Visual event recognition

This report summarizes the work that has been done in the final year project of recognizing visual events in videos. It starts with image recognition, in which im- ages are represented in spatial pyramids. Such representations are then input into SVM and KNN for recognition. In video recognition, ba...

Full description

Saved in:
Bibliographic Details
Main Author: Gong, Li.
Other Authors: Xu Dong
Format: Final Year Project
Language:English
Published: 2013
Subjects:
Online Access:http://hdl.handle.net/10356/55095
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-55095
record_format dspace
spelling sg-ntu-dr.10356-550952023-03-03T20:52:58Z Visual event recognition Gong, Li. Xu Dong School of Computer Engineering Centre for Multimedia and Network Technology DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition This report summarizes the work that has been done in the final year project of recognizing visual events in videos. It starts with image recognition, in which im- ages are represented in spatial pyramids. Such representations are then input into SVM and KNN for recognition. In video recognition, bag of words and special- ized Gaussian Mixture Models are employed to represent videos, and respective distance calculation is used to measure video-to-video distance. These distance matrices are then input into SVM for recognition using different kernel types. Also, four domain adaptation methods are implemented to recognize Kodak con- sumer videos using Youtube videos. Adaptive multiple kernel learning achieves the best and improves the mean average precision from 44.33% to 61.40%. Last but not least, a web-based demo system is implemented in two modes to visually demonstrate the underlying recognition system. Bachelor of Engineering (Computer Engineering) 2013-12-12T06:48:34Z 2013-12-12T06:48:34Z 2013 2013 Final Year Project (FYP) http://hdl.handle.net/10356/55095 en Nanyang Technological University 67 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition
spellingShingle DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition
Gong, Li.
Visual event recognition
description This report summarizes the work that has been done in the final year project of recognizing visual events in videos. It starts with image recognition, in which im- ages are represented in spatial pyramids. Such representations are then input into SVM and KNN for recognition. In video recognition, bag of words and special- ized Gaussian Mixture Models are employed to represent videos, and respective distance calculation is used to measure video-to-video distance. These distance matrices are then input into SVM for recognition using different kernel types. Also, four domain adaptation methods are implemented to recognize Kodak con- sumer videos using Youtube videos. Adaptive multiple kernel learning achieves the best and improves the mean average precision from 44.33% to 61.40%. Last but not least, a web-based demo system is implemented in two modes to visually demonstrate the underlying recognition system.
author2 Xu Dong
author_facet Xu Dong
Gong, Li.
format Final Year Project
author Gong, Li.
author_sort Gong, Li.
title Visual event recognition
title_short Visual event recognition
title_full Visual event recognition
title_fullStr Visual event recognition
title_full_unstemmed Visual event recognition
title_sort visual event recognition
publishDate 2013
url http://hdl.handle.net/10356/55095
_version_ 1759856001443430400