Distribution-based concept selection for concept-based video retrieval

Query-to-concept mapping plays one of the keys to concept-based video retrieval. Conventional approaches try to find concepts that are likely to co-occur in the relevant shots from the lexical or statistical aspects. However, the high probability of co-occurrence alone cannot ensure its effectivenes...

Full description

Saved in:
Bibliographic Details
Main Authors: CAO, Juan, JING, HongFang, NGO, Chong-wah, ZHANG, YongDong
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2009
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/6513
https://ink.library.smu.edu.sg/context/sis_research/article/7516/viewcontent/1631272.1631378.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-7516
record_format dspace
spelling sg-smu-ink.sis_research-75162022-01-10T03:56:20Z Distribution-based concept selection for concept-based video retrieval CAO, Juan JING, HongFang NGO, Chong-wah ZHANG, YongDong Query-to-concept mapping plays one of the keys to concept-based video retrieval. Conventional approaches try to find concepts that are likely to co-occur in the relevant shots from the lexical or statistical aspects. However, the high probability of co-occurrence alone cannot ensure its effectiveness to distinguish the relevant shots from the irrelevant ones. In this paper, we propose distribution-based concept selection (DBCS) for query-to-concept mapping by analyzing concept score distributions of within and between relevant and irrelevant sets. In view of the imbalance between relevant and irrelevant examples, two variants of DBCS are proposed respectively by considering the two-sided and onesided metrics of concept distributions. Specifically, the impact of positive and negative concepts toward search is explicitly considered. DBCS is found to be appropriate for both automatic and interactive video search. Using TRECVID 2008 video dataset for experiments, improvements of 50% and 34% are reported when compared to text-based and visual-based query-to-concept mapping respectively in automatic search. Meanwhile, DBCS shows continuous improvement for all rounds of user feedbacks in interactive search. 2009-10-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/6513 info:doi/10.1145/1631272.1631378 https://ink.library.smu.edu.sg/context/sis_research/article/7516/viewcontent/1631272.1631378.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 Concept-based video retrieval Distribution Query-to-concept mapping Databases and Information Systems Data Storage Systems Graphics and Human Computer Interfaces
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Concept-based video retrieval
Distribution
Query-to-concept mapping
Databases and Information Systems
Data Storage Systems
Graphics and Human Computer Interfaces
spellingShingle Concept-based video retrieval
Distribution
Query-to-concept mapping
Databases and Information Systems
Data Storage Systems
Graphics and Human Computer Interfaces
CAO, Juan
JING, HongFang
NGO, Chong-wah
ZHANG, YongDong
Distribution-based concept selection for concept-based video retrieval
description Query-to-concept mapping plays one of the keys to concept-based video retrieval. Conventional approaches try to find concepts that are likely to co-occur in the relevant shots from the lexical or statistical aspects. However, the high probability of co-occurrence alone cannot ensure its effectiveness to distinguish the relevant shots from the irrelevant ones. In this paper, we propose distribution-based concept selection (DBCS) for query-to-concept mapping by analyzing concept score distributions of within and between relevant and irrelevant sets. In view of the imbalance between relevant and irrelevant examples, two variants of DBCS are proposed respectively by considering the two-sided and onesided metrics of concept distributions. Specifically, the impact of positive and negative concepts toward search is explicitly considered. DBCS is found to be appropriate for both automatic and interactive video search. Using TRECVID 2008 video dataset for experiments, improvements of 50% and 34% are reported when compared to text-based and visual-based query-to-concept mapping respectively in automatic search. Meanwhile, DBCS shows continuous improvement for all rounds of user feedbacks in interactive search.
format text
author CAO, Juan
JING, HongFang
NGO, Chong-wah
ZHANG, YongDong
author_facet CAO, Juan
JING, HongFang
NGO, Chong-wah
ZHANG, YongDong
author_sort CAO, Juan
title Distribution-based concept selection for concept-based video retrieval
title_short Distribution-based concept selection for concept-based video retrieval
title_full Distribution-based concept selection for concept-based video retrieval
title_fullStr Distribution-based concept selection for concept-based video retrieval
title_full_unstemmed Distribution-based concept selection for concept-based video retrieval
title_sort distribution-based concept selection for concept-based video retrieval
publisher Institutional Knowledge at Singapore Management University
publishDate 2009
url https://ink.library.smu.edu.sg/sis_research/6513
https://ink.library.smu.edu.sg/context/sis_research/article/7516/viewcontent/1631272.1631378.pdf
_version_ 1770575979767398400