Motion Retrieval with Temporal-Spatial Features Based on Ensemble Learning

Authors:
Jian Xiang
Affiliations:
School of Information and Electronic Engineering, ZheJiang University of Science and Technology, 310023, Hangzhou, China
Venue:
ICIC '07 Proceedings of the 3rd International Conference on Intelligent Computing: Advanced Intelligent Computing Theories and Applications. With Aspects of Artificial Intelligence
Year:
2009

Citing 6
Cited 0

Bagging predictors

Machine Learning
A decision-theoretic generalization of on-line learning and an application to boosting

EuroCOLT '95 Proceedings of the Second European Conference on Computational Learning Theory
3D motion retrieval with motion index tree

Computer Vision and Image Understanding - Special isssue on video retrieval and summarization
Content-based retrieval for human motion data

Journal of Visual Communication and Image Representation
Asymmetrically boosted HMM for speech reading

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Recognition and segmentation of 3-d human action using HMM and multi-class adaboost

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV

Quantified Score

Hi-index	0.00

Visualization

Abstract

Along with the development of Motion Capture technique, more and more 3D motion database become available. In this paper, a novel method is presented for motion retrieval based on Ensemble HMM learning. First 3D temporal-spatial features and their keyspaces of each human joint are extracted for training data of Ensemble HMM learning. Then each action class is learned with one HMM. Since ensemble learning can effectively enhance supervised learners, ensembles of weak HMM learners are built. Experimental results show that our approaches are effective for motion data retrieval.