Institute of
Creative\Media/Technologies

Team

FH-Prof. Priv.-Doz. Dipl.-Ing. Mag. Dr. Matthias Zeppelzauer

  • Head of
    Media Computing Research Group
    Institute of Creative\Media/Technologies
  • Department of Media and Digital Technologies
Location: A - Campus-Platz 1
M: +43/676/847 228 652

Study programmes

  • Data Intelligence (MA)
  • Creative Computing (BA)
  • Data Science and Artificial Intelligence* (BA)
  • Media Technology (BA)

Departments

  • Computer Science and Security
  • Media and Digital Technologies

Research Vision

“Performing innovative human-centered research on AI across disciplines to serve the social good.”

Matthias Zeppelzauer is a professor for computer vision, multimedia retrieval and machine learning with a special focus on human-centered approaches. In his research he focuses on the development of methods for the retrieval of semantically meaningful information from different types of media including visual and acoustic data, 3D data, (medical) time series data, textual data as well as multimodal data, e.g. from social media platforms. Cross-sectional topics in his research represent interactive machine learning (human in the loop learning) and explainable machine learning. He holds habilitation from TU Wien and has co-authored more than 90 publications.
Full List of Publications

Research Interests

  • Human-Centered and Trustworthy AI
  • Computer Vision and Image Understanding
  • Content-based Audio, Image and Video Retrieval
  • Multimodal Media Retrieval and Learning
  • Environmental Sound Recognition
  • Social Media Analysis
  • Pattern Mining

Trust AI - A platform for interactive and trustworthy artificial intelligence.

Explainable and trustworthy AI solution in an easy-to-use platform for SMEs.

EyeQTrack - Quantitative Eye-Tracking Analytics for Adaptive XR Training & Rehabilitation in Healthcare

A self-adaptive eXtended reality environment for training and therapeutic purposes.

FAIRAI

Strengthening Austria's Innovation Capabilities and Research Excellence in Artificial Intelligence.

JHML - Joint Human Machine Learning for Exploratory Data Analysis

Combining Machine Learning with Methods of Visualization for Exploratory Data Analysis.

AniVision

Animation in Ephemeral Films from Austria, East & West Germany between 1945 and 1989: A Combined Film Analysis and Computer Vision Approach

deepForce - Pushing the limits of rapid estimation of knee joint contact force estimation in clinical gait analysis by Machine and Deep Learning

Machine learning methods to enable more clinicians to use data obtained by gait analyses for diagnosis.

CounterSpeech - Young People Against Online Hate

Computer-assisted Strategies for Facilitating Citizen-generated Counter Speech in Social Media

IMREA - Intelligent Multimodal Real Estate Assessment

Multimodal information extraction and machine learning techniques for the extraction of real estate related attributes and parameters from heterogeneous input data

BIMCheck – Intelligent and Automated Target-Performance Comparisons in the Building Industry.

Modern sensor technologies and image processing tools to track changes on a construction site.

FIVE - #Fitspiration Image VErification

Proof of Concept of an interdisciplinary online-course offering guidance on how to deal critically with information provided by social media sites.

QUAKE-iP - Quality Control and Evaluation in Production

Using sensor technologies and computer vision to examine the quality of metal profiles.

HIPstar

Evaluation of the accuracy of non-invasive hip joint centre estimation methods for clinical gait analysis in children and adolescents

Plant Monitoring AI

Leveraging machine learning and predictive analytics for early detection of plant stress for the benefit of sustainability in farming

IntelliGait 3D- Gait Data Mining

Establishing advanced analysis methods for modelling, classification and similarity retrieval of gait patterns to enable novel data-driven ways to access 3D gait databases

Scribe ID AI

Active Machine Learning for automatic identification of handwriting in 12th century manuscripts

ReMoCap-Lab

The „Laboratory for Capturing Motion and Augmenting Environment in Motor Rehabilitation“ will enable innovative projects and excellent research in Austria

QuickSpeech - Automatic Question and Answer Generation

Automatic generation of questions and answers for an app that companies can use to train their staff members.

SAiEX - Safe Artificial Intelligence with integrated explainable integrity level

Exploring ways to better understand decisions made by artificial intelligence

Trading Cultures

An ethnography of international trade fairs for television programs, music and books

Big-Data Analytics

Developing methods for the analysis of large amounts of data without compromising data protection.

Data Science Bootcamp

Training experts from within companies to become Data Scientists who are able to the best use of artificial intelligence methods

WiKant-Knowledge-based production of profiles

Optimising production through automation of the entire process chain

ImmBild - Location Assessment by Computer Vision

Location is key – especially when it comes to real estate value. “ImmBild” aims at developing a new method for estimating property value using computer vision of satellite data.

SoniControl 2.0 - The first Ultrasonic Firewall

Extending SoniControl, the first ultrasonic firewall, that detects and blocks unwanted acoustic tracking on mobile devices.

