The nonuniform discrete Fourier transform and its applications in signal processing
The nonuniform discrete Fourier transform and its applications in signal processing
Bayesian Learning for Neural Networks
Bayesian Learning for Neural Networks
Coupled hidden Markov models for complex action recognition
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Conditional Random Fields for Contextual Human Motion Recognition
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
The Function Space of an Activity
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Characteristic-Based Clustering for Time Series Data
Data Mining and Knowledge Discovery
Gaussian Process Dynamical Models for Human Motion
IEEE Transactions on Pattern Analysis and Machine Intelligence
Tracking and classifying of human motions with Gaussian process annealed particle filter
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part I
Characteristic-based descriptors for motion sequence recognition
PAKDD'08 Proceedings of the 12th Pacific-Asia conference on Advances in knowledge discovery and data mining
Extensions of the informative vector machine
Proceedings of the First international conference on Deterministic and Statistical Methods in Machine Learning
Human action recognition based on tracking features
IWINAC'11 Proceedings of the 4th international conference on Interplay between natural and artificial computation - Volume Part I
Human action recognition based on random spectral regression
AICI'11 Proceedings of the Third international conference on Artificial intelligence and computational intelligence - Volume Part III
Hi-index | 0.10 |
This paper presents a spectral analysis-based feature-reduced Gaussian Processes (GP) classification approach to recognition of articulated and deformable human actions from image sequences. Using Tensor Subspace Analysis (TSA), space-time human silhouettes extracted from action sequences are transformed to a low dimensional multivariate time series, from which structure-based statistical features are extracted to summarize the action properties. GP classification, based on spectrally reduced features, is then applied to learn and predict action categories. Experimental results on two real-world state-of-the-art datasets show that the GP classification outperforms a Support Vector Machine (SVM). In particular, spectral feature reduction can effectively eliminate the inconsistent features, while leaving performance undiminished. Moreover, compared with Automatic Relevance Determination (ARD), the spectral way for feature reduction is more efficient.