Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval
This paper proposes a deep hashing framework, namely, unsupervised deep video hashing (UDVH), for large-scale video similarity search with the aim to learn compact yet effective binary codes. Our UDVH produces the hash codes in a self-taught manner by jointly integrating discriminative video represe...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on image processing 2019-04, Vol.28 (4), p.1993-2007 |
|---|---|
| Hauptverfasser: | , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 2007 |
|---|---|
| container_issue | 4 |
| container_start_page | 1993 |
| container_title | IEEE transactions on image processing |
| container_volume | 28 |
| creator | Wu, Gengshen Han, Jungong Guo, Yuchen Liu, Li Ding, Guiguang Ni, Qiang Shao, Ling |
| description | This paper proposes a deep hashing framework, namely, unsupervised deep video hashing (UDVH), for large-scale video similarity search with the aim to learn compact yet effective binary codes. Our UDVH produces the hash codes in a self-taught manner by jointly integrating discriminative video representation with optimal code learning, where an efficient alternating approach is adopted to optimize the objective function. The key differences from most existing video hashing methods lie in: 1) UDVH is an unsupervised hashing method that generates hash codes by cooperatively utilizing feature clustering and a specifically designed binarization with the original neighborhood structure preserved in the binary space and 2) a specific rotation is developed and applied onto video features such that the variance of each dimension can be balanced, thus facilitating the subsequent quantization step. Extensive experiments performed on three popular video datasets show that the UDVH is overwhelmingly better than the state of the arts in terms of various evaluation metrics, which makes it practical in real-world applications. |
| doi_str_mv | 10.1109/TIP.2018.2882155 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_pubmed_primary_30452370</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8540456</ieee_id><sourcerecordid>2136068454</sourcerecordid><originalsourceid>FETCH-LOGICAL-c389t-881f78b1a5c22452933049854abdca1512060a35ac7c08fdb9e273dc0094ccd23</originalsourceid><addsrcrecordid>eNpdkMtLw0AQhxdRrFbvgiABL15SZ1_J7lHro4WCr9Zr2G4mNSVt4m5T8L93S2sPnmZgvhl-8xFyQaFHKejb8fC1x4CqHlOKUSkPyAnVgsYAgh2GHmQap1ToDjn1fg5AhaTJMelwEJLxFE7I22Tp2wbduvSYRw-ITfRZ5lhHA-O_yuUsWpcmujeVWdow79c5RkXtopFxM4w_rKlwx7_jypW4NtUZOSpM5fF8V7tk8vQ47g_i0cvzsH83ii1XehUrRYtUTamRlrGQRvMQSispzDS3hkrKIAHDpbGpBVXkU40s5bkF0MLanPEuudnebVz93aJfZYvSW6xCVKxbnzHKE0iUkCKg1__Qed26ZUgXKJlqSEWyoWBLWVd777DIGlcujPvJKGQb3VnQnW10ZzvdYeVqd7idLjDfL_z5DcDlFigRcT8OXwYg4b9TeYD1</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2157907464</pqid></control><display><type>article</type><title>Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval</title><source>IEEE Electronic Library (IEL)</source><creator>Wu, Gengshen ; Han, Jungong ; Guo, Yuchen ; Liu, Li ; Ding, Guiguang ; Ni, Qiang ; Shao, Ling</creator><creatorcontrib>Wu, Gengshen ; Han, Jungong ; Guo, Yuchen ; Liu, Li ; Ding, Guiguang ; Ni, Qiang ; Shao, Ling</creatorcontrib><description>This paper proposes a deep hashing framework, namely, unsupervised deep video hashing (UDVH), for large-scale video similarity search with the aim to learn compact yet effective binary codes. Our UDVH produces the hash codes in a self-taught manner by jointly integrating discriminative video representation with optimal code learning, where an efficient alternating approach is adopted to optimize the objective function. The key differences from most existing video hashing methods lie in: 1) UDVH is an unsupervised hashing method that generates hash codes by cooperatively utilizing feature clustering and a specifically designed binarization with the original neighborhood structure preserved in the binary space and 2) a specific rotation is developed and applied onto video features such that the variance of each dimension can be balanced, thus facilitating the subsequent quantization step. Extensive experiments performed on three popular video datasets show that the UDVH is overwhelmingly better than the state of the arts in terms of various evaluation metrics, which makes it practical in real-world applications.