Introduction to Algorithms
Estimating Human Body Configurations Using Shape Context Matching
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Maxdiff kd-trees for data condensation
Pattern Recognition Letters
Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words
International Journal of Computer Vision
Histogram of oriented rectangles: A new pose descriptor for human action recognition
Image and Vision Computing
An iterative image registration technique with an application to stereo vision
IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
An Experimental Study of Graph Connectivity for Unsupervised Word Sense Disambiguation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Multi person tracking within crowded scenes
Proceedings of the 2nd conference on Human motion: understanding, modeling, capture and animation
Recovering human body configurations: combining segmentation and recognition
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Modeling sense disambiguation of human pose: recognizing action at a distance by key poses
ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part I
Hidden Part Models for Human Action Recognition: Probabilistic versus Max Margin
IEEE Transactions on Pattern Analysis and Machine Intelligence
Predicting human activities using spatio-temporal structure of interest points
Proceedings of the 20th ACM international conference on Multimedia
A survey of video datasets for human action and activity recognition
Computer Vision and Image Understanding
Hi-index | 0.00 |
In this paper, we propose a graph theoretic approach for recognizing interactions between two human performers present in a video clip. We watch primarily the human poses of each performer and derive descriptors that capture the motion patterns of the poses. From an initial dictionary of poses (visual words), we extract key poses (or key words) by ranking the poses on the centrality measure of graph connectivity. We argue that the key poses are graph nodes which share a close semantic relationship (in terms of some suitable edge weight function) with all other pose nodes and hence are said to be the central part of the graph. We apply the same centrality measure on all possible combinations of the key poses of the two performers to select the set of 'key pose doublets' that best represent the corresponding action. The results on standard interaction recognition dataset show the robustness of our approach when compared to the present state of the art method.