Learning person-specific models for facial expression and action unit recognition |
| |
Authors: | Jixu Chen Xiaoming Liu Peter Tu Amy Aragones |
| |
Affiliation: | 1. GE Global Research, Niskayuna, NY 12309, United States;2. Michigan State University, East Lansing, MI, 48824, United States |
| |
Abstract: | A key assumption of traditional machine learning approach is that the test data are draw from the same distribution as the training data. However, this assumption does not hold in many real-world scenarios. For example, in facial expression recognition, the appearance of an expression may vary significantly for different people. As a result, previous work has shown that learning from adequate person-specific data can improve the expression recognition performance over the one from generic data. However, person-specific data is typically very sparse in real-world applications due to the difficulties of data collection and labeling, and learning from sparse data may suffer from serious over-fitting. In this paper, we propose to learn a person-specific model through transfer learning. By transferring the informative knowledge from other people, it allows us to learn an accurate model for a new subject with only a small amount of person-specific data. We conduct extensive experiments to compare different person-specific models for facial expression and action unit (AU) recognition, and show that transfer learning significantly improves the recognition performance with a small amount of training data. |
| |
Keywords: | Transfer learning Expression recognition Action unit recognition |
本文献已被 ScienceDirect 等数据库收录! |
|