Blind late fusion in multimedia event retrieval

One of the challenges in Multimedia Event Retrieval is the integration of data from multiple modalities. A modality is defined as a single channel of sensory input, such as visual or audio. We also refer to this as data source. Previous research has shown that the integration of different data sourc...

Full description

Saved in:
Bibliographic Details
Main Authors: DE BOER, Maaike H. T., SCHUTTE, Klamer, ZHANG, Hao, LU, Yi-Jie, NGO, Chong-wah, KRAAIJ, Wessel
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2016
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/6420
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-7423
record_format dspace
spelling sg-smu-ink.sis_research-74232021-11-23T01:36:02Z Blind late fusion in multimedia event retrieval DE BOER, Maaike H. T. SCHUTTE, Klamer ZHANG, Hao LU, Yi-Jie NGO, Chong-wah KRAAIJ, Wessel One of the challenges in Multimedia Event Retrieval is the integration of data from multiple modalities. A modality is defined as a single channel of sensory input, such as visual or audio. We also refer to this as data source. Previous research has shown that the integration of different data sources can improve performance compared to only using one source, but a clear insight of success factors of alternative fusion methods is still lacking. We introduce several new blind late fusion methods based on inversions and ratios of the state-of-the-art blind fusion methods and compare performance in both simulations and an international benchmark data set in multimedia event retrieval named TRECVID MED. The results show that five of the proposed methods outperform the state-of-the-art methods in a case with sufficient training examples (100 examples). The novel fusion method named JRER is not only the best method with dependent data sources, but this method is also a robust method in all simulations with sufficient training examples. 2016-11-01T07:00:00Z text https://ink.library.smu.edu.sg/sis_research/6420 info:doi/10.1007/s13735-016-0112-9 Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Multimedia event retrieval Multimodal Integration Late fusion 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 Multimedia event retrieval
Multimodal
Integration
Late fusion
Data Storage Systems
Graphics and Human Computer Interfaces
spellingShingle Multimedia event retrieval
Multimodal
Integration
Late fusion
Data Storage Systems
Graphics and Human Computer Interfaces
DE BOER, Maaike H. T.
SCHUTTE, Klamer
ZHANG, Hao
LU, Yi-Jie
NGO, Chong-wah
KRAAIJ, Wessel
Blind late fusion in multimedia event retrieval
description One of the challenges in Multimedia Event Retrieval is the integration of data from multiple modalities. A modality is defined as a single channel of sensory input, such as visual or audio. We also refer to this as data source. Previous research has shown that the integration of different data sources can improve performance compared to only using one source, but a clear insight of success factors of alternative fusion methods is still lacking. We introduce several new blind late fusion methods based on inversions and ratios of the state-of-the-art blind fusion methods and compare performance in both simulations and an international benchmark data set in multimedia event retrieval named TRECVID MED. The results show that five of the proposed methods outperform the state-of-the-art methods in a case with sufficient training examples (100 examples). The novel fusion method named JRER is not only the best method with dependent data sources, but this method is also a robust method in all simulations with sufficient training examples.
format text
author DE BOER, Maaike H. T.
SCHUTTE, Klamer
ZHANG, Hao
LU, Yi-Jie
NGO, Chong-wah
KRAAIJ, Wessel
author_facet DE BOER, Maaike H. T.
SCHUTTE, Klamer
ZHANG, Hao
LU, Yi-Jie
NGO, Chong-wah
KRAAIJ, Wessel
author_sort DE BOER, Maaike H. T.
title Blind late fusion in multimedia event retrieval
title_short Blind late fusion in multimedia event retrieval
title_full Blind late fusion in multimedia event retrieval
title_fullStr Blind late fusion in multimedia event retrieval
title_full_unstemmed Blind late fusion in multimedia event retrieval
title_sort blind late fusion in multimedia event retrieval
publisher Institutional Knowledge at Singapore Management University
publishDate 2016
url https://ink.library.smu.edu.sg/sis_research/6420
_version_ 1770575957299560448