List of Publications

Florian Henkel and Gerhard Widmer
Real-time Music Following in Score Sheet Images via Multi-resolution Prediction
Frontiers in Computer Science, 2021
Code

Florian Henkel and Gerhard Widmer
Multi-modal Conditional Bounding Box Regression for Music Score Following
In Proceedings of the 29th European Signal Processing Conference (EUSIPCO), 2021, Dublin, Ireland
Code

Florian Henkel, Rainer Kelz and Gerhard Widmer
Learning to Read and Follow Music in Complete Score Sheet Images
In Proceedings of the 21st International Society for Music Information Retrieval Conference, 2020, Montréal, Canada
Code

Florian Henkel, Stefan Balke, Matthias Dorfer and Gerhard Widmer
Score Following as a Multi-Modal Reinforcement Learning Problem
Transactions of the International Society for Music Information Retrieval, 2019
Code

Matthias Dorfer, Florian Henkel and Gerhard Widmer
Learning to Listen, Read, and Follow: Score Following as a Reinforcement Learning Game
In Proceedings of the 19th International Society for Music Information Retrieval Conference, 2018, Paris, France
Best Paper and Best Poster Presentation Award
Code

Florian Henkel, Stephanie Schwaiger and Gerhard Widmer
Fully Automatic Page Turning on Real Scores
Late Breaking/Demo at the 22nd International Society for Music Information Retrieval Conference, 2021, Online
Code

Khaled Koutini, Hamid Eghbal-zadeh, Florian Henkel, Jan Schlüter and Gerhard Widmer
Over-Parameterization and Generalization in Audio Classification
ICML 2021 Workshop on Overparameterization: Pitfalls & Opportunities

Hamid Eghbal-zadeh, Florian Henkel and Gerhard Widmer
Context-Adaptive Reinforcement Learning using Unsupervised Learning of Context Variables
In Proceedings of Machine Learning Research, NeurIPS 2020 Workshop on Pre-registration in Machine Learning, PMLR 148:236-254, 2021
Blog

Hamid Eghbal-zadeh, Florian Henkel and Gerhard Widmer
Learning to Infer Unseen Contexts in Causal Contextual Reinforcement Learning
Self-supervision for Reinforcement Learning (SSL-RL) Workshop ICLR, 2021, Vienna, Austria

Khaled Koutini, Florian Henkel, Hamid Eghbal-zadeh and Gerhard Widmer
Low-Complexity Models for Acoustic Scene Classification Based on Receptive Field Regularization and Frequency Damping
In Proceedings of the Detection and Classification of Acoustic Scenes and Events Workshop (DCASE), 2020, Tokyo, Japan

Florian Henkel, Rainer Kelz and Gerhard Widmer
Audio-Conditioned U-Net for Position Estimation in Full Sheet Images
In Proceedings of the 2nd International Workshop on Reading Music Systems, 2019, Delft, The Netherlands
Code

Carlos Eduardo Cancino-Chacón, Stefan Balke, Florian Henkel, Christian Stussak and Gerhard Widmer
The Con Espressione! Exhibit : Exploring Human-Machine Collaboration in Expressive Performance
Late Breaking/Demo at the 20th International Society for Music Information Retrieval Conference, 2019, Delft, The Netherlands

Khaled Koutini, Florian Henkel, Hamid Eghbal-zadeh and Gerhard Widmer
CP-JKU Submissions to DCASE’20: Low-Complexity Cross-Device Acoustic Scene Classification with RF-Regularized CNN
DCASE2020 Challenge
1st & 2nd place on Task 1B: Low-Complexity Acoustic Scene Classification

Drop me a mail, checkout my projects on GitHub or head over to Google Scholar for my latest research.

• florian.henkel@jku.at
• Github
• Google Scholar
• Linz, Austria