Addressing the challenge of visual information access from digital image and video libraries
While it would seem that digital video libraries should benefit from access mechanisms directed to their visual contents, years of TREC Video Retrieval Evaluation (TRECVID) research have shown that text search against transcript narrative text provides almost all the retrieval capability, even with...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 78 |
|---|---|
| container_issue | |
| container_start_page | 69 |
| container_title | |
| container_volume | |
| creator | Christel, Michael G. Conescu, Ronald M. |
| description | While it would seem that digital video libraries should benefit from access mechanisms directed to their visual contents, years of TREC Video Retrieval Evaluation (TRECVID) research have shown that text search against transcript narrative text provides almost all the retrieval capability, even with visually oriented generic topics. A within-subjects study involving 24 novice participants on TRECVID 2004 tasks again confirms this result. The study shows that satisfaction is greater and performance is significantly better on specific and generic information retrieval tasks from news broadcasts when transcripts are available for search. Additional runs with 7 expert users reveal different novice and expert interaction patterns with the video library interface, helping explain the novices' lack of success with image search and visual feature browsing for visual information needs. Analysis of TRECVID visual features well suited for particular tasks provides additional insights into the role of automated feature classification for digital image and video libraries. |
| doi_str_mv | 10.1145/1065385.1065402 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>proquest_6IE</sourceid><recordid>TN_cdi_proquest_miscellaneous_31127868</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4118518</ieee_id><sourcerecordid>31127868</sourcerecordid><originalsourceid>FETCH-LOGICAL-a278t-6633f810d449849e6663bc13549bc5b854ef559f71e17efb2b89ac245bcdce033</originalsourceid><addsrcrecordid>eNqNkDtrwzAUhQWl0FfmDl00lS5JfS3JlscQ-oJAl3YrCEm-StTaVio5hf77yiQ_oHc5cM93HxxCrqFYAHBxD0UlmBSLSXlRnpALEBKAybqSZ2SW0meRizWcsfqcfCzbNmJKftjQcYvUbnXX4bBBGhz98WmvO-oHF2KvRx8Gqq3NNHUx9LT1Gz9Ofq8zr4c2D7QYaOdN1NFjuiKnTncJZ0e9JO-PD2-r5_n69elltVzPdVnLcV5VjDkJRct5I3mDVW4YC0zwxlhhpODohGhcDQg1OlMa2WhbcmFsa7Fg7JLcHvbuYvjeYxpV75PFrtMDhn1SDCAfqmQGbw6gR0S1i_nz-Ks4gBQwuXcHV9temRC-koJCTaGqY6jqGGpGF_9ElclJOPYHs0J3WA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype><pqid>31127868</pqid></control><display><type>conference_proceeding</type><title>Addressing the challenge of visual information access from digital image and video libraries</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Christel, Michael G. ; Conescu, Ronald M.</creator><creatorcontrib>Christel, Michael G. ; Conescu, Ronald M.</creatorcontrib><description>While it would seem that digital video libraries should benefit from access mechanisms directed to their visual contents, years of TREC Video Retrieval Evaluation (TRECVID) research have shown that text search against transcript narrative text provides almost all the retrieval capability, even with visually oriented generic topics. A within-subjects study involving 24 novice participants on TRECVID 2004 tasks again confirms this result. The study shows that satisfaction is greater and performance is significantly better on specific and generic information retrieval tasks from news broadcasts when transcripts are available for search. Additional runs with 7 expert users reveal different novice and expert interaction patterns with the video library interface, helping explain the novices' lack of success with image search and visual feature browsing for visual information needs. Analysis of TRECVID visual features well suited for particular tasks provides additional insights into the role of automated feature classification for digital image and video libraries.