Authors:
Ankit Sharma
1
;
Apurv Kumar
1
;
Sony Allappa
1
;
Veena Thenkanidiyoor
1
;
Dileep Aroor Dinesh
2
and
Shikha Gupta
2
Affiliations:
1
National Institute of Technology Goa, India
;
2
Indian Institute of Technology Mandi, India
Keyword(s):
Video Activity Recognition, Gaussian Mixture Model based Encoding, Support Vector Machine, Histogram Intersection Kernel, Hellinger Kernel, Time Flexible Kernel, Modified Time Flexible Kernel.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Classification
;
Computer Vision, Visualization and Computer Graphics
;
Image and Video Analysis
;
Kernel Methods
;
Pattern Recognition
;
Software Engineering
;
Theory and Methods
;
Video Analysis
Abstract:
Video activity recognition involves automatically assigning a activity label to a video. This is a challenging
task due to the complex nature of video data. There exists many sub activities whose temporal order is
important. For building an SVM-based activity recognizer it is necessary to use a suitable kernel that considers
varying length temporal data corresponding to videos. In (Mario Rodriguez and Makris, 2016), a time flexible
kernel (TFK) is proposed for matching a pair of videos by encoding a video into a sequence of bag of visual
words (BOVW) vectors. The TFK involves matching every pair of BOVW vectors from a pair of videos using
linear kernel. In this paper we propose modified TFK (MTFK) where better approaches to match a pair of
BOVW vectors are explored. We propose to explore the use of frequency based kernels for matching a pair of
BOVW vectors. We also propose an approach for encoding the videos using Gaussian mixture models based
soft clustering technique. The effectiv
eness of the proposed approaches are studied using benchmark datasets.
(More)