Personalizing gesture recognition using hierarchical bayesian neural networks
Files
Published version
Date
2017-01-01
Authors
Joshi, Ajjen
Ghosh, Soumya
Betke, Margrit
Sclaroff, Stan
Pfister, Hanspeter
Version
Published version
OA Version
Citation
Ajjen Joshi, Soumya Ghosh, Margrit Betke, Stan Sclaroff, Hanspeter Pfister. 2017. "Personalizing Gesture Recognition Using Hierarchical Bayesian Neural Networks." 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017). 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, 2016-07-21 - 2016-07-26
Abstract
Building robust classifiers trained on data susceptible to group or subject-specific variations is a challenging pattern recognition problem. We develop hierarchical Bayesian neural networks to capture subject-specific variations and share statistical strength across subjects. Leveraging recent work on learning Bayesian neural networks, we build fast, scalable algorithms for inferring the posterior distribution over all network weights in the hierarchy. We also develop methods for adapting our model to new subjects when a small number of subject-specific personalization data is available. Finally, we investigate active learning algorithms for interactively labeling personalization data in resource-constrained scenarios. Focusing on the problem of gesture recognition where inter-subject variations are commonplace, we demonstrate the effectiveness of our proposed techniques. We test our framework on three widely used gesture recognition datasets, achieving personalization performance competitive with the state-of-the-art.
Description
License
This CVPR paper is the Open Access version, provided by the Computer Vision Foundation. Except for this watermark on the paper, it is identical to the version available on IEEE Xplore.