Multimodal Similarity-Preserving Hashing
We introduce an efficient computational framework for hashing data belonging to multiple modalities into a single representation space where they become mutually comparable. The proposed approach is based on a novel coupled siamese neural network architecture and allows unified treatment of intra- a...
Gespeichert in:
Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence 2014-04, Vol.36 (4), p.824-830 |
---|---|
Hauptverfasser: | , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 830 |
---|---|
container_issue | 4 |
container_start_page | 824 |
container_title | IEEE transactions on pattern analysis and machine intelligence |
container_volume | 36 |
creator | Masci, Jonathan Bronstein, Michael M. Bronstein, Alexander M. Schmidhuber, Jürgen |
description | We introduce an efficient computational framework for hashing data belonging to multiple modalities into a single representation space where they become mutually comparable. The proposed approach is based on a novel coupled siamese neural network architecture and allows unified treatment of intra- and inter-modality similarity learning. Unlike existing cross-modality similarity learning approaches, our hashing functions are not limited to binarized linear projections and can assume arbitrarily complex forms. We show experimentally that our method significantly outperforms state-of-the-art hashing approaches on multimedia retrieval tasks. |
doi_str_mv | 10.1109/TPAMI.2013.225 |
format | Article |
fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_pubmed_primary_26353203</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6654144</ieee_id><sourcerecordid>1711535608</sourcerecordid><originalsourceid>FETCH-LOGICAL-c406t-1be4918e06caac5b55902b88626ca81bf134f6754093cb9424bb2415480c97e03</originalsourceid><addsrcrecordid>eNqF0EtLAzEQwPEgitbq1YsgBRG8bJ3Jq8mxFB8Fi4J6XrIxqyn7qElX6Lc32qrgxdNA8stA_oQcIQwRQV883o9n0yEFZENKxRbpoWY6Y4LpbdIDlDRTiqo9sh_jHAC5ALZL9qhMggLrkfNZVy193T6bavDga1-Z4Jer7D646MK7b14GNya-pnlAdkpTRXe4mX3ydHX5OLnJbu-up5PxbWY5yGWGheMalQNpjbGiEEIDLZSSNB0oLEpkvJQjwUEzW2hOeVFQjoIrsHrkgPXJ-XrvIrRvnYvLvPbRuqoyjWu7mOMIUTAhQf1PBQOtqdY60dM_dN52oUkfSSqFHNGUKqnhWtnQxhhcmS-Cr01Y5Qj5Z-78K3f-mTtPudODk83arqjd8w__7pvA2QaYaE1VBtNYH3-d4sAkyuSO1847536upRQcOWcfK9uMrA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1511072162</pqid></control><display><type>article</type><title>Multimodal Similarity-Preserving Hashing</title><source>IEEE Electronic Library (IEL)</source><creator>Masci, Jonathan ; Bronstein, Michael M. ; Bronstein, Alexander M. ; Schmidhuber, Jürgen</creator><creatorcontrib>Masci, Jonathan ; Bronstein, Michael M. ; Bronstein, Alexander M. ; Schmidhuber, Jürgen</creatorcontrib><description>We introduce an efficient computational framework for hashing data belonging to multiple modalities into a single representation space where they become mutually comparable. The proposed approach is based on a novel coupled siamese neural network architecture and allows unified treatment of intra- and inter-modality similarity learning. Unlike existing cross-modality similarity learning approaches, our hashing functions are not limited to binarized linear projections and can assume arbitrarily complex forms. We show experimentally that our method significantly outperforms state-of-the-art hashing approaches on multimedia retrieval tasks.</description><identifier>ISSN: 0162-8828</identifier><identifier>EISSN: 1939-3539</identifier><identifier>EISSN: 2160-9292</identifier><identifier>DOI: 10.1109/TPAMI.2013.225</identifier><identifier>PMID: 26353203</identifier><identifier>CODEN: ITPIDJ</identifier><language>eng</language><publisher>Los Alamitos, CA: IEEE</publisher><subject>Applied sciences ; Architecture (computers) ; Artificial intelligence ; Computer science; control theory; systems ; Connectionism. Neural networks ; Data processing. List processing. Character string processing ; Exact sciences and technology ; feature descriptor ; Information systems. Data bases ; Learning ; Mathematical analysis ; Measurement ; Memory organisation. Data processing ; metric learning ; Multimedia ; neural network ; Neural networks ; Nonlinear dynamics and nonlinear dynamical systems ; Optimization ; Physics ; Representations ; Similarity ; Similarity-sensitive hashing ; Software ; Statistical physics, thermodynamics, and nonlinear dynamical systems ; Synchronization ; coupled oscillators ; Tasks ; Training ; Vectors</subject><ispartof>IEEE transactions on pattern analysis and machine intelligence, 