Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection
IEEE Transactions on Pattern Analysis and Machine Intelligence
A fast fixed-point algorithm for independent component analysis
Neural Computation
Comprehensive Database for Facial Expression Analysis
FG '00 Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition 2000
Haar Features for FACS AU Recognition
FGR '06 Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition
A fast learning algorithm for deep belief nets
Neural Computation
Dynamic Texture Recognition Using Local Binary Patterns with an Application to Facial Expressions
IEEE Transactions on Pattern Analysis and Machine Intelligence
Self-taught learning: transfer learning from unlabeled data
Proceedings of the 24th international conference on Machine learning
Journal of Cognitive Neuroscience
Boosting encoded dynamic features for facial expression recognition
Pattern Recognition Letters
A Survey of Affect Recognition Methods: Audio, Visual, and Spontaneous Expressions
IEEE Transactions on Pattern Analysis and Machine Intelligence
Facial expression recognition based on Local Binary Patterns: A comprehensive study
Image and Vision Computing
Convolutional learning of spatio-temporal features
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part VI
E-2DLDA: a new matrix-based image representation method for face recognition
ICONIP'06 Proceedings of the 13th international conference on Neural Information Processing - Volume Part II
Hi-index | 0.01 |
Engineered features have been heavily employed in computer vision. Recently, feature learning from unlabeled data for improving the performance of a given vision task has received increasing attention in both machine learning and computer vision. In this paper, we present using unlabeled video data to learn spatiotemporal features for video classification tasks. Specifically, we employ independent component analysis (ICA) to learn spatiotemporal filters from natural videos, and then construct feature representations for the input videos in classification tasks based on the learned filters. We test the performance of proposed feature learning method with application to facial expression recognition. The experimental results on the well-known Cohn-Kanade database show that the learned features perform better than engineered features. The comparison experiments on recognition of low intensity expressions show that our method yields a better performance than spatiotemporal Gabor features.