Audio-visual analysis for event understanding
AMC '09 Proceedings of the 2009 workshop on Ambient media computing
Human action recognition using Pose-based discriminant embedding
Image Communication
A review on vision techniques applied to Human Behaviour Analysis for Ambient-Assisted Living
Expert Systems with Applications: An International Journal
Action recognition for human-marionette interaction
Proceedings of the 20th ACM international conference on Multimedia
Dynamic eye movement datasets and learnt saliency models for visual action recognition
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
A tree-based approach to integrated action localization, recognition and segmentation
ECCV'10 Proceedings of the 11th European conference on Trends and Topics in Computer Vision - Volume Part I
A unified tree-based framework for joint action localization, recognition and segmentation
Computer Vision and Image Understanding
Online RGB-D gesture recognition with extreme learning machines
Proceedings of the 15th ACM on International conference on multimodal interaction
Pattern Recognition Letters
Online gesture recognition from pose kernel learning and decision forests
Pattern Recognition Letters
Hi-index | 0.00 |
This paper presents a graphical model for learning and recognizing human actions. Specifically, we propose to encode actions in a weighted directed graph, referred to as action graph, where nodes of the graph represent salient postures that are used to characterize the actions and are shared by all actions. The weight between two nodes measures the transitional probability between the two postures represented by the two nodes. An action is encoded as one or multiple paths in the action graph. The salient postures are modeled using Gaussian mixture models (GMMs). Both the salient postures and action graph are automatically learned from training samples through unsupervised clustering and expectation and maximization (EM) algorithm. The proposed action graph not only performs effective and robust recognition of actions, but it can also be expanded efficiently with new actions. An algorithm is also proposed for adding a new action to a trained action graph without compromising the existing action graph. Extensive experiments on widely used and challenging data sets have verified the performance of the proposed methods, its tolerance to noise and viewpoints, its robustness across different subjects and data sets, as well as the effectiveness of the algorithm for learning new actions.