Canonical Correlation Analysis of Video Volume Tensors for Action Categorization and Detection

Authors:
Tae-Kyun Kim;Roberto Cipolla
Affiliations:
University of Cambridge, Cambridge;University of Cambridge, Cambridge
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
2009

Citing 0
Cited 16

A survey on vision-based human action recognition

Image and Vision Computing
Relative Margin Support Tensor Machines for gait and action recognition

Proceedings of the ACM International Conference on Image and Video Retrieval
Action recognition based on human movement characteristics

WMVC'09 Proceedings of the 2009 international conference on Motion and video computing
A survey of multilinear subspace learning for tensor data

Pattern Recognition
Nonnegative tensor factorization as an alternative Csiszar---Tusnady procedure: algorithms, convergence, probabilistic interpretations and novel probabilistic tensor latent variable analysis algorithms

Data Mining and Knowledge Discovery
Correlation-based retrieval for heavily changed near-duplicate videos

ACM Transactions on Information Systems (TOIS)
Multiway canonical correlation analysis for frequency components recognition in SSVEP-Based BCIs

ICONIP'11 Proceedings of the 18th international conference on Neural Information Processing - Volume Part I
Higher rank Support Tensor Machines for visual recognition

Pattern Recognition
A hardware friendly algorithm for action recognition using spatio-temporal motion-field patches

Neurocomputing
Directional space-time oriented gradients for 3d visual pattern analysis

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Action recognition using canonical correlation kernels

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
Human gesture recognition on product manifolds

The Journal of Machine Learning Research
Application of 3D-wavelet statistics to video analysis

Multimedia Tools and Applications
Kernel analysis on Grassmann manifolds for action recognition

Pattern Recognition Letters
A template matching approach of one-shot-learning gesture recognition

Pattern Recognition Letters
Learning canonical correlations of paired tensor sets via tensor-to-vector projection

IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence

Quantified Score

Hi-index	0.14

Visualization

Abstract

This paper addresses a spatiotemporal pattern recognition problem. The main purpose of this study is to find a right representation and matching of action video volumes for categorization. A novel method is proposed to measure video-to-video volume similarity by extending Canonical Correlation Analysis (CCA), a principled tool to inspect linear relations between two sets of vectors, to that of two multiway data arrays (or tensors). The proposed method analyzes video volumes as inputs avoiding the difficult problem of explicit motion estimation required in traditional methods and provides a way of spatiotemporal pattern matching that is robust to intraclass variations of actions. The proposed matching is demonstrated for action classification by a simple Nearest Neighbor classifier. We, moreover, propose an automatic action detection method, which performs 3D window search over an input video with action exemplars. The search is speeded up by dynamic learning of subspaces in the proposed CCA. Experiments on a public action data set (KTH) and a self-recorded hand gesture data showed that the proposed method is significantly better than various state-of-the-art methods with respect to accuracy. Our method has low time complexity and does not require any major tuning parameters.