Accelerating near-duplicate video matching by combining visual similarity and alignment distortion

In this paper, we investigate a novel approach to accelerate the matching of two video clips by exploiting the temporal coherence property inherent in the keyframe sequence of a video. Motivated by the fact that keyframe correspondences between near-duplicate videos typically follow certain spatial...

Full description

Saved in:
Bibliographic Details
Main Authors: TAN, Hung-Khoon, WU, Xiao, NGO, Chong-wah, ZHAO, Wan-Lei
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2008
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/6367
https://ink.library.smu.edu.sg/context/sis_research/article/7370/viewcontent/10.1.1.571.2964.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-7370
record_format dspace
spelling sg-smu-ink.sis_research-73702021-11-23T02:49:48Z Accelerating near-duplicate video matching by combining visual similarity and alignment distortion TAN, Hung-Khoon WU, Xiao NGO, Chong-wah ZHAO, Wan-Lei In this paper, we investigate a novel approach to accelerate the matching of two video clips by exploiting the temporal coherence property inherent in the keyframe sequence of a video. Motivated by the fact that keyframe correspondences between near-duplicate videos typically follow certain spatial arrangements, such property could be employed to guide the alignment of two keyframe sequences. We set the alignment problem as an integer quadratic programming problem, where the cost function takes into account both the visual similarity of the corresponding keyframes as well as the alignment distortion among the set of correspondences. The set of keyframe-pairs found by our algorithm provides our proposal on the list of candidate keyframe-pairs for near-duplicate detection using local interest points. This eliminates the need for exhaustive keyframe-pair comparisons, which significantly accelerates the matching speed. Experiments on a dataset of 12,790 web videos demonstrate that the proposed method maintains a similar near-duplicate video retrieval performance as the hierarchical method proposed in [12] but with a significantly reduced number of keyframe-pair comparisons. 2008-10-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/6367 info:doi/10.1145/1459359.1459506 https://ink.library.smu.edu.sg/context/sis_research/article/7370/viewcontent/10.1.1.571.2964.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Algorithms Experimentation Performance Graphics and Human Computer Interfaces Theory and Algorithms
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Algorithms
Experimentation
Performance
Graphics and Human Computer Interfaces
Theory and Algorithms
spellingShingle Algorithms
Experimentation
Performance
Graphics and Human Computer Interfaces
Theory and Algorithms
TAN, Hung-Khoon
WU, Xiao
NGO, Chong-wah
ZHAO, Wan-Lei
Accelerating near-duplicate video matching by combining visual similarity and alignment distortion
description In this paper, we investigate a novel approach to accelerate the matching of two video clips by exploiting the temporal coherence property inherent in the keyframe sequence of a video. Motivated by the fact that keyframe correspondences between near-duplicate videos typically follow certain spatial arrangements, such property could be employed to guide the alignment of two keyframe sequences. We set the alignment problem as an integer quadratic programming problem, where the cost function takes into account both the visual similarity of the corresponding keyframes as well as the alignment distortion among the set of correspondences. The set of keyframe-pairs found by our algorithm provides our proposal on the list of candidate keyframe-pairs for near-duplicate detection using local interest points. This eliminates the need for exhaustive keyframe-pair comparisons, which significantly accelerates the matching speed. Experiments on a dataset of 12,790 web videos demonstrate that the proposed method maintains a similar near-duplicate video retrieval performance as the hierarchical method proposed in [12] but with a significantly reduced number of keyframe-pair comparisons.
format text
author TAN, Hung-Khoon
WU, Xiao
NGO, Chong-wah
ZHAO, Wan-Lei
author_facet TAN, Hung-Khoon
WU, Xiao
NGO, Chong-wah
ZHAO, Wan-Lei
author_sort TAN, Hung-Khoon
title Accelerating near-duplicate video matching by combining visual similarity and alignment distortion
title_short Accelerating near-duplicate video matching by combining visual similarity and alignment distortion
title_full Accelerating near-duplicate video matching by combining visual similarity and alignment distortion
title_fullStr Accelerating near-duplicate video matching by combining visual similarity and alignment distortion
title_full_unstemmed Accelerating near-duplicate video matching by combining visual similarity and alignment distortion
title_sort accelerating near-duplicate video matching by combining visual similarity and alignment distortion
publisher Institutional Knowledge at Singapore Management University
publishDate 2008
url https://ink.library.smu.edu.sg/sis_research/6367
https://ink.library.smu.edu.sg/context/sis_research/article/7370/viewcontent/10.1.1.571.2964.pdf
_version_ 1770575943131201536