Human Action Recognition Based on Improved MIL

Shao Ping Zhu

doi:10.4028/www.scientific.net/AMM.713-715.2152

Paper Titles

Knowledge Discovery in Incomplete Medical Data Using Flow-Graph Networks
p.2133

Research on the Credibility Evaluation Methods of Combat Simulation
p.2139

Shadow Rendering Technology in the Application of Virtual Simulation System
p.2143

Study of DEM Information Security in Geographic Information Service
p.2147

Human Action Recognition Based on Improved MIL
p.2152

A Gesture Recognition Algorithm Using Hausdorff-Like Distance Template Matching Based on the Main Direction of Gesture
p.2156

Research on Face Recognition Technology of Real-Time Video High Performance Similarity
p.2160

A Comparative Study of Visual Salient Features Affect Object Recognition
p.2165

Application of SOM Neural Network in Lithology Recognition
p.2169

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 713-715Human Action Recognition Based on Improved MIL

Human Action Recognition Based on Improved MIL

Abstract:

According to the problem that achieves robust human actions recognition from image sequences in computer vision, using the Iterative Querying Heuristic algorithm as a guide, a improved Multiple Instance Learning (MIL) method is proposed for human action recognition in video image sequences. Experiments show that the new method can quickly recognize human actions and achieve high recognition rates, and on the Weizmann database validate our analysis.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 713-715)

Pages:

2152-2155

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.713-715.2152

Citation:

Cite this paper

Online since:

January 2015

Authors:

Shao Ping Zhu*

Keywords:

Global Silhouette, Human Action Recognition, Iterative Querying Heuristic Algorithm, Multiple Instance Learning, Optimal Design

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Olivera N, Garg A, Horvitz E. Layered representations for learning and inferring office activity from multiple sensory channels [J]. Computer Vision and Image Understanding, 2004, 96(2): 163-180.

DOI: 10.1016/j.cviu.2004.02.004

Google Scholar

[2] Flaherty P, Giaever G, Kumm J, et al. A latent variable model for chemogenomic profiling [J]. Bioinformatics, 2005, 21(15): 3286-3293.

DOI: 10.1093/bioinformatics/bti515

Google Scholar

[3] Schuldt C, Laptev I, Caputo B. Recognizing human actions: a local svm approach [J]. ICPR, 2004, 32-36.

DOI: 10.1109/icpr.2004.1334462

Google Scholar

[4] Cheung V, Frey B, Jojic N. Video epitomes. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C], 2005, 1: 42–49.

DOI: 10.1109/cvpr.2005.366

Google Scholar

[5] Ronald P. A survey on vision-based human action recognition [J]. Image and Vision Computing, 2010, 28( 6) : 976-990.

DOI: 10.1016/j.imavis.2009.11.014

Google Scholar

[6] Keeler J D, Rumelhart D E, and Leow W K. Integrated segmentation and recognition of hand-printed numerals[A]. in NIPS-3: Proceedings of the 1990 conference on advances in neural information processing systems 3[C], San Francisco, CA, USA: Morgan Kaufmann Publishers Inc, 1990, 557–563.

Google Scholar