Paper Info
Title
The University of Passau Open Emotion Recognition System for the Multimodal Emotion Challenge.
Abstract
This paper presents the University of Passau's approaches for the Multimodal Emotion Recognition Challenge 2016. For audio signals, we exploit Bag-of-Audio-Words techniques combining Extreme Learning Machines and Hierarchical Extreme Learning Machines. For video signals, we use not only the information from the cropped face of a video frame, but also the broader contextual information from the entire frame. This information is extracted via two Convolutional Neural Networks pre-trained for face detection and object classification. Moreover, we extract facial action units, which reflect facial muscle movements and are known to be important for emotion recognition. Long Short-Term Memory Recurrent Neural Networks are deployed to exploit temporal information in the video representation. Average late fusion of audio and video systems is applied to make prediction for multimodal emotion recognition. Experimental results on the challenge database demonstrate the effectiveness of our proposed systems when compared to the baseline.
Year
DOI
Venue
2016
10.1007/978-981-10-3005-5_54
Communications in Computer and Information Science
Keywords
Field
DocType
Multimodal emotion recognition,Bag-of-audio-words,Transfer learning,Long short-term memory,Convolutional neural networks
Audio signal,Convolutional neural network,Computer science,Emotion recognition,Transfer of learning,Recurrent neural network,Speech recognition,Exploit,Facial muscles,Face detection
Conference
Volume
ISSN
Citations 
663
1865-0929
4
PageRank 
References 
Authors
0.53
23
8
Name
Order
Citations
PageRank
Jun Deng127818.59
Nicholas Cummins234932.93
Jing Han340.53
Xinzhou Xu440.53
Ren Zhao54815.88
Vedhas Pandit6193.68
Zixing Zhang739731.73
Björn Schuller86749463.50