Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | Proceedings - 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2020 |
| Herausgeber/-innen | Vitomir Struc, Francisco Gomez-Fernandez |
| Seiten | 600-605 |
| Seitenumfang | 6 |
| ISBN (elektronisch) | 978-1-7281-3079-8 |
| Publikationsstatus | Veröffentlicht - 2020 |
Publikationsreihe
| Name | Proceedings - 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2020 |
|---|
Abstract
Human affect recognition is an essential part of natural human-computer interaction. However, current methods are still in their infancy, especially for in-the-wild data. In this work, we introduce our submission to the Affective Behavior Analysis in-the-wild (ABAW) 2020 competition. We propose a two-stream aural-visual analysis model to recognize affective behavior from videos. Audio and image streams are first processed separately and fed into a convolutional neural network. Instead of applying recurrent architectures for temporal analysis we only use temporal convolutions. Furthermore, the model is given access to additional features extracted during face-alignment. At training time, we exploit correlations between different emotion representations to improve performance. Our model achieves promising results on the challenging Aff-Wild2 database.The code is publicly available1.1https://github.com/kuhnkeF/ABAW2020TNT.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Artificial intelligence
- Informatik (insg.)
- Maschinelles Sehen und Mustererkennung
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
Proceedings - 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2020. Hrsg. / Vitomir Struc; Francisco Gomez-Fernandez. 2020. S. 600-605 9320301 (Proceedings - 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2020).
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Two-Stream Aural-Visual Affect Analysis in the Wild
AU - Kuhnke, Felix
AU - Rumberg, Lars
AU - Ostermann, Jörn
PY - 2020
Y1 - 2020
N2 - Human affect recognition is an essential part of natural human-computer interaction. However, current methods are still in their infancy, especially for in-the-wild data. In this work, we introduce our submission to the Affective Behavior Analysis in-the-wild (ABAW) 2020 competition. We propose a two-stream aural-visual analysis model to recognize affective behavior from videos. Audio and image streams are first processed separately and fed into a convolutional neural network. Instead of applying recurrent architectures for temporal analysis we only use temporal convolutions. Furthermore, the model is given access to additional features extracted during face-alignment. At training time, we exploit correlations between different emotion representations to improve performance. Our model achieves promising results on the challenging Aff-Wild2 database.The code is publicly available1.1https://github.com/kuhnkeF/ABAW2020TNT.
AB - Human affect recognition is an essential part of natural human-computer interaction. However, current methods are still in their infancy, especially for in-the-wild data. In this work, we introduce our submission to the Affective Behavior Analysis in-the-wild (ABAW) 2020 competition. We propose a two-stream aural-visual analysis model to recognize affective behavior from videos. Audio and image streams are first processed separately and fed into a convolutional neural network. Instead of applying recurrent architectures for temporal analysis we only use temporal convolutions. Furthermore, the model is given access to additional features extracted during face-alignment. At training time, we exploit correlations between different emotion representations to improve performance. Our model achieves promising results on the challenging Aff-Wild2 database.The code is publicly available1.1https://github.com/kuhnkeF/ABAW2020TNT.
KW - action units
KW - affective behavior analysis
KW - emotion recognition
KW - expression recognition
KW - human computer interaction
KW - valence arousal
UR - http://www.scopus.com/inward/record.url?scp=85101440514&partnerID=8YFLogxK
U2 - 10.48550/arXiv.2002.03399
DO - 10.48550/arXiv.2002.03399
M3 - Conference contribution
SN - 978-1-7281-3080-4
T3 - Proceedings - 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2020
SP - 600
EP - 605
BT - Proceedings - 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2020
A2 - Struc, Vitomir
A2 - Gomez-Fernandez, Francisco
ER -