Abstract | ||
---|---|---|
Automatic facial Action Unit (AU) detection from video is a long-standing problem in facial expression analysis. AU detection is typically posed as a classification problem between frames or segments of positive examples and negative ones, where existing work emphasizes the use of different features or classifiers. In this paper, we propose a method called Cascade of Tasks (CoT) that combines the use of different tasks (i.e., frame, segment and transition) for AU event detection. We train CoT in a sequential manner embracing diversity, which ensures robustness and generalization to unseen data. In addition to conventional frame-based metrics that evaluate frames independently, we propose a new event-based metric to evaluate detection performance at event-level. We show how the CoT method consistently outperforms state-of-the-art approaches in both frame-based and event-based metrics, across three public datasets that differ in complexity: CK+, FERA and RU-FACS. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/ICCV.2013.298 | ICCV |
Keywords | Field | DocType |
automatic facial action unit,detection performance,au detection,facial action unit event,cot method,conventional frame,different task,event-based metrics,classification problem,au event detection,different feature,face recognition,bioinformatics,biomedical research | Facial recognition system,Computer vision,Pattern recognition,Computer science,Robustness (computer science),Speech recognition,Frame based,Facial expression,Cascade,Artificial intelligence | Conference |
Volume | Issue | ISSN |
2013 | 1 | 1550-5499 |
Citations | PageRank | References |
29 | 0.75 | 26 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiaoyu Ding | 1 | 69 | 6.57 |
Wen-Sheng Chu | 2 | 380 | 14.54 |
Fernando De La Torre | 3 | 3832 | 181.17 |
Jeffery F Cohn | 4 | 173 | 5.90 |
Qiao Wang | 5 | 163 | 15.33 |