</description><identifier>ISSN: 1057-7149</identifier><identifier>EISSN: 1941-0042</identifier><identifier>DOI: 10.1109/TIP.2018.2882155</identifier><identifier>PMID: 30452370</identifier><identifier>CODEN: IIPRE4</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>balanced rotation ; Binary codes ; Clustering ; deep learning ; Feature extraction ; feature representation ; Hamming distance ; Nickel ; Optimization ; Quantization (signal) ; similarity retrieval ; Training ; Video hashing</subject><ispartof>IEEE transactions on image processing, 2019-04, Vol.28 (4), p.1993-2007</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c389t-881f78b1a5c22452933049854abdca1512060a35ac7c08fdb9e273dc0094ccd23</citedby><cites>FETCH-LOGICAL-c389t-881f78b1a5c22452933049854abdca1512060a35ac7c08fdb9e273dc0094ccd23</cites><orcidid>0000-0002-4593-1656 ; 0000-0002-8264-6117 ; 0000-0001-9808-9805 ; 0000-0003-4361-956X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8540456$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>315,781,785,797,27929,27930,54763</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/8540456$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/30452370$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Wu, Gengshen</creatorcontrib><creatorcontrib>Han, Jungong</creatorcontrib><creatorcontrib>Guo, Yuchen</creatorcontrib><creatorcontrib>Liu, Li</creatorcontrib><creatorcontrib>Ding, Guiguang</creatorcontrib><creatorcontrib>Ni, Qiang</creatorcontrib><creatorcontrib>Shao, Ling</creatorcontrib><title>Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval</title><title>IEEE transactions on image processing</title><addtitle>TIP</addtitle><addtitle>IEEE Trans Image Process</addtitle><description>This paper proposes a deep hashing framework, namely, unsupervised deep video hashing (UDVH), for large-scale video similarity search with the aim to learn compact yet effective binary codes. Our UDVH produces the hash codes in a self-taught manner by jointly integrating discriminative video representation with optimal code learning, where an efficient alternating approach is adopted to optimize the objective function. The key differences from most existing video hashing methods lie in: 1) UDVH is an unsupervised hashing method that generates hash codes by cooperatively utilizing feature clustering and a specifically designed binarization with the original neighborhood structure preserved in the binary space and 2) a specific rotation is developed and applied onto video features such that the variance of each dimension can be balanced, thus facilitating the subsequent quantization step. Extensive experiments performed on three popular video datasets show that the UDVH is overwhelmingly better than the state of the arts in terms of various evaluation metrics, which makes it practical in real-world applications.</description><subject>balanced rotation</subject><subject>Binary codes</subject><subject>Clustering</subject><subject>deep learning</subject><subject>Feature extraction</subject><subject>feature representation</subject><subject>Hamming distance</subject><subject>Nickel</subject><subject>Optimization</subject><subject>Quantization (signal)</subject><subject>similarity retrieval</subject><subject>Training</subject><subject>Video hashing</subject><issn>1057-7149</issn><issn>1941-0042</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpdkMtLw0AQhxdRrFbvgiABL15SZ1_J7lHro4WCr9Zr2G4mNSVt4m5T8L93S2sPnmZgvhl-8xFyQaFHKejb8fC1x4CqHlOKUSkPyAnVgsYAgh2GHmQap1ToDjn1fg5AhaTJMelwEJLxFE7I22Tp2wbduvSYRw-ITfRZ5lhHA-O_yuUsWpcmujeVWdow79c5RkXtopFxM4w_rKlwx7_jypW4NtUZOSpM5fF8V7tk8vQ47g_i0cvzsH83ii1XehUrRYtUTamRlrGQRvMQSispzDS3hkrKIAHDpbGpBVXkU40s5bkF0MLanPEuudnebVz93aJfZYvSW6xCVKxbnzHKE0iUkCKg1__Qed26ZUgXKJlqSEWyoWBLWVd777DIGlcujPvJKGQb3VnQnW10ZzvdYeVqd7idLjDfL_z5DcDlFigRcT8OXwYg4b9TeYD1</recordid><startdate>20190401</startdate><enddate>20190401</enddate><creator>Wu, Gengshen</creator><creator>Han, Jungong</creator><creator>Guo, Yuchen</creator><creator>Liu, Li</creator><creator>Ding, Guiguang</creator><creator>Ni, Qiang</creator><creator>Shao, Ling</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</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>7X8</scope><orcidid>https://orcid.org/0000-0002-4593-1656</orcidid><orcidid>https://orcid.org/0000-0002-8264-6117</orcidid><orcidid>https://orcid.org/0000-0001-9808-9805</orcidid><orcidid>https://orcid.org/0000-0003-4361-956X</orcidid></search><sort><creationdate>20190401</creationdate><title>Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval</title><author>Wu, Gengshen ; Han, Jungong ; Guo, Yuchen ; Liu, Li ; Ding, Guiguang ; Ni, Qiang ; Shao, Ling</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c389t-881f78b1a5c22452933049854abdca1512060a35ac7c08fdb9e273dc0094ccd23</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>balanced rotation</topic><topic>Binary codes</topic><topic>Clustering</topic><topic>deep learning</topic><topic>Feature extraction</topic><topic>feature representation</topic><topic>Hamming distance</topic><topic>Nickel</topic><topic>Optimization</topic><topic>Quantization (signal)</topic><topic>similarity retrieval</topic><topic>Training</topic><topic>Video hashing</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Wu, Gengshen</creatorcontrib><creatorcontrib>Han, Jungong</creatorcontrib><creatorcontrib>Guo, Yuchen</creatorcontrib><creatorcontrib>Liu, Li</creatorcontrib><creatorcontrib>Ding, Guiguang</creatorcontrib><creatorcontrib>Ni, Qiang</creatorcontrib><creatorcontrib>Shao, Ling</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>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>MEDLINE - Academic</collection><jtitle>IEEE transactions on image processing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Wu, Gengshen</au><au>Han, Jungong</au><au>Guo, Yuchen</au><au>Liu, Li</au><au>Ding, Guiguang</au><au>Ni, Qiang</au><au>Shao, Ling</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval</atitle><jtitle>IEEE transactions on image processing</jtitle><stitle>TIP</stitle><addtitle>IEEE Trans Image Process</addtitle><date>2019-04-01</date><risdate>2019</risdate><volume>28</volume><issue>4</issue><spage>1993</spage><epage>2007</epage><pages>1993-2007</pages><issn>1057-7149</issn><eissn>1941-0042</eissn><coden>IIPRE4</coden><abstract>This paper proposes a deep hashing framework, namely, unsupervised deep video hashing (UDVH), for large-scale video similarity search with the aim to learn compact yet effective binary codes. Our UDVH produces the hash codes in a self-taught manner by jointly integrating discriminative video representation with optimal code learning, where an efficient alternating approach is adopted to optimize the objective function. The key differences from most existing video hashing methods lie in: 1) UDVH is an unsupervised hashing method that generates hash codes by cooperatively utilizing feature clustering and a specifically designed binarization with the original neighborhood structure preserved in the binary space and 2) a specific rotation is developed and applied onto video features such that the variance of each dimension can be balanced, thus facilitating the subsequent quantization step. Extensive experiments performed on three popular video datasets show that the UDVH is overwhelmingly better than the state of the arts in terms of various evaluation metrics, which makes it practical in real-world applications.</abstract><cop>United States</cop><pub>IEEE</pub><pmid>30452370</pmid><doi>10.1109/TIP.2018.2882155</doi><tpages>15</tpages><orcidid>https://orcid.org/0000-0002-4593-1656</orcidid><orcidid>https://orcid.org/0000-0002-8264-6117</orcidid><orcidid>https://orcid.org/0000-0001-9808-9805</orcidid><orcidid>https://orcid.org/0000-0003-4361-956X</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1057-7149 |
| ispartof | IEEE transactions on image processing, 2019-04, Vol.28 (4), p.1993-2007 |
| issn | 1057-7149 1941-0042 |
| language | eng |
| recordid | cdi_pubmed_primary_30452370 |
| source | IEEE Electronic Library (IEL) |
| subjects | balanced rotation Binary codes Clustering deep learning Feature extraction feature representation Hamming distance Nickel Optimization Quantization (signal) similarity retrieval Training Video hashing |
| title | Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-15T20%3A02%3A28IST&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=Unsupervised%20Deep%20Video%20Hashing%20via%20Balanced%20Code%20for%20Large-Scale%20Video%20Retrieval&rft.jtitle=IEEE%20transactions%20on%20image%20processing&rft.au=Wu,%20Gengshen&rft.date=2019-04-01&rft.volume=28&rft.issue=4&rft.spage=1993&rft.epage=2007&rft.pages=1993-2007&rft.issn=1057-7149&rft.eissn=1941-0042&rft.coden=IIPRE4&rft_id=info:doi/10.1109/TIP.2018.2882155&rft_dat=%3Cproquest_RIE%3E2136068454%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=2157907464&rft_id=info:pmid/30452370&rft_ieee_id=8540456&rfr_iscdi=true |