Domain adaptive semantic diffusion for large scale context-based video annotation

Learning to cope with domain change has been known as a challenging problem in many real-world applications. This paper proposes a novel and efficient approach, named domain adaptive semantic diffusion (DASD), to exploit semantic context while considering the domain-shift-of-context for large scale...

Full description

Saved in:
Bibliographic Details
Main Authors: JIANG, Yu-Gang, WANG, Jun, CHANG, Shih-Fu, NGO, Chong-wah
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2009
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/6625
https://ink.library.smu.edu.sg/context/sis_research/article/7628/viewcontent/10.1.1.442.9011.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-7628
record_format dspace
spelling sg-smu-ink.sis_research-76282022-01-14T03:42:33Z Domain adaptive semantic diffusion for large scale context-based video annotation JIANG, Yu-Gang WANG, Jun CHANG, Shih-Fu NGO, Chong-wah Learning to cope with domain change has been known as a challenging problem in many real-world applications. This paper proposes a novel and efficient approach, named domain adaptive semantic diffusion (DASD), to exploit semantic context while considering the domain-shift-of-context for large scale video concept annotation. Starting with a large set of concept detectors, the proposed DASD refines the initial annotation results using graph diffusion technique, which preserves the consistency and smoothness of the annotation over a semantic graph. Different from the existing graph learning methods which capture relations among data samples, the semantic graph treats concepts as nodes and the concept affinities as the weights of edges. Particularly, the DASD approach is capable of simultaneously improving the annotation results and adapting the concept affinities to new test data. The adaptation provides a means to handle domain change between training and test data, which occurs very often in video annotation task. We conduct extensive experiments to improve annotation results of 374 concepts over 340 hours of videos from TRECVID 2005-2007 data sets. Results show consistent and significant performance gain over various baselines. In addition, the proposed approach is very efficient, completing DASD over 374 concepts within just 2 milliseconds for each video shot on a regular PC. 2009-10-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/6625 info:doi/10.1109/ICCV.2009.5459295 https://ink.library.smu.edu.sg/context/sis_research/article/7628/viewcontent/10.1.1.442.9011.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 Databases and Information 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 Databases and Information Systems
Graphics and Human Computer Interfaces
spellingShingle Databases and Information Systems
Graphics and Human Computer Interfaces
JIANG, Yu-Gang
WANG, Jun
CHANG, Shih-Fu
NGO, Chong-wah
Domain adaptive semantic diffusion for large scale context-based video annotation
description Learning to cope with domain change has been known as a challenging problem in many real-world applications. This paper proposes a novel and efficient approach, named domain adaptive semantic diffusion (DASD), to exploit semantic context while considering the domain-shift-of-context for large scale video concept annotation. Starting with a large set of concept detectors, the proposed DASD refines the initial annotation results using graph diffusion technique, which preserves the consistency and smoothness of the annotation over a semantic graph. Different from the existing graph learning methods which capture relations among data samples, the semantic graph treats concepts as nodes and the concept affinities as the weights of edges. Particularly, the DASD approach is capable of simultaneously improving the annotation results and adapting the concept affinities to new test data. The adaptation provides a means to handle domain change between training and test data, which occurs very often in video annotation task. We conduct extensive experiments to improve annotation results of 374 concepts over 340 hours of videos from TRECVID 2005-2007 data sets. Results show consistent and significant performance gain over various baselines. In addition, the proposed approach is very efficient, completing DASD over 374 concepts within just 2 milliseconds for each video shot on a regular PC.
format text
author JIANG, Yu-Gang
WANG, Jun
CHANG, Shih-Fu
NGO, Chong-wah
author_facet JIANG, Yu-Gang
WANG, Jun
CHANG, Shih-Fu
NGO, Chong-wah
author_sort JIANG, Yu-Gang
title Domain adaptive semantic diffusion for large scale context-based video annotation
title_short Domain adaptive semantic diffusion for large scale context-based video annotation
title_full Domain adaptive semantic diffusion for large scale context-based video annotation
title_fullStr Domain adaptive semantic diffusion for large scale context-based video annotation
title_full_unstemmed Domain adaptive semantic diffusion for large scale context-based video annotation
title_sort domain adaptive semantic diffusion for large scale context-based video annotation
publisher Institutional Knowledge at Singapore Management University
publishDate 2009
url https://ink.library.smu.edu.sg/sis_research/6625
https://ink.library.smu.edu.sg/context/sis_research/article/7628/viewcontent/10.1.1.442.9011.pdf
_version_ 1770576012190416896