2014-04, Vol.36 (4), p.824-830</ispartof><rights>2015 INIST-CNRS</rights><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Apr 2014</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c406t-1be4918e06caac5b55902b88626ca81bf134f6754093cb9424bb2415480c97e03</citedby><cites>FETCH-LOGICAL-c406t-1be4918e06caac5b55902b88626ca81bf134f6754093cb9424bb2415480c97e03</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6654144$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6654144$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=28403616$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/26353203$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Masci, Jonathan</creatorcontrib><creatorcontrib>Bronstein, Michael M.</creatorcontrib><creatorcontrib>Bronstein, Alexander M.</creatorcontrib><creatorcontrib>Schmidhuber, Jürgen</creatorcontrib><title>Multimodal Similarity-Preserving Hashing</title><title>IEEE transactions on pattern analysis and machine intelligence</title><addtitle>TPAMI</addtitle><addtitle>IEEE Trans Pattern Anal Mach Intell</addtitle><description>We introduce an efficient computational framework for hashing data belonging to multiple modalities into a single representation space where they become mutually comparable. The proposed approach is based on a novel coupled siamese neural network architecture and allows unified treatment of intra- and inter-modality similarity learning. Unlike existing cross-modality similarity learning approaches, our hashing functions are not limited to binarized linear projections and can assume arbitrarily complex forms. We show experimentally that our method significantly outperforms state-of-the-art hashing approaches on multimedia retrieval tasks.</description><subject>Applied sciences</subject><subject>Architecture (computers)</subject><subject>Artificial intelligence</subject><subject>Computer science; control theory; systems</subject><subject>Connectionism. Neural networks</subject><subject>Data processing. List processing. Character string processing</subject><subject>Exact sciences and technology</subject><subject>feature descriptor</subject><subject>Information systems. Data bases</subject><subject>Learning</subject><subject>Mathematical analysis</subject><subject>Measurement</subject><subject>Memory organisation. Data processing</subject><subject>metric learning</subject><subject>Multimedia</subject><subject>neural network</subject><subject>Neural networks</subject><subject>Nonlinear dynamics and nonlinear dynamical systems</subject><subject>Optimization</subject><subject>Physics</subject><subject>Representations</subject><subject>Similarity</subject><subject>Similarity-sensitive hashing</subject><subject>Software</subject><subject>Statistical physics, thermodynamics, and nonlinear dynamical systems</subject><subject>Synchronization ; coupled oscillators</subject><subject>Tasks</subject><subject>Training</subject><subject>Vectors</subject><issn>0162-8828</issn><issn>1939-3539</issn><issn>2160-9292</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2014</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNqF0EtLAzEQwPEgitbq1YsgBRG8bJ3Jq8mxFB8Fi4J6XrIxqyn7qElX6Lc32qrgxdNA8stA_oQcIQwRQV883o9n0yEFZENKxRbpoWY6Y4LpbdIDlDRTiqo9sh_jHAC5ALZL9qhMggLrkfNZVy193T6bavDga1-Z4Jer7D646MK7b14GNya-pnlAdkpTRXe4mX3ydHX5OLnJbu-up5PxbWY5yGWGheMalQNpjbGiEEIDLZSSNB0oLEpkvJQjwUEzW2hOeVFQjoIrsHrkgPXJ-XrvIrRvnYvLvPbRuqoyjWu7mOMIUTAhQf1PBQOtqdY60dM_dN52oUkfSSqFHNGUKqnhWtnQxhhcmS-Cr01Y5Qj5Z-78K3f-mTtPudODk83arqjd8w__7pvA2QaYaE1VBtNYH3-d4sAkyuSO1847536upRQcOWcfK9uMrA</recordid><startdate>20140401</startdate><enddate>20140401</enddate><creator>Masci, Jonathan</creator><creator>Bronstein, Michael M.</creator><creator>Bronstein, Alexander M.</creator><creator>Schmidhuber, Jürgen</creator><general>IEEE</general><general>IEEE Computer Society</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>IQODW</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>F28</scope><scope>FR3</scope><scope>7X8</scope></search><sort><creationdate>20140401</creationdate><title>Multimodal Similarity-Preserving Hashing</title><author>Masci, Jonathan ; Bronstein, Michael M. ; Bronstein, Alexander M. ; Schmidhuber, Jürgen</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c406t-1be4918e06caac5b55902b88626ca81bf134f6754093cb9424bb2415480c97e03</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2014</creationdate><topic>Applied sciences</topic><topic>Architecture (computers)</topic><topic>Artificial intelligence</topic><topic>Computer