View and style-independent action manifolds for human activity recognition

Authors:
Michał Lewandowski;Dimitrios Makris;Jean-Christophe Nebel
Affiliations:
Digital Imaging Research Centre, Kingston University, London, United Kingdom;Digital Imaging Research Centre, Kingston University, London, United Kingdom;Digital Imaging Research Centre, Kingston University, London, United Kingdom
Venue:
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part VI
Year:
2010

Citing 17
Cited 8

Fundamentals of speech recognition

Fundamentals of speech recognition
Robust Real-Time Periodic Motion Detection, Analysis, and Applications

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Multilinear Singular Value Decomposition

SIAM Journal on Matrix Analysis and Applications
The Recognition of Human Movement Using Temporal Templates

IEEE Transactions on Pattern Analysis and Machine Intelligence
On Space-Time Interest Points

International Journal of Computer Vision
Recognizing Human Actions in Videos Acquired by Uncalibrated Moving Cameras

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
View Invariance for Human Action Recognition

International Journal of Computer Vision
Automatic Discovery of Action Taxonomies from Multiple Views

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Free viewpoint action recognition using motion history volumes

Computer Vision and Image Understanding - Special issue on modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
Actions as Space-Time Shapes

IEEE Transactions on Pattern Analysis and Machine Intelligence
Manifold alignment using Procrustes analysis

Proceedings of the 25th international conference on Machine learning
Cross-View Action Recognition from Temporal Self-similarities

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part II
Tracking People on a Torus

IEEE Transactions on Pattern Analysis and Machine Intelligence
Viewpoint manifolds for action recognition

Journal on Image and Video Processing - Special issue on video-based modeling, analysis, and recognition of human motion
Temporal Extension of Laplacian Eigenmaps for Unsupervised Dimensionality Reduction of Time Series

ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition
Homeomorphic manifold analysis: learning decomposable generative models for human motion analysis

WDV'05/WDV'06/ICCV'05/ECCV'06 Proceedings of the 2005/2006 international conference on Dynamical vision
View-invariant modeling and recognition of human actions using grammars

WDV'05/WDV'06/ICCV'05/ECCV'06 Proceedings of the 2005/2006 international conference on Dynamical vision

Improving the accuracy of action classification using view-dependent context information

HAIS'11 Proceedings of the 6th international conference on Hybrid artificial intelligent systems - Volume Part II
Probabilistic feature extraction from multivariate time series using spatio-temporal constraints

PAKDD'11 Proceedings of the 15th Pacific-Asia conference on Advances in knowledge discovery and data mining - Volume Part II
Fast human activity recognition based on structure and motion

Pattern Recognition Letters
Are current monocular computer vision systems for human action recognition suitable for visual surveillance applications?

ISVC'11 Proceedings of the 7th international conference on Advances in visual computing - Volume Part II
View-Invariant action recognition using latent kernelized structural SVM

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Transfer discriminant-analysis of canonical correlations for view-transfer action recognition

PCM'12 Proceedings of the 13th Pacific-Rim conference on Advances in Multimedia Information Processing
Common-sense reasoning for human action recognition

Pattern Recognition Letters
Temporal segmentation and assignment of successive actions in a long-term video

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

We introduce a novel approach to automatically learn intuitive and compact descriptors of human body motions for activity recognition. Each action descriptor is produced, first, by applying Temporal Laplacian Eigenmaps to view-dependent videos in order to produce a stylistic invariant embedded manifold for each view separately. Then, all view-dependent manifolds are automatically combined to discover a unified representation which model in a single three dimensional space an action independently from style and viewpoint. In addition, a bidirectional nonlinear mapping function is incorporated to allow projecting actions between original and embedded spaces. The proposed framework is evaluated on a real and challenging dataset (IXMAS), which is composed of a variety of actions seen from arbitrary viewpoints. Experimental results demonstrate robustness against style and view variation and match the most accurate action recognition method.