Name
Abstract | ||
|---|---|---|
We present a robust model to locate facial landmarks under different views and possibly severe occlusions. To build reliable relationships between face appearance and shape with large view variations, we propose to formulate face alignment as an L1-induced Stagewise Relational Dictionary (SRD) learning problem. During each training stage, the SRD model learns a relational dictionary to capture consistent relationships between face appearance and shape, which are respectively modeled by the pose-indexed image features and the shape displacements for current estimated landmarks. During testing, the SRD model automatically selects a sparse set of the most related shape displacements for the testing face and uses them to refine its shape iteratively. To locate facial landmarks under occlusions, we further propose to learn an occlusion dictionary to model different kinds of partial face occlusions. By deploying the occlusion dictionary into the SRD model, the alignment performance for occluded faces can be further improved. Our algorithm is simple, effective, and easy to implement. Extensive experiments on two benchmark datasets and two newly built datasets have demonstrated its superior performances over the state-of-the-art methods, especially for faces with large view variations and/or occlusions. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/CVPR.2014.236 | CVPR |
Keywords | Field | DocType |
face appearance,face alignment,pose-indexed image features,face recognition,partially-occluded face alignment,alignment performance,facial landmarks location,partial face occlusions,learning (artificial intelligence),dictionary learning,sparse coding,shape displacements,face shape,multiview face alignment,srd model,feature extraction,face alignment, dictionary learning, sparse coding,occlusion dictionary,stagewise relational dictionary learning problem,view variations,srd learning problem,shape,dictionaries,face,robustness,learning artificial intelligence,optimization,testing | Computer vision,Dictionary learning,Pattern recognition,Neural coding,Computer science,Feature (computer vision),Artificial intelligence | Conference |
ISSN | Citations | PageRank |
1063-6919 | 15 | 0.54 |
References | Authors | |
20 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Junliang Xing | 1 | 1193 | 63.31 |
| Zhiheng Niu | 2 | 52 | 3.50 |
| Junshi Huang | 3 | 334 | 10.15 |
| Weiming Hu | 4 | 5300 | 261.38 |
| Shuicheng Yan | 5 | 9701 | 359.54 |