Ohsu @ MediaEval 2015: Adapting textual techniques to multimedia search

Shiran Dudy, Steven Bedrick

Research output: Contribution to journalArticle

Abstract

In this paper, we present the motivation, process, results and analysis of results that we have worked on as part of our participation in the 2015 MediaEval Retrieving Diverse Social Images Task. This year, we adapted a recently-published technique for result diversification ("Relational Learning-to-Rank" [13]), borrowed from the world of standard document retrieval. As compared to the original work, our version makes certain changes to the ranking and comparison algorithm, and explores a variety of feature combinations specific to an image retrieval context. The key idea behind our technique was a greedy iterative approach to ranking search results, which attempted to balance relevance with redundancy by comparing candidate results to those already selected by the algorithm. Our approach worked tolerably well on many queries, but there is clearly room for improvement.

Original languageEnglish (US)
JournalUnknown Journal
Volume1436
StatePublished - 2015

Fingerprint

Multimedia
Image retrieval
Redundancy
Motivation
Learning

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Ohsu @ MediaEval 2015 : Adapting textual techniques to multimedia search. / Dudy, Shiran; Bedrick, Steven.

In: Unknown Journal, Vol. 1436, 2015.

Research output: Contribution to journalArticle

@article{fbb9c744cd70433e99748316681c5e63,
title = "Ohsu @ MediaEval 2015: Adapting textual techniques to multimedia search",
abstract = "In this paper, we present the motivation, process, results and analysis of results that we have worked on as part of our participation in the 2015 MediaEval Retrieving Diverse Social Images Task. This year, we adapted a recently-published technique for result diversification ({"}Relational Learning-to-Rank{"} [13]), borrowed from the world of standard document retrieval. As compared to the original work, our version makes certain changes to the ranking and comparison algorithm, and explores a variety of feature combinations specific to an image retrieval context. The key idea behind our technique was a greedy iterative approach to ranking search results, which attempted to balance relevance with redundancy by comparing candidate results to those already selected by the algorithm. Our approach worked tolerably well on many queries, but there is clearly room for improvement.",
author = "Shiran Dudy and Steven Bedrick",
year = "2015",
language = "English (US)",
volume = "1436",
journal = "Indian Journal of Rheumatology",
issn = "0973-3698",
publisher = "Elsevier (Singapore) Pte Ltd",

}

TY - JOUR

T1 - Ohsu @ MediaEval 2015

T2 - Adapting textual techniques to multimedia search

AU - Dudy, Shiran

AU - Bedrick, Steven

PY - 2015

Y1 - 2015

N2 - In this paper, we present the motivation, process, results and analysis of results that we have worked on as part of our participation in the 2015 MediaEval Retrieving Diverse Social Images Task. This year, we adapted a recently-published technique for result diversification ("Relational Learning-to-Rank" [13]), borrowed from the world of standard document retrieval. As compared to the original work, our version makes certain changes to the ranking and comparison algorithm, and explores a variety of feature combinations specific to an image retrieval context. The key idea behind our technique was a greedy iterative approach to ranking search results, which attempted to balance relevance with redundancy by comparing candidate results to those already selected by the algorithm. Our approach worked tolerably well on many queries, but there is clearly room for improvement.

AB - In this paper, we present the motivation, process, results and analysis of results that we have worked on as part of our participation in the 2015 MediaEval Retrieving Diverse Social Images Task. This year, we adapted a recently-published technique for result diversification ("Relational Learning-to-Rank" [13]), borrowed from the world of standard document retrieval. As compared to the original work, our version makes certain changes to the ranking and comparison algorithm, and explores a variety of feature combinations specific to an image retrieval context. The key idea behind our technique was a greedy iterative approach to ranking search results, which attempted to balance relevance with redundancy by comparing candidate results to those already selected by the algorithm. Our approach worked tolerably well on many queries, but there is clearly room for improvement.

UR - http://www.scopus.com/inward/record.url?scp=84989840245&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84989840245&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84989840245

VL - 1436

JO - Indian Journal of Rheumatology

JF - Indian Journal of Rheumatology

SN - 0973-3698

ER -