Florian Schmid
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Florian Schmid has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Gerhard Widmer
Johannes Kepler University Linz Austria
2 shared publications Arnoldas Jasonas
Meta Reality Labs Research, Menlo Park, CA, USA
1 shared publication- Camilla Clark
Meta Reality Labs Research, Menlo Park, CA, USA
1 shared publication Chi Ian Tang
Meta Reality Labs Research, Menlo Park, CA, USA
1 shared publicationChristoph Muessel
1 shared publicationCosmin Frateanu
Meta Reality Labs Research, Menlo Park, CA, USA
1 shared publication
Latest Publications
- 1 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33 (10709908) , 2340-2344
Sound Event Detection With Boundary-Aware Optimization and Inference
Temporal detection problems appear in many fields including time-series estimation, activity recognition and sound event detection (SED). In this work, we propose a new approach to temporal event modeling by explicitly modeling event onsets and offsets, and by introducing boundary-aware optimization and inference strategies that substantially enhance temporal event detection. The presented methodology incorporates new temporal modeling layers—Recurrent Event Detection (RED) and Event Proposal Network (EPN)—which, together with tailored loss functions, enable more effective and precise temporal event detection. We evaluate the proposed method in the SED domain using a subset of the temporally-strongly annotated portion of AudioSet. Experimental results show that our approach not only outperforms traditional frame-wise SED models with state-of-the-art post-processing, but also removes the need for post-processing hyperparameter tuning, and scales to achieve new state-of-the-art performance across all AudioSet Strong classes.
- 1 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33 (10709908) , 2340-2344
Sound Event Detection With Boundary-Aware Optimization and Inference
Temporal detection problems appear in many fields including time-series estimation, activity recognition and sound event detection (SED). In this work, we propose a new approach to temporal event modeling by explicitly modeling event onsets and offsets, and by introducing boundary-aware optimization and inference strategies that substantially enhance temporal event detection. The presented methodology incorporates new temporal modeling layers—Recurrent Event Detection (RED) and Event Proposal Network (EPN)—which, together with tailored loss functions, enable more effective and precise temporal event detection. We evaluate the proposed method in the SED domain using a subset of the temporally-strongly annotated portion of AudioSet. Experimental results show that our approach not only outperforms traditional frame-wise SED models with state-of-the-art post-processing, but also removes the need for post-processing hyperparameter tuning, and scales to achieve new state-of-the-art performance across all AudioSet Strong classes.
- Open Access
- 18 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 32 (23299290) , 2227-2241
Dynamic Convolutional Neural Networks as Efficient Pre-Trained Audio Models
The introduction of large-scale audio datasets, such as AudioSet, paved the way for Transformers to conquer the audio domain and replace CNNs as the state-of-the-art neural network architecture for many tasks. Audio Spectrogram Transformers are excellent at exploiting large datasets, creating powerful pre-trained models that surpass CNNs when fine-tuned on downstream tasks. However, current popular Audio Spectrogram Transformers are demanding in terms of computational complexity compared to CNNs. Recently, we have shown that, by employing Transformer-to-CNN Knowledge Distillation, efficient CNNs can catch up with and even outperform Transformers on large datasets. In this work, we extend this line of research and increase the capacity of efficient CNNs by introducing dynamic CNN blocks constructed of dynamic convolutions, a dynamic ReLU activation function, and Coordinate Attention. We show that these dynamic CNNs outperform traditional efficient CNNs, such as MobileNets, in terms of the performance–complexity trade-off at the task of audio tagging on the large-scale AudioSet. Our experiments further indicate that the proposed dynamic CNNs achieve competitive performance with Transformer-based models for end-to-end fine-tuning on downstream tasks while being much more computationally efficient.
- 18 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 32 (23299290) , 2227-2241
Open AccessDynamic Convolutional Neural Networks as Efficient Pre-Trained Audio Models
The introduction of large-scale audio datasets, such as AudioSet, paved the way for Transformers to conquer the audio domain and replace CNNs as the state-of-the-art neural network architecture for many tasks. Audio Spectrogram Transformers are excellent at exploiting large datasets, creating powerful pre-trained models that surpass CNNs when fine-tuned on downstream tasks. However, current popular Audio Spectrogram Transformers are demanding in terms of computational complexity compared to CNNs. Recently, we have shown that, by employing Transformer-to-CNN Knowledge Distillation, efficient CNNs can catch up with and even outperform Transformers on large datasets. In this work, we extend this line of research and increase the capacity of efficient CNNs by introducing dynamic CNN blocks constructed of dynamic convolutions, a dynamic ReLU activation function, and Coordinate Attention. We show that these dynamic CNNs outperform traditional efficient CNNs, such as MobileNets, in terms of the performance–complexity trade-off at the task of audio tagging on the large-scale AudioSet. Our experiments further indicate that the proposed dynamic CNNs achieve competitive performance with Transformer-based models for end-to-end fine-tuning on downstream tasks while being much more computationally efficient.
- 6 August 2015
- Published by The R Foundation
GiANT: Gene Set Uncertainty in Enrichment Analysis