A 3-Dimensional SIFT Descriptor and its Application to Action Recognition ABSTRACT

A 3-Dimensional SIFT Descriptor and its Application to Action Recognition ABSTRACT

Cached

Download Links

by Paul Scovanner

Citations:

BibTeX

@MISC{Scovanner_a3-dimensional,
    author = {Paul Scovanner},
    title = {A 3-Dimensional SIFT Descriptor and its Application to Action Recognition ABSTRACT},
    year = {}
}

Bookmark

OpenURL

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. 1.

Citations

3104	Distinctive image features from scale invariant keypoints - Lowe
1032	Object recognition from local scale-invariant features,” in Computer Vision - Lowe - 1999
11	et al., “Visual categorization with bags of keypoints - Csurka
1	et al., “Recognizing Action at a Distance,” ICCV - Efros - 2003
1	et al., “Efficient Visual Event Detection using Volumetric Features - Ke - 2005
1	et al., “Real-time eye blink detection with GPU-based - Lalonde - 2007
1	et al., “Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories,” CVPR - Lazebnik - 2005
1	Niebles et al., “Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words,” BMVC - C - 2006
1	et al., “Vision-based Mobile Robot Localization And Mapping using Scale-Invariant Features - Se - 2002
1	et al., “Actions Sketch: A Novel Action Representation - Yilmaz