SAMBA - Smart Data for Music Business Administration

The project aims at exploring the economic value of social media data for the music industry.

360 AI

Developing a method for efficient object recognition in 360° images

InfraBase - Automatic Building Footprint Segmentation

The project deals with the fully automatic analysis of satellite imagery. The goal is to extract a pixel-accurate segmentation of building roofs to generate a rich meta-data layer.

IntelliGait – Intelligent Gait Analysis

Automatic gait pattern analysis for robust classification of functional deficits. Intelligait aims at developing automated methods to analyze and classify gait patterns.

Object Recognition for Indoor Navigation

Object recognition for autonomous indoor positioning and navigation

SoniTalk - an Open Protocol for Data-over-Sound

While interconnectedness amongst our devices increases rapidly, SoniTalk aims at developing an open protocol for ultrasonic device communication that fully preserves the privacy of the user.

ImmoAge - Visual Age Prediction of Real Estate

Year of construction, architectural period and architectural style have a significant impact on property prices. New methods of classifying and evaluating real estate have been developed on the basis ...

Ressel Center: Horizons of personalized music therapy 1

Investigating how a better evaluation of biological measurement data can support therapeutic measures.

SoniControl - the first ultrasonic firewall

The project SoniControl aims at developing an application to detect and block unwanted audio tracking on mobile devices.

Pitoti 3D

Italy’s petroglyphs were carved into rock faces by prehistoric cultures. This project sets out to investigate and document the 3D nature of these petroglyphs for the first time.

Digital interactive display window application

Concept development for gesture controlled product presentation at the point-of-sale

Deep Tagging - Automatic Image Tagging by Deep Learning

Visual Heritage

Visual Analytics and Computer Vision Meet Cultural Heritage.

