articleSep 29, 2007GREEN OA

A 3-dimensional sift descriptor and its application to action recognition

University of Central Florida

Indexed incrossref

Abstract

In this paper we introduce a 3-dimensional (3D) SIFT descriptor for video or 3D imagery such as MRI data. We also show how this new descriptor is able to better represent the 3D nature of video data in the application of action recognition. This paper will show how 3D SIFT is able to outperform previously used description methods in an elegant and efficient manner. We use a bag of words approach to represent videos, and present a method to discover relationships between spatio-temporal words in order to better describe the video data.

Citation impact

1,619
total citations
FWCI
34.87
Percentile
100%
References
15
Citations per year

Authors

3

Topics & keywords

Keywords
  • Scale-invariant feature transform
  • Computer science
  • Artificial intelligence
  • Action recognition
  • Action (physics)
  • Pattern recognition (psychology)
  • Bag-of-words model
  • Computer vision
No related works found for this paper.