A Framework for crowdsourced multimedia processing and querying

Alessandro Bozzon; Ilio Catallo; Eleonora Ciceri; Piero Fraternali; Davide Martinenghi; Marco Tagliasacchi

A Framework for crowdsourced multimedia processing and querying

Alessandro Bozzon, Ilio Catallo, Eleonora Ciceri, Piero Fraternali, Davide Martinenghi, Marco Tagliasacchi

Research output: Contribution to journal › Article › Scientific › peer-review

Abstract

This paper introduces a conceptual and architectural frame- work for addressing the design, execution and verification of tasks by a crowd of performers. The proposed framework is substantiated by an ongoing application to a problem of trademark logo detection in video collections. Preliminary results show that the contribution of crowds can improve the recall of state-of-the-art traditional algorithms, with no loss in terms of precision. However, task-to-executor matching, as expected, has an important influence on the task performance.

Original language	English
Pages (from-to)	3-8
Number of pages	6
Journal	CEUR Workshop Proceedings
Volume	842
Publication status	Published - 2012
Externally published	Yes

Keywords

Crowdsourcing
Human Computation
Multimedia

Cite this

@article{905fee7b4c734f7f973a0caee0c17842,

title = "A Framework for crowdsourced multimedia processing and querying",

abstract = "This paper introduces a conceptual and architectural frame- work for addressing the design, execution and verification of tasks by a crowd of performers. The proposed framework is substantiated by an ongoing application to a problem of trademark logo detection in video collections. Preliminary results show that the contribution of crowds can improve the recall of state-of-the-art traditional algorithms, with no loss in terms of precision. However, task-to-executor matching, as expected, has an important influence on the task performance.",

keywords = "Crowdsourcing, Human Computation, Multimedia",

author = "Alessandro Bozzon and Ilio Catallo and Eleonora Ciceri and Piero Fraternali and Davide Martinenghi and Marco Tagliasacchi",

year = "2012",

language = "English",

volume = "842",

pages = "3--8",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

publisher = "CEUR-WS",

}

TY - JOUR

T1 - A Framework for crowdsourced multimedia processing and querying

AU - Bozzon, Alessandro

AU - Catallo, Ilio

AU - Ciceri, Eleonora

AU - Fraternali, Piero

AU - Martinenghi, Davide

AU - Tagliasacchi, Marco

PY - 2012

Y1 - 2012

N2 - This paper introduces a conceptual and architectural frame- work for addressing the design, execution and verification of tasks by a crowd of performers. The proposed framework is substantiated by an ongoing application to a problem of trademark logo detection in video collections. Preliminary results show that the contribution of crowds can improve the recall of state-of-the-art traditional algorithms, with no loss in terms of precision. However, task-to-executor matching, as expected, has an important influence on the task performance.

AB - This paper introduces a conceptual and architectural frame- work for addressing the design, execution and verification of tasks by a crowd of performers. The proposed framework is substantiated by an ongoing application to a problem of trademark logo detection in video collections. Preliminary results show that the contribution of crowds can improve the recall of state-of-the-art traditional algorithms, with no loss in terms of precision. However, task-to-executor matching, as expected, has an important influence on the task performance.

KW - Crowdsourcing

KW - Human Computation

KW - Multimedia

UR - http://www.scopus.com/inward/record.url?scp=84892559229&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84892559229

SN - 1613-0073

VL - 842

SP - 3

EP - 8

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

ER -

A Framework for crowdsourced multimedia processing and querying

Abstract

Keywords

Other files and links

Fingerprint

Cite this