Loading…

VISALOGY: Answering Visual Analogy Questions

In this paper, we study the problem of answering visual analogy questions. These questions take the form of image A is to image B as image C is to what. Answering these questions entails discovering the mapping from image A to image B and then extending the mapping to image C and searching for the i...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2015-10
Main Authors: Sadeghi, Fereshteh, Zitnick, C Lawrence, Farhadi, Ali
Format: Article
Language:English
Subjects:
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Sadeghi, Fereshteh
Zitnick, C Lawrence
Farhadi, Ali
description In this paper, we study the problem of answering visual analogy questions. These questions take the form of image A is to image B as image C is to what. Answering these questions entails discovering the mapping from image A to image B and then extending the mapping to image C and searching for the image D such that the relation from A to B holds for C to D. We pose this problem as learning an embedding that encourages pairs of analogous images with similar transformations to be close together using convolutional neural networks with a quadruple Siamese architecture. We introduce a dataset of visual analogy questions in natural images, and show first results of its kind on solving analogy questions on natural images.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2084096277</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2084096277</sourcerecordid><originalsourceid>FETCH-proquest_journals_20840962773</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mTQCfMMdvTxd4-0UnDMKy5PLcrMS1cIyywuTcwBCiTm5KdXKgSWphaXZObnFfMwsKYl5hSn8kJpbgZlN9cQZw_dgqL8QpCi-Kz80iKgruJ4IwMLEwNLMyNzc2PiVAEAIPIw6w</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2084096277</pqid></control><display><type>article</type><title>VISALOGY: Answering Visual Analogy Questions</title><source>Publicly Available Content Database</source><creator>Sadeghi, Fereshteh ; Zitnick, C Lawrence ; Farhadi, Ali</creator><creatorcontrib>Sadeghi, Fereshteh ; Zitnick, C Lawrence ; Farhadi, Ali</creatorcontrib><description>In this paper, we study the problem of answering visual analogy questions. These questions take the form of image A is to image B as image C is to what. Answering these questions entails discovering the mapping from image A to image B and then extending the mapping to image C and searching for the image D such that the relation from A to B holds for C to D. We pose this problem as learning an embedding that encourages pairs of analogous images with similar transformations to be close together using convolutional neural networks with a quadruple Siamese architecture. We introduce a dataset of visual analogy questions in natural images, and show first results of its kind on solving analogy questions on natural images.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Artificial neural networks ; Mapping ; Neural networks</subject><ispartof>arXiv.org, 2015-10</ispartof><rights>2015. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2084096277?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,44590</link.rule.ids></links><search><creatorcontrib>Sadeghi, Fereshteh</creatorcontrib><creatorcontrib>Zitnick, C Lawrence</creatorcontrib><creatorcontrib>Farhadi, Ali</creatorcontrib><title>VISALOGY: Answering Visual Analogy Questions</title><title>arXiv.org</title><description>In this paper, we study the problem of answering visual analogy questions. These questions take the form of image A is to image B as image C is to what. Answering these questions entails discovering the mapping from image A to image B and then extending the mapping to image C and searching for the image D such that the relation from A to B holds for C to D. We pose this problem as learning an embedding that encourages pairs of analogous images with similar transformations to be close together using convolutional neural networks with a quadruple Siamese architecture. We introduce a dataset of visual analogy questions in natural images, and show first results of its kind on solving analogy questions on natural images.</description><subject>Artificial neural networks</subject><subject>Mapping</subject><subject>Neural networks</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2015</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mTQCfMMdvTxd4-0UnDMKy5PLcrMS1cIyywuTcwBCiTm5KdXKgSWphaXZObnFfMwsKYl5hSn8kJpbgZlN9cQZw_dgqL8QpCi-Kz80iKgruJ4IwMLEwNLMyNzc2PiVAEAIPIw6w</recordid><startdate>20151030</startdate><enddate>20151030</enddate><creator>Sadeghi, Fereshteh</creator><creator>Zitnick, C Lawrence</creator><creator>Farhadi, Ali</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20151030</creationdate><title>VISALOGY: Answering Visual Analogy Questions</title><author>Sadeghi, Fereshteh ; Zitnick, C Lawrence ; Farhadi, Ali</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_20840962773</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2015</creationdate><topic>Artificial neural networks</topic><topic>Mapping</topic><topic>Neural networks</topic><toplevel>online_resources</toplevel><creatorcontrib>Sadeghi, Fereshteh</creatorcontrib><creatorcontrib>Zitnick, C Lawrence</creatorcontrib><creatorcontrib>Farhadi, Ali</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Sadeghi, Fereshteh</au><au>Zitnick, C Lawrence</au><au>Farhadi, Ali</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>VISALOGY: Answering Visual Analogy Questions</atitle><jtitle>arXiv.org</jtitle><date>2015-10-30</date><risdate>2015</risdate><eissn>2331-8422</eissn><abstract>In this paper, we study the problem of answering visual analogy questions. These questions take the form of image A is to image B as image C is to what. Answering these questions entails discovering the mapping from image A to image B and then extending the mapping to image C and searching for the image D such that the relation from A to B holds for C to D. We pose this problem as learning an embedding that encourages pairs of analogous images with similar transformations to be close together using convolutional neural networks with a quadruple Siamese architecture. We introduce a dataset of visual analogy questions in natural images, and show first results of its kind on solving analogy questions on natural images.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2015-10
issn 2331-8422
language eng
recordid cdi_proquest_journals_2084096277
source Publicly Available Content Database
subjects Artificial neural networks
Mapping
Neural networks
title VISALOGY: Answering Visual Analogy Questions
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T16%3A37%3A06IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=VISALOGY:%20Answering%20Visual%20Analogy%20Questions&rft.jtitle=arXiv.org&rft.au=Sadeghi,%20Fereshteh&rft.date=2015-10-30&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2084096277%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_20840962773%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2084096277&rft_id=info:pmid/&rfr_iscdi=true