End-to-End Attention-based Image Captioning

In this paper, we address the problem of image captioning specifically for molecular translation where the result would be a predicted chemical notation in InChI format for a given molecular structure. Current approaches mainly follow rule-based or CNN+RNN based methodology. However, they seem to un...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-04
Main Authors: Sundaramoorthy, Carola, Lin Ziwen Kelvin, Sarin, Mahak, Gupta, Shubham
Format: Article
Language:English
Subjects:
Molecular structure
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 Sundaramoorthy, Carola
Lin Ziwen Kelvin
Sarin, Mahak
Gupta, Shubham
description In this paper, we address the problem of image captioning specifically for molecular translation where the result would be a predicted chemical notation in InChI format for a given molecular structure. Current approaches mainly follow rule-based or CNN+RNN based methodology. However, they seem to underperform on noisy images and images with small number of distinguishable features. To overcome this, we propose an end-to-end transformer model. When compared to attention-based techniques, our proposed model outperforms on molecular datasets.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2521274431</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2521274431</sourcerecordid><originalsourceid>FETCH-proquest_journals_25212744313</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mTQds1L0S3J1wVSCo4lJal5JZn5ebpJicWpKQqeuYnpqQrOiQUgscy8dB4G1rTEnOJUXijNzaDs5hri7KFbUJRfWJpaXBKflV9alAeUijcyNTI0MjcxMTY0Jk4VAP0PMIo</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2521274431</pqid></control><display><type>article</type><title>End-to-End Attention-based Image Captioning</title><source>Publicly Available Content Database</source><creator>Sundaramoorthy, Carola ; Lin Ziwen Kelvin ; Sarin, Mahak ; Gupta, Shubham</creator><creatorcontrib>Sundaramoorthy, Carola ; Lin Ziwen Kelvin ; Sarin, Mahak ; Gupta, Shubham</creatorcontrib><description>In this paper, we address the problem of image captioning specifically for molecular translation where the result would be a predicted chemical notation in InChI format for a given molecular structure. Current approaches mainly follow rule-based or CNN+RNN based methodology. However, they seem to underperform on noisy images and images with small number of distinguishable features. To overcome this, we propose an end-to-end transformer model. When compared to attention-based techniques, our proposed model outperforms on molecular datasets.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Molecular structure</subject><ispartof>arXiv.org, 2021-04</ispartof><rights>2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (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/2521274431?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25752,37011,44589</link.rule.ids></links><search><creatorcontrib>Sundaramoorthy, Carola</creatorcontrib><creatorcontrib>Lin Ziwen Kelvin</creatorcontrib><creatorcontrib>Sarin, Mahak</creatorcontrib><creatorcontrib>Gupta, Shubham</creatorcontrib><title>End-to-End Attention-based Image Captioning</title><title>arXiv.org</title><description>In this paper, we address the problem of image captioning specifically for molecular translation where the result would be a predicted chemical notation in InChI format for a given molecular structure. Current approaches mainly follow rule-based or CNN+RNN based methodology. However, they seem to underperform on noisy images and images with small number of distinguishable features. To overcome this, we propose an end-to-end transformer model. When compared to attention-based techniques, our proposed model outperforms on molecular datasets.</description><subject>Molecular structure</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mTQds1L0S3J1wVSCo4lJal5JZn5ebpJicWpKQqeuYnpqQrOiQUgscy8dB4G1rTEnOJUXijNzaDs5hri7KFbUJRfWJpaXBKflV9alAeUijcyNTI0MjcxMTY0Jk4VAP0PMIo</recordid><startdate>20210430</startdate><enddate>20210430</enddate><creator>Sundaramoorthy, Carola</creator><creator>Lin Ziwen Kelvin</creator><creator>Sarin, Mahak</creator><creator>Gupta, Shubham</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>20210430</creationdate><title>End-to-End Attention-based Image Captioning</title><author>Sundaramoorthy, Carola ; Lin Ziwen Kelvin ; Sarin, Mahak ; Gupta, Shubham</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_25212744313</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Molecular structure</topic><toplevel>online_resources</toplevel><creatorcontrib>Sundaramoorthy, Carola</creatorcontrib><creatorcontrib>Lin Ziwen Kelvin</creatorcontrib><creatorcontrib>Sarin, Mahak</creatorcontrib><creatorcontrib>Gupta, Shubham</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</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>Sundaramoorthy, Carola</au><au>Lin Ziwen Kelvin</au><au>Sarin, Mahak</au><au>Gupta, Shubham</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>End-to-End Attention-based Image Captioning</atitle><jtitle>arXiv.org</jtitle><date>2021-04-30</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>In this paper, we address the problem of image captioning specifically for molecular translation where the result would be a predicted chemical notation in InChI format for a given molecular structure. Current approaches mainly follow rule-based or CNN+RNN based methodology. However, they seem to underperform on noisy images and images with small number of distinguishable features. To overcome this, we propose an end-to-end transformer model. When compared to attention-based techniques, our proposed model outperforms on molecular datasets.</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, 2021-04
issn 2331-8422
language eng
recordid cdi_proquest_journals_2521274431
source Publicly Available Content Database
subjects Molecular structure
title End-to-End Attention-based Image Captioning
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-12T00%3A42%3A40IST&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=End-to-End%20Attention-based%20Image%20Captioning&rft.jtitle=arXiv.org&rft.au=Sundaramoorthy,%20Carola&rft.date=2021-04-30&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2521274431%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_25212744313%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2521274431&rft_id=info:pmid/&rfr_iscdi=true