Auto learning temporal atomic actions for activity classification

Authors:
Jiangen Zhang;Benjamin Yao;Yongtian Wang
Affiliations:
Key Laboratory of Photoelectronic Imaging Technology and System, Ministry of Education, Beijing Institute of Technology, Beijing 100081, China;Department of Statistics, University of California, Los Angeles, Los Angeles, CA 90095, Unites States;Key Laboratory of Photoelectronic Imaging Technology and System, Ministry of Education, Beijing Institute of Technology, Beijing 100081, China
Venue:
Pattern Recognition
Year:
2013

Citing 16
Cited 0

Latent dirichlet allocation

The Journal of Machine Learning Research
Space-time Interest Points

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Recognizing Human Actions: A Local SVM Approach

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
Computational studies of human motion: part 1, tracking and motion synthesis

Foundations and Trends® in Computer Graphics and Vision
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
Describing Visual Scenes Using Transformed Objects and Parts

International Journal of Computer Vision
Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words

International Journal of Computer Vision
LIBLINEAR: A Library for Large Linear Classification

The Journal of Machine Learning Research
An Efficient Dense and Scale-Invariant Spatio-Temporal Interest Point Detector

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part II
Unsupervised Activity Perception in Crowded and Complicated Scenes Using Hierarchical Bayesian Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
Human Action Recognition by Semilatent Topic Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
Modeling temporal structure of decomposable motion segments for activity classification

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
Actom sequence models for efficient action detection

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
Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis

CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Modelling Atomic Actions for Activity Classification

ICME '12 Proceedings of the 2012 IEEE International Conference on Multimedia and Expo

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper, we present a model for learning atomic actions for complex activities classification. A video sequence is first represented by a collection of visual interest points. Then the model automatically clusters visual words into atomic actions (topics) based on their co-occurrence and temporal proximity in the same activity category using an extension of hierarchical Dirichlet process (HDP) mixture model. Our approach is robust to noisy interest points caused by various conditions because HDP is a generative model. Finally, we use both a Naive Bayesian and a linear SVM classifier for the problem of activity classification. We first use the intermediate result of a synthetic example to demonstrate the superiority of our model, then we apply our model on the complex Olympic Sport 16-class dataset and show that it outperforms other state-of-art methods.