</description><identifier>ISBN: 1581138768</identifier><identifier>ISBN: 9781581138764</identifier><identifier>DOI: 10.1145/1065385.1065402</identifier><language>eng</language><publisher>New York, NY, USA: ACM</publisher><subject>Applied computing -- Computers in other domains -- Digital libraries and archives ; Automatic testing ; Broadcasting ; Content based retrieval ; Digital images ; Human computer interaction ; Image analysis ; Image retrieval ; Indexing ; Information retrieval ; Information systems -- Information retrieval ; Information systems -- Information systems applications -- Digital libraries and archives ; Software libraries ; TRECVID results analysis ; video retrieval</subject><ispartof>Proceedings of the 5th ACM/IEEE Joint Conference on Digital Libraries : Denver, CO, USA, June 7-11, 2005 : digital libraries, cyberinfrastructure for research and education, 2005, p.69-78</ispartof><rights>2005 ACM</rights><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/4118518$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,27902,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4118518$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Christel, Michael G.</creatorcontrib><creatorcontrib>Conescu, Ronald M.</creatorcontrib><title>Addressing the challenge of visual information access from digital image and video libraries</title><title>Proceedings of the 5th ACM/IEEE Joint Conference on Digital Libraries : Denver, CO, USA, June 7-11, 2005 : digital libraries, cyberinfrastructure for research and education</title><addtitle>JCDL</addtitle><description>While it would seem that digital video libraries should benefit from access mechanisms directed to their visual contents, years of TREC Video Retrieval Evaluation (TRECVID) research have shown that text search against transcript narrative text provides almost all the retrieval capability, even with visually oriented generic topics. A within-subjects study involving 24 novice participants on TRECVID 2004 tasks again confirms this result. The study shows that satisfaction is greater and performance is significantly better on specific and generic information retrieval tasks from news broadcasts when transcripts are available for search. Additional runs with 7 expert users reveal different novice and expert interaction patterns with the video library interface, helping explain the novices' lack of success with image search and visual feature browsing for visual information needs. Analysis of TRECVID visual features well suited for particular tasks provides additional insights into the role of automated feature classification for digital image and video libraries.</description><subject>Applied computing -- Computers in other domains -- Digital libraries and archives</subject><subject>Automatic testing</subject><subject>Broadcasting</subject><subject>Content based retrieval</subject><subject>Digital images</subject><subject>Human computer interaction</subject><subject>Image analysis</subject><subject>Image retrieval</subject><subject>Indexing</subject><subject>Information retrieval</subject><subject>Information systems -- Information retrieval</subject><subject>Information systems -- Information systems applications -- Digital libraries and archives</subject><subject>Software libraries</subject><subject>TRECVID results analysis</subject><subject>video retrieval</subject><isbn>1581138768</isbn><isbn>9781581138764</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2005</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNqNkDtrwzAUhQWl0FfmDl00lS5JfS3JlscQ-oJAl3YrCEm-StTaVio5hf77yiQ_oHc5cM93HxxCrqFYAHBxD0UlmBSLSXlRnpALEBKAybqSZ2SW0meRizWcsfqcfCzbNmJKftjQcYvUbnXX4bBBGhz98WmvO-oHF2KvRx8Gqq3NNHUx9LT1Gz9Ofq8zr4c2D7QYaOdN1NFjuiKnTncJZ0e9JO-PD2-r5_n69elltVzPdVnLcV5VjDkJRct5I3mDVW4YC0zwxlhhpODohGhcDQg1OlMa2WhbcmFsa7Fg7JLcHvbuYvjeYxpV75PFrtMDhn1SDCAfqmQGbw6gR0S1i_nz-Ks4gBQwuXcHV9temRC-koJCTaGqY6jqGGpGF_9ElclJOPYHs0J3WA</recordid><startdate>20050607</startdate><enddate>20050607</enddate><creator>Christel, Michael G.</creator><creator>Conescu, Ronald M.</creator><general>ACM</general><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>20050607</creationdate><title>Addressing the challenge of visual information access from digital image and video libraries</title><author>Christel, Michael G. ; Conescu, Ronald M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a278t-6633f810d449849e6663bc13549bc5b854ef559f71e17efb2b89ac245bcdce033</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2005</creationdate><topic>Applied computing -- Computers in other domains -- Digital libraries and archives</topic><topic>Automatic testing</topic><topic>Broadcasting</topic><topic>Content based retrieval</topic><topic>Digital images</topic><topic>Human computer interaction</topic><topic>Image analysis</topic><topic>Image retrieval</topic><topic>Indexing</topic><topic>Information retrieval</topic><topic>Information systems -- Information retrieval</topic><topic>Information systems -- Information systems applications -- Digital libraries and archives</topic><topic>Software libraries</topic><topic>TRECVID results analysis</topic><topic>video retrieval</topic><toplevel>online_resources</toplevel><creatorcontrib>Christel, Michael G.