Cross-modal retrieval: A pairwise classification approach

Aditya Krishna Menon, Didi Sudan, Sanjay Chawla

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

Content is increasingly available in multiple modalities (such as images, text, and video), each of which provides a different representation of some entity. The cross-modal retrieval problem is: given the representation of an entity in one modality, find its best representation in all other modalities. We propose a novel approach to this problem based on pairwise classification. The approach seamlessly applies to both the settings where ground-truth annotations for the entities are absent and present. In the former case, the approach considers both positive and unlabelled links that arise in standard cross-modal retrieval datasets. Empirical comparisons show improvements over state-of-the-art methods for cross-modal retrieval.

Original languageEnglish
Title of host publicationSIAM International Conference on Data Mining 2015, SDM 2015
PublisherSociety for Industrial and Applied Mathematics Publications
Pages199-207
Number of pages9
ISBN (Print)9781510811522
Publication statusPublished - 2015
Externally publishedYes
EventSIAM International Conference on Data Mining 2015, SDM 2015 - Vancouver, Canada
Duration: 30 Apr 20152 May 2015

Other

OtherSIAM International Conference on Data Mining 2015, SDM 2015
CountryCanada
CityVancouver
Period30/4/152/5/15

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Menon, A. K., Sudan, D., & Chawla, S. (2015). Cross-modal retrieval: A pairwise classification approach. In SIAM International Conference on Data Mining 2015, SDM 2015 (pp. 199-207). Society for Industrial and Applied Mathematics Publications.

Cross-modal retrieval : A pairwise classification approach. / Menon, Aditya Krishna; Sudan, Didi; Chawla, Sanjay.

SIAM International Conference on Data Mining 2015, SDM 2015. Society for Industrial and Applied Mathematics Publications, 2015. p. 199-207.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Menon, AK, Sudan, D & Chawla, S 2015, Cross-modal retrieval: A pairwise classification approach. in SIAM International Conference on Data Mining 2015, SDM 2015. Society for Industrial and Applied Mathematics Publications, pp. 199-207, SIAM International Conference on Data Mining 2015, SDM 2015, Vancouver, Canada, 30/4/15.
Menon AK, Sudan D, Chawla S. Cross-modal retrieval: A pairwise classification approach. In SIAM International Conference on Data Mining 2015, SDM 2015. Society for Industrial and Applied Mathematics Publications. 2015. p. 199-207
Menon, Aditya Krishna ; Sudan, Didi ; Chawla, Sanjay. / Cross-modal retrieval : A pairwise classification approach. SIAM International Conference on Data Mining 2015, SDM 2015. Society for Industrial and Applied Mathematics Publications, 2015. pp. 199-207
@inproceedings{67d485b7729a4fabb80374920a22cf29,
title = "Cross-modal retrieval: A pairwise classification approach",
abstract = "Content is increasingly available in multiple modalities (such as images, text, and video), each of which provides a different representation of some entity. The cross-modal retrieval problem is: given the representation of an entity in one modality, find its best representation in all other modalities. We propose a novel approach to this problem based on pairwise classification. The approach seamlessly applies to both the settings where ground-truth annotations for the entities are absent and present. In the former case, the approach considers both positive and unlabelled links that arise in standard cross-modal retrieval datasets. Empirical comparisons show improvements over state-of-the-art methods for cross-modal retrieval.",
author = "Menon, {Aditya Krishna} and Didi Sudan and Sanjay Chawla",
year = "2015",
language = "English",
isbn = "9781510811522",
pages = "199--207",
booktitle = "SIAM International Conference on Data Mining 2015, SDM 2015",
publisher = "Society for Industrial and Applied Mathematics Publications",

}

TY - GEN

T1 - Cross-modal retrieval

T2 - A pairwise classification approach

AU - Menon, Aditya Krishna

AU - Sudan, Didi

AU - Chawla, Sanjay

PY - 2015

Y1 - 2015

N2 - Content is increasingly available in multiple modalities (such as images, text, and video), each of which provides a different representation of some entity. The cross-modal retrieval problem is: given the representation of an entity in one modality, find its best representation in all other modalities. We propose a novel approach to this problem based on pairwise classification. The approach seamlessly applies to both the settings where ground-truth annotations for the entities are absent and present. In the former case, the approach considers both positive and unlabelled links that arise in standard cross-modal retrieval datasets. Empirical comparisons show improvements over state-of-the-art methods for cross-modal retrieval.

AB - Content is increasingly available in multiple modalities (such as images, text, and video), each of which provides a different representation of some entity. The cross-modal retrieval problem is: given the representation of an entity in one modality, find its best representation in all other modalities. We propose a novel approach to this problem based on pairwise classification. The approach seamlessly applies to both the settings where ground-truth annotations for the entities are absent and present. In the former case, the approach considers both positive and unlabelled links that arise in standard cross-modal retrieval datasets. Empirical comparisons show improvements over state-of-the-art methods for cross-modal retrieval.

UR - http://www.scopus.com/inward/record.url?scp=84961878145&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961878145&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84961878145

SN - 9781510811522

SP - 199

EP - 207

BT - SIAM International Conference on Data Mining 2015, SDM 2015

PB - Society for Industrial and Applied Mathematics Publications

ER -