Analysis of emotion recognition using facial expressions, speech and multimodal information
Proceedings of the 6th international conference on Multimodal interfaces
The eNTERFACE'05 Audio-Visual Emotion Database
ICDEW '06 Proceedings of the 22nd International Conference on Data Engineering Workshops
3D Facial Expression Recognition Based on Primitive Surface Feature Distribution
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Audio-visual emotion recognition in adult attachment interview
Proceedings of the 8th international conference on Multimodal interfaces
Audiovisual recognition of spontaneous interest within conversations
Proceedings of the 9th international conference on Multimodal interfaces
A robust multimodal approach for emotion recognition
Neurocomputing
Audio-Visual Emotion Recognition Based on a DBN Model with Constrained Asynchrony
ICIG '09 Proceedings of the 2009 Fifth International Conference on Image and Graphics
Robust shape-based head tracking
ACIVS'07 Proceedings of the 9th international conference on Advanced concepts for intelligent vision systems
Audio–Visual Affective Expression Recognition Through Multistream Fused HMM
IEEE Transactions on Multimedia
Proceedings of the 14th ACM international conference on Multimodal interaction
Hi-index | 0.00 |
We present a triple stream DBN model (T_AsyDBN) for audio visual emotion recognition, in which the two audio feature streams are synchronous, while they are asynchronous with the visual feature stream within controllable constraints. MFCC features and the principle component analysis (PCA) coefficients of local prosodic features are used for the audio streams. For the visual stream, 2D facial features as well 3D facial animation unit features are defined and concatenated, and the feature dimensions are reduced by PCA. Emotion recognition experiments on the eNERFACE'05 database show that by adjusting the asynchrony constraint, the proposed T_AsyDBN model obtains 18.73% higher correction rate than the traditional multi-stream state synchronous HMM (MSHMM), and 10.21% higher than the two stream asynchronous DBN model (Asy_DBN).