science; control theory; systems</topic><topic>Connectionism. Neural networks</topic><topic>Data processing. List processing. Character string processing</topic><topic>Exact sciences and technology</topic><topic>feature descriptor</topic><topic>Information systems. Data bases</topic><topic>Learning</topic><topic>Mathematical analysis</topic><topic>Measurement</topic><topic>Memory organisation. Data processing</topic><topic>metric learning</topic><topic>Multimedia</topic><topic>neural network</topic><topic>Neural networks</topic><topic>Nonlinear dynamics and nonlinear dynamical systems</topic><topic>Optimization</topic><topic>Physics</topic><topic>Representations</topic><topic>Similarity</topic><topic>Similarity-sensitive hashing</topic><topic>Software</topic><topic>Statistical physics, thermodynamics, and nonlinear dynamical systems</topic><topic>Synchronization ; coupled oscillators</topic><topic>Tasks</topic><topic>Training</topic><topic>Vectors</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Masci, Jonathan</creatorcontrib><creatorcontrib>Bronstein, Michael M.</creatorcontrib><creatorcontrib>Bronstein, Alexander M.</creatorcontrib><creatorcontrib>Schmidhuber, Jürgen</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>Pascal-Francis</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><collection>MEDLINE - Academic</collection><jtitle>IEEE transactions on pattern analysis and machine intelligence</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Masci, Jonathan</au><au>Bronstein, Michael M.</au><au>Bronstein, Alexander M.</au><au>Schmidhuber, Jürgen</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Multimodal Similarity-Preserving Hashing</atitle><jtitle>IEEE transactions on pattern analysis and machine intelligence</jtitle><stitle>TPAMI</stitle><addtitle>IEEE Trans Pattern Anal Mach Intell</addtitle><date>2014-04-01</date><risdate>2014</risdate><volume>36</volume><issue>4</issue><spage>824</spage><epage>830</epage><pages>824-830</pages><issn>0162-8828</issn><eissn>1939-3539</eissn><eissn>2160-9292</eissn><coden>ITPIDJ</coden><abstract>We introduce an efficient computational framework for hashing data belonging to multiple modalities into a single representation space where they become mutually comparable. The proposed approach is based on a novel coupled siamese neural network architecture and allows unified treatment of intra- and inter-modality similarity learning. Unlike existing cross-modality similarity learning approaches, our hashing functions are not limited to binarized linear projections and can assume arbitrarily complex forms. We show experimentally that our method significantly outperforms state-of-the-art hashing approaches on multimedia retrieval tasks.</abstract><cop>Los Alamitos, CA</cop><pub>IEEE</pub><pmid>26353203</pmid><doi>10.1109/TPAMI.2013.225</doi><tpages>7</tpages></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | ISSN: 0162-8828 |
ispartof | IEEE transactions on pattern analysis and machine intelligence, 2014-04, Vol.36 (4), p.824-830 |
issn | 0162-8828 1939-3539 2160-9292 |
language | eng |
recordid | cdi_pubmed_primary_26353203 |
source | IEEE Electronic Library (IEL) |
subjects | Applied sciences Architecture (computers) Artificial intelligence Computer science control theory systems Connectionism. Neural networks Data processing. List processing. Character string processing Exact sciences and technology feature descriptor Information systems. Data bases Learning Mathematical analysis Measurement Memory organisation. Data processing metric learning Multimedia neural network Neural networks Nonlinear dynamics and nonlinear dynamical systems Optimization Physics Representations Similarity Similarity-sensitive hashing Software Statistical physics, thermodynamics, and nonlinear dynamical systems Synchronization coupled oscillators Tasks Training Vectors |
title | Multimodal Similarity-Preserving Hashing |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T00%3A35%3A48IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Multimodal%20Similarity-Preserving%20Hashing&rft.jtitle=IEEE%20transactions%20on%20pattern%20analysis%20and%20machine%20intelligence&rft.au=Masci,%20Jonathan&rft.date=2014-04-01&rft.volume=36&rft.issue=4&rft.spage=824&rft.epage=830&rft.pages=824-830&rft.issn=0162-8828&rft.eissn=1939-3539&rft.coden=ITPIDJ&rft_id=info:doi/10.1109/TPAMI.2013.225&rft_dat=%3Cproquest_RIE%3E1711535608%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1511072162&rft_id=info:pmid/26353203&rft_ieee_id=6654144&rfr_iscdi=true |