Title | ||
---|---|---|
Evaluating Multi-task Learning for Multi-view Head-Pose Classification in Interactive Environments |
Abstract | ||
---|---|---|
Social attention behavior offers vital cues towards inferring one's personality traits from interactive settings such as round-table meetings and cocktail parties. Head orientation is typically employed as a proxy for determining the social attention direction when faces are captured at low-resolution. Recently, multi-task learning has been proposed to robustly compute head pose under perspective and scale-based facial appearance variations when multiple, distant and large field-of-view cameras are employed for visual analysis in smart-room applications. In this paper, we evaluate the effectiveness of an SVM-based MTL (SVM+MTL) framework with various facial descriptors (KL, HOG, LBP, etc.). The KL+HOG feature combination is found to produce the best classification performance, with SVM+MTL outperforming classical SVM irrespective of the feature used. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/ICPR.2014.717 | ICPR |
Keywords | DocType | ISSN |
facial descriptors,kl+hog feature combination,human computer interaction,large field-of-view cameras,multiview head-pose classification,learning (artificial intelligence),head orientation,image resolution,svm-based mtl framework,cocktail parties,smart-room applications,pose estimation,image classification,vital cues,cameras,scale-based facial appearance variations,social attention behavior,interactive environments,visual analysis,interactive systems,social sciences computing,round-table meetings,support vector machines,multitask learning evaluation | Conference | 1051-4651 |
Citations | PageRank | References |
2 | 0.37 | 17 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yan Yan | 1 | 691 | 31.13 |
Ramanathan Subramanian | 2 | 461 | 22.16 |
Elisa Ricci 0002 | 3 | 1393 | 73.75 |
Oswald Lanz | 4 | 462 | 33.34 |
Nicu Sebe | 5 | 7013 | 403.03 |