Cross-Modal Retrieval: A Pairwise Classification Approach

Aditya Krishna Menon; Didi Sudan; Sanjay Chawla

doi:10.1137/1.9781611974010.23

Cross-Modal Retrieval: A Pairwise Classification Approach

Aditya Krishna Menon, Didi Sudan, Sanjay Chawla

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

9 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 language	English
Title of host publication	Proceedings of the 2015 SIAM International Conference on Data Mining
Editors	Jieping Ye, Suresh Venkatasubramanian
Publisher	Society for Industrial and Applied Mathematics Publications
Pages	199-207
Number of pages	9
ISBN (Electronic)	9781510811522
DOIs	https://doi.org/10.1137/1.9781611974010.23
Publication status	Published - 2015
Event	SIAM International Conference on Data Mining 2015 - Vancouver, Canada Duration: 30 Apr 2015 → 2 May 2015 https://epubs.siam.org/doi/book/10.1137/1.9781611974010

Conference

Conference	SIAM International Conference on Data Mining 2015
Abbreviated title	SDM 2015
Country/Territory	Canada
City	Vancouver
Period	30/04/15 → 2/05/15
Internet address	https://epubs.siam.org/doi/book/10.1137/1.9781611974010

Access to Document

10.1137/1.9781611974010.23

https://epubs.siam.org/doi/pdf/10.1137/1.9781611974010.23

Cite this

@inproceedings{40dfe7c3bb3b4108a9a547b63def3d40,

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",

note = "Publisher Copyright: Copyright {\textcopyright} SIAM.; SIAM International Conference on Data Mining 2015, SDM 2015 ; Conference date: 30-04-2015 Through 02-05-2015",

year = "2015",

doi = "10.1137/1.9781611974010.23",

language = "English",

pages = "199--207",

editor = "Jieping Ye and Suresh Venkatasubramanian",

booktitle = "Proceedings of the 2015 SIAM International Conference on Data Mining",

publisher = "Society for Industrial and Applied Mathematics Publications",

address = "United States",

url = "https://epubs.siam.org/doi/book/10.1137/1.9781611974010",

}

Menon, AK, Sudan, D & Chawla, S 2015, Cross-Modal Retrieval: A Pairwise Classification Approach. in J Ye & S Venkatasubramanian (eds), Proceedings of the 2015 SIAM International Conference on Data Mining. Society for Industrial and Applied Mathematics Publications, pp. 199-207, SIAM International Conference on Data Mining 2015, Vancouver, Canada, 30/04/15. https://doi.org/10.1137/1.9781611974010.23

Cross-Modal Retrieval: A Pairwise Classification Approach. / Menon, Aditya Krishna; Sudan, Didi; Chawla, Sanjay.
Proceedings of the 2015 SIAM International Conference on Data Mining. ed. / Jieping Ye; Suresh Venkatasubramanian. Society for Industrial and Applied Mathematics Publications, 2015. p. 199-207.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Cross-Modal Retrieval: 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

U2 - 10.1137/1.9781611974010.23

DO - 10.1137/1.9781611974010.23

M3 - Conference contribution

SP - 199

EP - 207

BT - Proceedings of the 2015 SIAM International Conference on Data Mining

A2 - Ye, Jieping

A2 - Venkatasubramanian, Suresh

PB - Society for Industrial and Applied Mathematics Publications

T2 - SIAM International Conference on Data Mining 2015

Y2 - 30 April 2015 through 2 May 2015

ER -

Cross-Modal Retrieval: A Pairwise Classification Approach

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this