Searching Human Behaviors using Spatial-Temporalwords

This paper proposes an approach to searching human behaviors in videos using spatial-temporal words which are learnt from unlabelled data with various human behaviors through unsupervised learning. Both the query and the searched videos are represented by codewords frequencies, which capture the int...

Full description

Saved in:
Bibliographic Details
Published in2007 IEEE International Conference on Image Processing Vol. 6; pp. VI - 337 - VI - 340
Main Authors Huazhong Ning, Yuxiao Hu, Huang, T.S.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.09.2007
Subjects
Acceleration
Frequency
Gabor filters
Histograms
Human Behavior Searching
Humans
Motion estimation
Object recognition
Optical filters
Spatial-Temporal Words
Unsupervised learning
Video Matching
Videos
Online AccessGet full text

Cover

More Information
Summary:This paper proposes an approach to searching human behaviors in videos using spatial-temporal words which are learnt from unlabelled data with various human behaviors through unsupervised learning. Both the query and the searched videos are represented by codewords frequencies, which capture the intrinsic information of motion and appearance of human behaviors. This representation further enables us to make use of integral histograms to accelerate the searching procedure. The performance also benefits from our feature representation that, through a MAX-like operation, may simulate the cortical equivalent of the machine-vision "window of analysis"(M. Riesenhuber and T. Poggio, 1999). Examples of challenging sequences with complex behaviors, including tennis and ballet, are shown.
ISBN:9781424414369
1424414369
ISSN:1522-4880
2381-8549
DOI:10.1109/ICIP.2007.4379590