Name
Abstract | ||
|---|---|---|
Conditional Random Fields (CRFs) can be used as a discriminative approach for simultaneous sequence segmentation and frame labeling. Latent-Dynamic Conditional Random Fields (LDCRFs) incorporates hidden state variables within CRFs which model sub-structure motion patterns and dynamics between labels. Motivated by the success of LDCRFs in gesture recognition, we propose a framework for automatic facial expression recognition from continuous video sequence by modeling temporal variations within shapes using LDCRFs. We show that the proposed approach outperforms CRFs for recognizing facial expressions. Using Principal Component Analysis (PCA) we study the separability of various expression classes in lower dimension projected spaces. By comparing the performance of CRFs and LDCRFs against that of Support Vector Machines (SVMs), we demonstrate that temporal variations within shapes are crucial in classifying expressions especially for those with a small range of facial motion like anger and sadness. We also show empirically that only using changes in facial appearance over time, without using shape variations, is not sufficient to obtain high performance for facial expression recognition. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1109/ICCVW.2011.6130446 | Computer Vision Workshops |
Keywords | Field | DocType |
face recognition,gesture recognition,image segmentation,principal component analysis,support vector machines,automatic facial expression recognition,continuous video sequence,frame labeling,gesture recognition,latent-dynamic conditional random fields,principal component analysis,shape variations,simultaneous sequence segmentation,substructure motion patterns,support vector machines,temporal modeling | Conditional random field,Computer vision,Facial recognition system,Pattern recognition,Expression (mathematics),Computer science,Gesture recognition,Facial expression,Artificial intelligence,Hidden Markov model,Discriminative model,CRFS | Conference |
Volume | Issue | ISBN |
2011 | 1 | 978-1-4673-0062-9 |
Citations | PageRank | References |
59 | 1.87 | 12 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Suyog Jain | 1 | 59 | 1.87 |
| Changbo Hu | 2 | 613 | 34.71 |
| Jake K. Aggarwal | 3 | 1746 | 219.02 |