Modeling video hyperlinks with hypergraph for web video reranking

In this paper, we investigate a novel approach of exploiting visual-duplicates for web video reranking using hypergraph. Current graph-based reranking approaches consider mainly the pair-wise linking of keyframes and ignore reliability issues that are inherent in such representation. We exploit high...

Full description

Saved in:
Bibliographic Details
Main Authors: TAN, Hung-Khoon, NGO, Chong-wah, WU, Xiao
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2008
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/6511
https://ink.library.smu.edu.sg/context/sis_research/article/7514/viewcontent/1459359.1459453.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-7514
record_format dspace
spelling sg-smu-ink.sis_research-75142022-01-10T03:57:01Z Modeling video hyperlinks with hypergraph for web video reranking TAN, Hung-Khoon NGO, Chong-wah WU, Xiao In this paper, we investigate a novel approach of exploiting visual-duplicates for web video reranking using hypergraph. Current graph-based reranking approaches consider mainly the pair-wise linking of keyframes and ignore reliability issues that are inherent in such representation. We exploit higher order relation to overcome the issues of missing links in visual-duplicate keyframes and in addition identify the latent relationships among keyframes. Based on hypergraph, we consider two groups of video threads: visual near-duplicate threads and story threads, to hyperlink web videos and describe the higher order information existing in video content. To facilitate reranking using random walk algorithm, the hypergraph is converted to a star-like graph using star expansion algorithm. Experiments on a dataset of 12,790 web videos show that hypergraph reranking can improve web video retrieval up to 45% over the initial ranked result by the video sharing websites and 8.3% over the pair-wise based graph reranking in mean average precision (MAP). 2008-10-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/6511 info:doi/10.1145/1459359.1459453 https://ink.library.smu.edu.sg/context/sis_research/article/7514/viewcontent/1459359.1459453.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 Data Storage Systems 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
Data Storage Systems
Theory and Algorithms
spellingShingle Algorithms
Experimentation
Performance
Data Storage Systems
Theory and Algorithms
TAN, Hung-Khoon
NGO, Chong-wah
WU, Xiao
Modeling video hyperlinks with hypergraph for web video reranking
description In this paper, we investigate a novel approach of exploiting visual-duplicates for web video reranking using hypergraph. Current graph-based reranking approaches consider mainly the pair-wise linking of keyframes and ignore reliability issues that are inherent in such representation. We exploit higher order relation to overcome the issues of missing links in visual-duplicate keyframes and in addition identify the latent relationships among keyframes. Based on hypergraph, we consider two groups of video threads: visual near-duplicate threads and story threads, to hyperlink web videos and describe the higher order information existing in video content. To facilitate reranking using random walk algorithm, the hypergraph is converted to a star-like graph using star expansion algorithm. Experiments on a dataset of 12,790 web videos show that hypergraph reranking can improve web video retrieval up to 45% over the initial ranked result by the video sharing websites and 8.3% over the pair-wise based graph reranking in mean average precision (MAP).
format text
author TAN, Hung-Khoon
NGO, Chong-wah
WU, Xiao
author_facet TAN, Hung-Khoon
NGO, Chong-wah
WU, Xiao
author_sort TAN, Hung-Khoon
title Modeling video hyperlinks with hypergraph for web video reranking
title_short Modeling video hyperlinks with hypergraph for web video reranking
title_full Modeling video hyperlinks with hypergraph for web video reranking
title_fullStr Modeling video hyperlinks with hypergraph for web video reranking
title_full_unstemmed Modeling video hyperlinks with hypergraph for web video reranking
title_sort modeling video hyperlinks with hypergraph for web video reranking
publisher Institutional Knowledge at Singapore Management University
publishDate 2008
url https://ink.library.smu.edu.sg/sis_research/6511
https://ink.library.smu.edu.sg/context/sis_research/article/7514/viewcontent/1459359.1459453.pdf
_version_ 1770575979406688256