Predictable Dual-View Hashing

Mohammad Rastegari; Jonghyun Choi; Shobeir Fakhraei; Hal Daumé; Larry S. Davis

Predictable Dual-View Hashing

Mohammad Rastegari, Jonghyun Choi, Shobeir Fakhraei, Hal Daumé, Larry S. Davis

Department of Artificial Intelligence

Research output: Contribution to conference › Paper › peer-review

57 Citations (Scopus)

Abstract

We propose a Predictable Dual-View Hashing (PDH) algorithm which embeds proximity of data samples in the original spaces. We create a cross-view hamming space with the ability to compare information from previously incomparable domains with a notion of 'predictability'. By performing comparative experimental analysis on two large datasets, PASCAL-Sentence and SUN-Attribute, we demonstrate the superiority of our method to the state-of-the-art dual-view binary code learning algorithms.

Original language	English
Pages	2365-2373
Number of pages	9
Publication status	Published - 2013
Event	30th International Conference on Machine Learning, ICML 2013 - Atlanta, GA, United States Duration: 2013 Jun 16 → 2013 Jun 21

Conference

Conference	30th International Conference on Machine Learning, ICML 2013
Country/Territory	United States
City	Atlanta, GA
Period	13/6/16 → 13/6/21

All Science Journal Classification (ASJC) codes

Human-Computer Interaction
Sociology and Political Science

Cite this

@conference{a6f376bc2c9142b7bbce3d391915bca6,

title = "Predictable Dual-View Hashing",

abstract = "We propose a Predictable Dual-View Hashing (PDH) algorithm which embeds proximity of data samples in the original spaces. We create a cross-view hamming space with the ability to compare information from previously incomparable domains with a notion of 'predictability'. By performing comparative experimental analysis on two large datasets, PASCAL-Sentence and SUN-Attribute, we demonstrate the superiority of our method to the state-of-the-art dual-view binary code learning algorithms.",

author = "Mohammad Rastegari and Jonghyun Choi and Shobeir Fakhraei and Hal Daum{\'e} and Davis, {Larry S.}",

year = "2013",

language = "English",

pages = "2365--2373",

note = "30th International Conference on Machine Learning, ICML 2013 ; Conference date: 16-06-2013 Through 21-06-2013",

}

TY - CONF

T1 - Predictable Dual-View Hashing

AU - Rastegari, Mohammad

AU - Choi, Jonghyun

AU - Fakhraei, Shobeir

AU - Daumé, Hal

AU - Davis, Larry S.

PY - 2013

Y1 - 2013

N2 - We propose a Predictable Dual-View Hashing (PDH) algorithm which embeds proximity of data samples in the original spaces. We create a cross-view hamming space with the ability to compare information from previously incomparable domains with a notion of 'predictability'. By performing comparative experimental analysis on two large datasets, PASCAL-Sentence and SUN-Attribute, we demonstrate the superiority of our method to the state-of-the-art dual-view binary code learning algorithms.

AB - We propose a Predictable Dual-View Hashing (PDH) algorithm which embeds proximity of data samples in the original spaces. We create a cross-view hamming space with the ability to compare information from previously incomparable domains with a notion of 'predictability'. By performing comparative experimental analysis on two large datasets, PASCAL-Sentence and SUN-Attribute, we demonstrate the superiority of our method to the state-of-the-art dual-view binary code learning algorithms.

UR - http://www.scopus.com/inward/record.url?scp=84897498413&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897498413&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84897498413

SP - 2365

EP - 2373

T2 - 30th International Conference on Machine Learning, ICML 2013

Y2 - 16 June 2013 through 21 June 2013

ER -

Predictable Dual-View Hashing

Abstract

Conference

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this