Cross-Media database retrieval system based on TOTEM

Authors:
Cheng Zeng;Haiyang Zhou;Bing Yan
Affiliations:
State Key Lab of Software Engineering, Wuhan University, Wuhan, P.R. China;State Key Lab of Software Engineering, Wuhan University, Wuhan, P.R. China;Hubei University of Economics, Wuhan, P.R. China
Venue:
WISE'06 Proceedings of the 7th international conference on Web Information Systems
Year:
2006

Citing 9
Cited 0

OCTOPUS: aggressive search of multi-modality data using multifaceted knowledge base

Proceedings of the 11th international conference on World Wide Web
A multi-paradigm querying approach for a generic multimedia database management system

ACM SIGMOD Record
Deputy Mechanisms for Object-Oriented Databases

ICDE '95 Proceedings of the Eleventh International Conference on Data Engineering
Automatic image annotation and retrieval using cross-media relevance models

Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval
Using Object Deputy Model to Prepare Data for Data Warehousing

IEEE Transactions on Knowledge and Data Engineering
Information server for highly-connected cross-media publishing

Information Systems - Special issue: The 15th international conference on advanced information systems engineering (CAiSE 2003)
Semantic-based cross-media image retrieval

ICAPR'05 Proceedings of the Third international conference on Pattern Recognition and Image Analysis - Volume Part II
Data mining based on objects in video flow with dynamic background

ADMA'05 Proceedings of the First international conference on Advanced Data Mining and Applications
Understanding multimedia document semantics for cross-media retrieval

PCM'05 Proceedings of the 6th Pacific-Rim conference on Advances in Multimedia Information Processing - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a model CSRM for realizing cross-media semantic retrieval in multimedia digital library. The object semantic is regarded as the core of all semantic information which is mined by maximum likelihood estimate method. Bayesian network instantiation, Markov chain are respectively utilized to recognize dynamic scene semantic and complex event semantic. Semantic templates are constructed to store the mapping relation between media features and semantic concepts so that all media in multimedia digital library could be automatically annotated. Besides, user could retrieve cross-media information with media example set in real time. A prototype system of cross-media retrieval based on TOTEM is constructed to prove the validity of CSRM and flexibility of data management.