Abstract | ||
---|---|---|
We propose a method to automatically detect emotions in unconstrained settings as part of the 2013 Emotion Recognition in the Wild Challenge [16], organized in conjunction with the ACM International Conference on Multimodal Interaction (ICMI 2013). Our method combines multiple visual descriptors with paralinguistic audio features for multimodal classification of video clips. Extracted features are combined using Multiple Kernel Learning and the clips are classified using an SVM into one of the seven emotion categories: Anger, Disgust, Fear, Happiness, Neutral, Sadness and Surprise. The proposed method achieves competitive results, with an accuracy gain of approximately 10% above the challenge baseline. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1145/2522848.2531741 | ICMI |
Keywords | Field | DocType |
emotion recognition,challenge baseline,competitive result,acm international conference,multiple kernel learning,extracted feature,accuracy gain,multiple kernel,multimodal interaction,wild challenge,multimodal,support vector machine,bag of words | Bag-of-words model,Sadness,Computer vision,Multimodal interaction,Paralanguage,Disgust,Computer science,Multiple kernel learning,Support vector machine,Speech recognition,Artificial intelligence,Surprise | Conference |
Citations | PageRank | References |
40 | 1.42 | 39 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Karan Sikka | 1 | 270 | 13.22 |
Karmen Dykstra | 2 | 42 | 2.20 |
Suchitra Sathyanarayana | 3 | 42 | 1.82 |
gwen littlewort | 4 | 1159 | 67.40 |
Marian Stewart Bartlett | 5 | 223 | 11.41 |