for forgery detection are highly desirable. In this work, we examine potential incorporating synthetic artworks into training datasets to enhance performance detection. Our investigation focuses on Vincent...
Precisely estimating a child's body measurements and weight from single image is useful in pediatrics for monitoring growth detecting early signs of malnutrition. The development estimation models this task hampered by the unavailability labeled dataset to support supervised learning. This paper introduces "Age-Restricted Anonymized" (ARAN) dataset, first children with approved an ethics committee under European General Data Protection Regulation guidelines. ARAN consists images 512 aged 16...
The problem of outlier detection is well studied in the fields Machine Learning (ML) and Knowledge Discovery Databases (KDD). Both have their own methods evaluation procedures. In ML, Support Vector Machines Parzen Windows are well-known that can be used for detection. KDD, heuristic local-density estimation LOF LOCI generally considered to superior outlier-detection methods. Hitherto, performances these ML KDD not been compared. This paper formalizes framework one-class classification...
Abstract In recent years, transformers, initially developed for language, have been successfully applied to visual tasks. Vision transformers shown push the state of art in a wide range tasks, including image classification, object detection, and semantic segmentation. While ample research has promising results attribution authentication tasks using convolutional neural networks, this paper examines whether superiority vision extends authentication, improving, thus, reliability...
In an experimental study, we explored the role of auditory perception bias in vocal pitch imitation. Psychoacoustic tasks involving a missing fundamental indicate that some listeners are attuned to relationship between all higher harmonics present signal, which supports their frequency (the primary acoustic correlate pitch). Other focus on lowest harmonic constituents complex sound signal may hamper fundamental. These two listener types referred as and spectral listeners, respectively. We...