Title | ||
---|---|---|
Dynamic facial expression recognition by joint static and multi-time gap transition classification |
Abstract | ||
---|---|---|
Automatic facial expression classification is a challenging problem for developing intelligent human-computer interaction systems. In order to take into account the expression dynamics, existing works usually make the assumption that a specific facial expression is displayed with a pre-segmented evolution, i.e. starting from neutral and finishing on an apex frame. In this paper, we propose a method to train a transition classifier from pairs of images. This transition classifier is applied at multiple time gaps and the output probabilities are fused along with a static estimation. We eventually show that our approach yields state-of-the-art accuracy on popular datasets without exploiting any such prior on the segmentation of the expression. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/FG.2015.7163111 | FG |
Keywords | Field | DocType |
databases,support vector machines,vegetation,accuracy,estimation,face recognition | Computer vision,Facial recognition system,Interaction systems,Facial expression recognition,Pattern recognition,Computer science,Segmentation,Support vector machine,Facial expression,Artificial intelligence,Classifier (linguistics) | Conference |
ISSN | Citations | PageRank |
2326-5396 | 5 | 0.43 |
References | Authors | |
18 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Arnaud Dapogny | 1 | 42 | 7.06 |
Kevin Bailly | 2 | 244 | 19.10 |
Séverine Dubuisson | 3 | 168 | 24.12 |