</creatorcontrib><creatorcontrib>Conescu, Ronald M.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection><collection>Computer and Information Systems 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></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Christel, Michael G.</au><au>Conescu, Ronald M.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Addressing the challenge of visual information access from digital image and video libraries</atitle><btitle>Proceedings of the 5th ACM/IEEE Joint Conference on Digital Libraries : Denver, CO, USA, June 7-11, 2005 : digital libraries, cyberinfrastructure for research and education</btitle><stitle>JCDL</stitle><date>2005-06-07</date><risdate>2005</risdate><spage>69</spage><epage>78</epage><pages>69-78</pages><isbn>1581138768</isbn><isbn>9781581138764</isbn><abstract>While it would seem that digital video libraries should benefit from access mechanisms directed to their visual contents, years of TREC Video Retrieval Evaluation (TRECVID) research have shown that text search against transcript narrative text provides almost all the retrieval capability, even with visually oriented generic topics. A within-subjects study involving 24 novice participants on TRECVID 2004 tasks again confirms this result. The study shows that satisfaction is greater and performance is significantly better on specific and generic information retrieval tasks from news broadcasts when transcripts are available for search. Additional runs with 7 expert users reveal different novice and expert interaction patterns with the video library interface, helping explain the novices' lack of success with image search and visual feature browsing for visual information needs. Analysis of TRECVID visual features well suited for particular tasks provides additional insights into the role of automated feature classification for digital image and video libraries.</abstract><cop>New York, NY, USA</cop><pub>ACM</pub><doi>10.1145/1065385.1065402</doi><tpages>10</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISBN: 1581138768 |
| ispartof | Proceedings of the 5th ACM/IEEE Joint Conference on Digital Libraries : Denver, CO, USA, June 7-11, 2005 : digital libraries, cyberinfrastructure for research and education, 2005, p.69-78 |
| issn | |
| language | eng |
| recordid | cdi_proquest_miscellaneous_31127868 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Applied computing -- Computers in other domains -- Digital libraries and archives Automatic testing Broadcasting Content based retrieval Digital images Human computer interaction Image analysis Image retrieval Indexing Information retrieval Information systems -- Information retrieval Information systems -- Information systems applications -- Digital libraries and archives Software libraries TRECVID results analysis video retrieval |
| title | Addressing the challenge of visual information access from digital image and video libraries |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-13T08%3A08%3A02IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Addressing%20the%20challenge%20of%20visual%20information%20access%20from%20digital%20image%20and%20video%20libraries&rft.btitle=Proceedings%20of%20the%205th%20ACM/IEEE%20Joint%20Conference%20on%20Digital%20Libraries%20:%20Denver,%20CO,%20USA,%20June%207-11,%202005%20:%20digital%20libraries,%20cyberinfrastructure%20for%20research%20and%20education&rft.au=Christel,%20Michael%20G.&rft.date=2005-06-07&rft.spage=69&rft.epage=78&rft.pages=69-78&rft.isbn=1581138768&rft.isbn_list=9781581138764&rft_id=info:doi/10.1145/1065385.1065402&rft_dat=%3Cproquest_6IE%3E31127868%3C/proquest_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=31127868&rft_id=info:pmid/&rft_ieee_id=4118518&rfr_iscdi=true |