A practical Bayesian framework for backpropagation networks
Neural Computation
Belief networks, hidden Markov models, and Markov random fields: a unifying view
Pattern Recognition Letters - special issue on pattern recognition in practice V
Learning nonlinear dynamical systems using an EM algorithm
Proceedings of the 1998 conference on Advances in neural information processing systems II
Learning and Classification of Complex Dynamics
IEEE Transactions on Pattern Analysis and Machine Intelligence
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
An Alternate Objective Function for Markovian Fields
ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning
Semi-Supervised Self-Training of Object Detection Models
WACV-MOTION '05 Proceedings of the Seventh IEEE Workshops on Application of Computer Vision (WACV/MOTION'05) - Volume 1 - Volume 01
Discriminative Density Propagation for 3D Human Motion Estimation
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Articulated Pose Estimation in a Learned Smooth Space of Feasible Solutions
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops - Volume 03
Learning subjective nouns using extraction pattern bootstrapping
CONLL '03 Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003 - Volume 4
Combining discriminative features to infer complex trajectories
ICML '06 Proceedings of the 23rd international conference on Machine learning
Conditional Random People: Tracking Humans with CRFs and Grid Filters
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Co-training for predicting emotions with spoken dialogue data
ACLdemo '04 Proceedings of the ACL 2004 on Interactive poster and demonstration sessions
Semi-supervised conditional random fields for improved sequence segmentation and labeling
ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
Factoring Gaussian precision matrices for linear dynamic models
Pattern Recognition Letters
Gaussian Process Dynamical Models for Human Motion
IEEE Transactions on Pattern Analysis and Machine Intelligence
Discriminative Learning for Dynamic State Prediction
IEEE Transactions on Pattern Analysis and Machine Intelligence
Introduction to Semi-Supervised Learning
Introduction to Semi-Supervised Learning
Robust online appearance models for visual tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence
Aggregation pheromone metaphor for semi-supervised classification
Pattern Recognition
| Hi-index | 0.01 |
We introduce novel discriminative semi-supervised learning algorithms for dynamical systems, and apply them to the problem of 3D human motion estimation. Our recent work on discriminative learning of dynamical systems has been proven to achieve superior performance than traditional generative learning approaches. However, one of the main issues of learning the dynamical systems is to gather labeled output sequences which are typically obtained from precise motion capture tools, hence expensive. In this paper we utilize a large amount of unlabeled (input) video data to improve the prediction performance of the dynamical systems significantly. We suggest two discriminative semi-supervised learning approaches that extend the well-known algorithms in static domains to the sequential, real-valued multivariate output domains: (i) self-training which we derive as coordinate ascent optimization of a proper discriminative objective over both model parameters and the unlabeled state sequences, (ii) minimum entropy approach which maximally reduces the model's uncertainty in state prediction for unlabeled data points. These approaches are shown to achieve significant improvement against the traditional generative semi-supervised learning methods. We demonstrate the benefits of our approaches on the 3D human motion estimation problems.