Detecting irregularity in videos using kernel estimation and KD trees
MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
A survey of advances in vision-based human motion capture and analysis
Computer Vision and Image Understanding - Special issue on modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words
International Journal of Computer Vision
Contour graph based human tracking and action sequence recognition
Pattern Recognition
A survey on vision-based human action recognition
Image and Vision Computing
Human motion recognition using Isomap and dynamic time warping
Proceedings of the 2nd conference on Human motion: understanding, modeling, capture and animation
Activities as time series of human postures
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
Trajectory-based representation of human actions
ICMI'06/IJCAI'07 Proceedings of the ICMI 2006 and IJCAI 2007 international conference on Artifical intelligence for human computing
Action recognition with appearance-motion features and fast search trees
Computer Vision and Image Understanding
Unsupervised action classification using space-time link analysis
Journal on Image and Video Processing
Boosted multi-class semi-supervised learning for human action recognition
Pattern Recognition
DEVS-based modeling of a human motion data synthesis and control system
Proceedings of the 2010 Summer Computer Simulation Conference
Human behavior clustering for anomaly detection
Frontiers of Computer Science in China
Learning semantic features for action recognition via diffusion maps
Computer Vision and Image Understanding
Extracting spatio-temporal local features considering consecutiveness of motions
ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part II
Learning discriminative localization from weakly labeled data
Pattern Recognition
| Hi-index | 0.00 |
Probabilistic models have been previously shown to be efficient and effective for modeling and recognition of human motion. In particular we focus on methods which represent the human motion model as a triangulated graph. Previous approaches learned models based just on positions and velocities of the body parts while ignoring their appearance. Moreover, a heuristic approachwas commonly used to obtain translation invariance. In this paper we suggest an improved approach for learning such models and using them for human motion recognition. The suggested approach combines multiple cues, i.e., positions, velocities and appearance into both the learning and detection phases. Furthermore, we introduce global variables in the model, which can represent global properties such as translation, scale or view-point. The model is learned in an unsupervised manner from unlabelled data. We show that the suggested hybrid probabilistic model (which combines global variables, like translation, with local variables, like relative positions and appearances of body parts), leads to: (i) faster convergence of learning phase, (ii) robustness to occlusions, and, (iii) higher recognition rate.