Abstract | ||
---|---|---|
Face alignment consists in aligning a shape model on a face in an image. It is an active domain in computer vision as it is a preprocessing for applications like facial expression recognition, face recognition and tracking, face animation, etc. Current state-of-the-art methods already perform well on "easy" datasets, i.e. those that present moderate variations in head pose, expression, illumination or partial occlusions, but may not be robust to "in-the-wild" data. In this paper, we address this problem by using an ensemble of deep regressors instead of a single large regressor. Furthermore, instead of averaging the ouputs of each regressor, we propose an adaptative weighting scheme that uses a tree-structured gate. Experiments on several challenging face datasets demonstrate that our approach outperforms the state-of-the-art methods. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/FG.2019.8756538 | 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019) |
Keywords | Field | DocType |
tree-gated deep regressor ensemble,face alignment,shape model,computer vision,facial expression recognition,face animation,illumination,tree-structured gate,face datasets,adaptative weighting scheme | Facial recognition system,Weighting,Facial expression recognition,Pattern recognition,Computer science,Preprocessor,Animation,Artificial intelligence | Conference |
ISSN | ISBN | Citations |
2326-5396 | 978-1-7281-0090-6 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Estephe Arnaud | 1 | 0 | 0.34 |
Arnaud Dapogny | 2 | 42 | 7.06 |
Kevin Bailly | 3 | 244 | 19.10 |