Tommaso Apicella
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Tommaso Apicella has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Edoardo Ragusa
Department of Electrical, Electronic, Telecommunications Engineering and Naval Architecture, University of Genoa, Genoa, Italy
2 shared publications - Paolo Gastaldo
DITEN, University of Genoa, Genoa, Italy
2 shared publications - Alessio Canepa
Department of Electrical, Electronic and Telecommunications Engineering, and Naval Architecture, DITEN, University of Genoa
1 shared publication - Andrea Albanese
University of Trento
1 shared publication - Davide Brunelli
University of Trento
1 shared publication - Edoardo Ragusa
University of Genoa
1 shared publication
Latest Publications
- 4 September 2022
- Published by Springer Nature
- p. 137-147
Design and Deployment of an Efficient Landing Pad Detector
- 4 September 2022
- Published by Springer Nature
- p. 137-147
Design and Deployment of an Efficient Landing Pad Detector
- Open Access
Emotion Recognition on Edge Devices: Training and Deployment
Emotion recognition, among other natural language processing tasks, has greatly benefited from the use of large transformer models. Deploying these models on resource-constrained devices, however, is a major challenge due to their computational cost. In this paper, we show that the combination of large transformers, as high-quality feature extractors, and simple hardware-friendly classifiers based on linear separators can achieve competitive performance while allowing real-time inference and fast training. Various solutions including batch and Online Sequential Learning are analyzed. Additionally, our experiments show that latency and performance can be further improved via dimensionality reduction and pre-training, respectively. The resulting system is implemented on two types of edge device, namely an edge accelerator and two smartphones.
Open AccessEmotion Recognition on Edge Devices: Training and Deployment
Emotion recognition, among other natural language processing tasks, has greatly benefited from the use of large transformer models. Deploying these models on resource-constrained devices, however, is a major challenge due to their computational cost. In this paper, we show that the combination of large transformers, as high-quality feature extractors, and simple hardware-friendly classifiers based on linear separators can achieve competitive performance while allowing real-time inference and fast training. Various solutions including batch and Online Sequential Learning are analyzed. Additionally, our experiments show that latency and performance can be further improved via dimensionality reduction and pre-training, respectively. The resulting system is implemented on two types of edge device, namely an edge accelerator and two smartphones.