Properties of Embedding Methods for Similarity Searching in Metric Spaces
IEEE Transactions on Pattern Analysis and Machine Intelligence
Recognizing Human Actions: A Local SVM Approach
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
A Probabilistic Approach to Learning Costs for Graph Edit Distance
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
International Journal of Computer Vision
The Dissimilarity Representation for Pattern Recognition: Foundations And Applications (Machine Perception and Artificial Intelligence)
Behavior recognition via sparse spatio-temporal features
ICCCN '05 Proceedings of the 14th International Conference on Computer Communications and Networks
Hidden Conditional Random Fields
IEEE Transactions on Pattern Analysis and Machine Intelligence
A survey of graph edit distance
Pattern Analysis & Applications
Graph classification by means of Lipschitz embedding
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
A survey on vision-based human action recognition
Image and Vision Computing
Graph embedding in vector spaces by means of prototype selection
GbRPR'07 Proceedings of the 6th IAPR-TC-15 international conference on Graph-based representations in pattern recognition
Human motion recognition using Isomap and dynamic time warping
Proceedings of the 2nd conference on Human motion: understanding, modeling, capture and animation
Recognizing and Localizing Individual Activities through Graph Matching
AVSS '10 Proceedings of the 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance
Human action recognition in video by fusion of structural and spatio-temporal features
SSPR'12/SPR'12 Proceedings of the 2012 Joint IAPR international conference on Structural, Syntactic, and Statistical Pattern Recognition
Hi-index | 0.00 |
The problem of human action recognition has received increasing attention in recent years for its importance in many applications. Yet, the main limitation of current approaches is that they do not capture well the spatial relationships in the subject performing the action. This paper presents an initial study which uses graphs to represent the actor's shape and graph embedding to then convert the graph into a suitable feature vector. In this way, we can benefit from the wide range of statistical classifiers while retaining the strong representational power of graphs. The paper shows that, although the proposed method does not yet achieve accuracy comparable to that of the best existing approaches, the embedded graphs are capable of describing the deformable human shape and its evolution along the time. This confirms the interesting rationale of the approach and its potential for future performance.