Selected Publications

Download Bibtex for all results
Matt, M., Zeppelzauer, M., & Waldner, M. (2024). cVIL: Class-Centric Visual Interactive Labeling. Proceedings of the 15th International EuroVis Workshop on Visual Analytics (EuroVA). 15th International EuroVis Workshop on Visual Analytics (EuroVA), Odense, Denmark. http://arxiv.org/abs/2405.08150
Slijepcevic, D., Horst, F., Lapuschkin, S., Horsak, B., Raberger, A.-M., Kranzl, A., Samek, W., Breitender, C., Schöllhorn, W., & Zeppelzauer, M. (2022). Explaining Machine Learning Models for Clinical Gait Analysis. ACM Transactions on Computing for Healthcare, 3(2), 14:1-14:27. https://doi.org/10.1145/3474121
Baumhauer, T., Schöttele, P., & Zeppelzauer, M. (2022). Machine Unlearning: Linear Filtration for Logit-based Classifiers. Journal on Machine Learning, 111(1), 3203–3226. https://doi.org/10.1007/s10994-022-06178-9
Beckmann, Rafael, Blaga, C., El-Assady, M., Zeppelzauer, M., & Bernard, J. (2022). Interactive Visual Explanation of Incremental Data Labeling. EuroVis Workshop on Visual Analytics (EuroVA), 6. https://doi.org/10.2312/eurova.20221073
Baumhauer, T., Slijepcevic, D., & Zeppelzauer, M. (2022). Bounded logit attention: Learning to explain image classifiers. NeurIPS 2022 Workshop: All Things Attention: Bridging Different Perspectives on Attention, New Orleans, USA. https://arxiv.org/pdf/2105.14824
Slijepčević, D., Henzl, M., Klausner, L. D., Dam, T., Kieseberg, P., & Zeppelzauer, M. (2021). k‑Anonymity in Practice: How Generalisation and Suppression Affect Machine Learning Classifiers. Computers & Security, 111, 19. https://doi.org/10.1016/j.cose.2021.102488
Bernard, J., Hutter, M., Zeppelzauer, M., Sedlmair, M., & Munzner, T. (2021). ProSeCo: Visual analysis of class separation measures and dataset characteristics. Computers & Graphics, 96, 48–60. https://doi.org/https://doi.org/10.1016/j.cag.2021.03.004
Bernard, Jürgen, Hutter, M., Sedlmair, M., Zeppelzauer, Matthias, & Munzner, Tamara. (2021). A Taxonomy of Property Measures to Unify Active Learning and Human-centered Approaches to Data Labeling. ACM Transactions on Interactive Intelligent Systems (TiiS), 11(3–4), 1–42. https://doi.org/10/gnt2wf
Zielinski, B., Lipinski, M., Juda, M., Zeppelzauer, Matthias, & Dlotko, Pawel. (2021). Persistence Codebooks for Topological Data Analysis. Journal of Artificial Intelligence Review, 54, 1969–2009. https://doi.org/https://doi.org/10.1007/s10462-020-09897-4
Kirchknopf, A., Slijepcevic, D., & Zeppelzauer, M. (2021). Multimodal Detection of Information Disorder from Social Media. International Conference on Content-Based Multimedia Indexing (CBMI), 4. https://doi.org/10/gmxnm5
Horsak, B., Slijepcevic, D., Raberger, A.-M., Schwab, C., Worisch, M., & Zeppelzauer, M. (2020). GaitRec, a large-scale ground reaction force dataset of healthy and impaired gait. Scientific Data, 7:143(1), 1–8. https://doi.org/10/gh372d
Bernard, Jürgen, Hutter, M., Sedlmair, M., Zeppelzauer, Matthias, & Munzner, Tamara. (2019). A taxonomy of property measures to support the explainability of the interactive data labeling process. ACM Transactions on Interactive Intelligent Systems (TiiS), Submitted.
Zielinski, B., Lipinski, Michal, Juda, M., Zeppelzauer, M., & Dlotko, Pawel. (2019). Persistence Bag-of-Words for Topological Data Analysis. Proceedings of the International Joint Conference on Artificial Intelligence 2019, 6. https://doi.org/10/ghpp7z
Wagner, M., Slijepcevic, D., Horsak, B., Rind, A., Zeppelzauer, M., & Aigner, W. (2018). KAVAGait: Knowledge-Assisted Visual Analytics for Clinical Gait Analysis. IEEE Transactions on Visualization and Computer Graphics (TVCG), 25(3), 1528–1542. https://doi.org/10/ghppzn
Bernard, J., Zeppelzauer, M., Sedlmair, M., & Aigner, W. (2018). VIAL – A Unified Process for Visual-Interactive Labeling. The Visual Computer, 34(1189), 16. https://doi.org/10/gd5hr3
Slijepcevic, D., Zeppelzauer, M., Raberger, A.-M., Schwab, C., Schuller, M., Baca, A., Breiteneder, C., & Horsak, B. (2018). Automatic Classification of Functional Gait Disorders. IEEE Journal of Biomedical and Health Informatics, 5(22), 1653–1661. https://doi.org/10/ghz24w
Zeppelzauer, M., Despotovic, M., Sakeena, M., Koch, D., & Döller, M. (2018). Automatic Prediction of Building Age from Photographs. Proceedings of the ACM International Conference on Multimedia Retrieval (ICMR "18), 126–134. https://doi.org/10/ghpp2k
Bernard, J., Zeppelzauer, M., Lehmann, M., Müller, M., & Sedlmair, M. (2018). Towards User-Centered Active Learning Algorithms. Computer Graphics Forum, 37, 121–132. https://doi.org/10/gdw79h
Zeppelzauer, M., Zielinski, B., Juda, M., & Seidl, M. (2018). A Study on Topological Descriptors for the Analysis of 3D Surface Texture. Journal on Computer Vision and Image Understanding (CVIU), 167, 74–88. https://doi.org/10/ghpp2h
Bernard, Jürgen, Hutter, M., Zeppelzauer, M., Fellner, D., & Sedlmair, M. (2017). Comparing Visual-Interactive Labeling with Active Learning: An Experimental Study. IEEE Transactions on Visualization and Computer Graphics (TVCG), 24(1). https://doi.org/10/gcqb3r
Zeppelzauer, M., & Schopfhauser, D. (2016). Multimodal classification of events in social media. Image and Vision Computing. https://doi.org/10/ghpp2q
Zaharieva, M., Del Fabro, M., & Zeppelzauer, M. (2015). Cross-Platform Social Event Detection. IEEE Multimedia, 22(3), 14. https://doi.org/10/gh3773
Salvador, A., Zeppelzauer, M., Manchón-Vizuente, D., Calafell, A., & Giró-i-Nieto, X. (2015, April 28). Cultural Event Recognition with Visual ConvNets and Temporal Models. Proceedings of the CVPR Workshop ChaLearn Looking at People 2015. Computer Vision and Pattern Recognition (CVPR), Boston, Massachusetts, United States. http://arxiv.org/abs/1504.06567
Zaharieva, M., Zeppelzauer, M., Del Fabro, M., & Schopfhauser, D. (2015, March 24). Social Event Mining in Large Photo Collections. Proceedings of the International Conference on Multimedia Retrieval. ACM International Conference on Multimedia Retrieval, Shanghai, China.
Stöger, A., Heimann, G., Zeppelzauer, M., Ganswindt, A., Hensman, S., & Charlton, B. (2012). Visualizing Sound Emission of Elephant Vocalizations: Evidence for Two Rumble Production Types. Plos One, 7(11:e48907). http://dx.plos.org/10.1371/journal.pone.0048907
Mitrović, D., Zeppelzauer, M., & Breiteneder, C. (2010). Features for Content-Based Audio Retrieval. In Advances in Computers (Vol. 78, pp. 71–150). Burlington: Academic Press. http://www.sciencedirect.com/science/article/pii/S0065245810780037

Publication Browser