Instance-Based Learning Algorithms
Machine Learning
Fast subsequence matching in time-series databases
SIGMOD '94 Proceedings of the 1994 ACM SIGMOD international conference on Management of data
Scaling up dynamic time warping for datamining applications
Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining
The Recognition of Human Movement Using Temporal Templates
IEEE Transactions on Pattern Analysis and Machine Intelligence
Machine Learning
Shape Matching and Object Recognition Using Shape Contexts
IEEE Transactions on Pattern Analysis and Machine Intelligence
Tracking and Object Classification for Automated Surveillance
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
An Online Algorithm for Segmenting Time Series
ICDM '01 Proceedings of the 2001 IEEE International Conference on Data Mining
Similarity Search Over Time-Series Data Using Wavelets
ICDE '02 Proceedings of the 18th International Conference on Data Engineering
A symbolic representation of time series, with implications for streaming algorithms
DMKD '03 Proceedings of the 8th ACM SIGMOD workshop on Research issues in data mining and knowledge discovery
Recognizing Action at a Distance
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Face Recognition from Face Profile Using Dynamic Time Warping
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 4 - Volume 04
Actions Sketch: A Novel Action Representation
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
International Journal of Computer Vision
HOT SAX: Efficiently Finding the Most Unusual Time Series Subsequence
ICDM '05 Proceedings of the Fifth IEEE International Conference on Data Mining
VLDB '06 Proceedings of the 32nd international conference on Very large data bases
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
Experiencing SAX: a novel symbolic representation of time series
Data Mining and Knowledge Discovery
IEEE Transactions on Pattern Analysis and Machine Intelligence
Time series shapelets: a new primitive for data mining
Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining
The WEKA data mining software: an update
ACM SIGKDD Explorations Newsletter
Human action recognition using distribution of oriented rectangular patches
Proceedings of the 2nd conference on Human motion: understanding, modeling, capture and animation
Representing pairwise spatial and temporal relations for action recognition
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
Computer Vision and Image Understanding
Recognizing human actions by attributes
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Learning context for collective activity recognition
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Action recognition by dense trajectories
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
On the Orientability of Shapes
IEEE Transactions on Image Processing
A multiscale representation method for nonrigid shapes with a single closed contour
IEEE Transactions on Circuits and Systems for Video Technology
Using SAX representation for human action recognition
Journal of Visual Communication and Image Representation
Hi-index | 0.00 |
Human action recognition is an important problem in Computer Vision. Although most of the existing solutions provide good accuracy results, the methods are often overly complex and computationally expensive, hindering practical applications. In this regard, we introduce the combination of time-series representation for the silhouette and Symbolic Aggregate approXimation (SAX), which we refer to as SAX-Shapes, to address the problem of human action recognition. Given an action sequence, the extracted silhouettes of an actor from every frame are transformed into time series. Each of these time series is then efficiently converted into the symbolic vector: SAX. The set of all these SAX vectors (SAX-Shape) represents the action. We propose a rotation invariant distance function to be used by a random forest algorithm to perform the human action recognition. Requiring only silhouettes of actors, the proposed method is validated on two public datasets. It has an accuracy comparable to the related works and it performs well even in varying rotation.