{"id":"https://openalex.org/W2090571927","doi":"https://doi.org/10.1145/2072298.2071930","title":"Combining image and text features","display_name":"Combining image and text features","publication_year":2011,"publication_date":"2011-11-28","ids":{"openalex":"https://openalex.org/W2090571927","doi":"https://doi.org/10.1145/2072298.2071930","mag":"2090571927"},"language":"en","primary_location":{"id":"doi:10.1145/2072298.2071930","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2072298.2071930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113536035","display_name":"Sam S. Tsai","orcid":"https://orcid.org/0000-0002-7220-9108"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sam S. Tsai","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675683","display_name":"David Chen","orcid":"https://orcid.org/0009-0002-8386-7840"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Chen","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103172393","display_name":"Huizhong Chen","orcid":"https://orcid.org/0000-0002-9160-6571"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huizhong Chen","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062062165","display_name":"Cheng-Hsin Hsu","orcid":"https://orcid.org/0009-0008-5856-8201"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng-Hsin Hsu","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan Roc","National Tsing-Hua University, Hsinchu, Taiwan, ROC#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan Roc","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"National Tsing-Hua University, Hsinchu, Taiwan, ROC#TAB#","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088588796","display_name":"Kyu-Han Kim","orcid":"https://orcid.org/0000-0002-8247-225X"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyu-Han Kim","raw_affiliation_strings":["HP Laboratories, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Laboratories, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082866143","display_name":"Jatinder Singh","orcid":"https://orcid.org/0000-0002-5102-6564"},"institutions":[{"id":"https://openalex.org/I58534130","display_name":"Deutsche Telekom (United Kingdom)","ror":"https://ror.org/00qxrgg46","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210093367","https://openalex.org/I58534130"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jatinder P. Singh","raw_affiliation_strings":["Deutsche Telekom R&D Laboratories USA, Los Altos, CA, USA","Deutsche Telekom R&D Laboratories USA, Los Altos, CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deutsche Telekom R&D Laboratories USA, Los Altos, CA, USA","institution_ids":[]},{"raw_affiliation_string":"Deutsche Telekom R&D Laboratories USA, Los Altos, CA, USA#TAB#","institution_ids":["https://openalex.org/I58534130"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004042863","display_name":"Bernd Girod","orcid":"https://orcid.org/0000-0001-6950-1020"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bernd Girod","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6156,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.92592424,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.8090837001800537},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.746145486831665},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6630752086639404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6324732303619385},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5925185680389404},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4930243194103241},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.49268990755081177},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44532787799835205},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43706780672073364},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42780637741088867},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4226968586444855}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.8090837001800537},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.746145486831665},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6630752086639404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6324732303619385},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5925185680389404},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4930243194103241},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.49268990755081177},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44532787799835205},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43706780672073364},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42780637741088867},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4226968586444855},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2072298.2071930","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2072298.2071930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W93684869","https://openalex.org/W191231183","https://openalex.org/W1978394996","https://openalex.org/W1998354075","https://openalex.org/W2043114845","https://openalex.org/W2046059220","https://openalex.org/W2054945570","https://openalex.org/W2055223283","https://openalex.org/W2078997308","https://openalex.org/W2085261163","https://openalex.org/W2119605622","https://openalex.org/W2128017662","https://openalex.org/W2137139302","https://openalex.org/W2148809531","https://openalex.org/W2160484851","https://openalex.org/W2621280964","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3037187668","https://openalex.org/W4330338194","https://openalex.org/W2118758177","https://openalex.org/W2153520307","https://openalex.org/W2151459719","https://openalex.org/W623261610","https://openalex.org/W4234772502","https://openalex.org/W2036523811","https://openalex.org/W4232264032","https://openalex.org/W1988462741"],"abstract_inverted_index":{"Despite":[0],"the":[1,65,86,102,111,116,154],"successful":[2],"use":[3],"of":[4,85,101,152,161],"local":[5],"image":[6,37,57,68,83,89,96,145],"features":[7,84],"for":[8],"large-scale":[9],"object":[10],"recognition,":[11],"they":[12],"are":[13,90,105],"not":[14,34],"effective":[15],"in":[16,123],"recognizing":[17],"book":[18,26,66,78,87,94,119,125],"spines":[19,27],"on":[20],"bookshelves.":[21],"This":[22],"is":[23,69],"because":[24],"some":[25],"contain":[28],"only":[29,148],"text":[30,63,80],"components":[31],"that":[32,48,141],"do":[33],"yield":[35],"distinguishing":[36],"features.":[38],"To":[39],"overcome":[40],"this":[41],"issue,":[42],"we":[43],"develop":[44],"a":[45,50,77,93,124,150,159],"new":[46],"approach":[47],"combines":[49],"text-based":[51,143],"spine":[52,59,67,79,88,95],"recognition":[53,60,120],"pipeline":[54,121],"with":[55],"an":[56],"feature-based":[58,146],"pipeline.":[61],"The":[62,82,98,137],"within":[64],"recognized":[70],"and":[71,129],"used":[72,122],"as":[73],"keywords":[74],"to":[75,109,133],"search":[76,99],"database.":[81,97],"searched":[91],"through":[92],"results":[100,139],"two":[103],"approaches":[104],"then":[106],"carefully":[107],"combined":[108],"form":[110],"final":[112],"result.":[113],"We":[114],"implement":[115],"proposed":[117,155],"hybrid":[118,156],"inventory":[126],"management":[127],"system,":[128],"conduct":[130],"extensive":[131],"experiments":[132],"evaluate":[134],"its":[135],"performance.":[136],"experimental":[138],"show":[140],"while":[142],"or":[144],"systems":[147],"achieve":[149],"recall":[151,160],"72%,":[153],"system":[157],"achieves":[158],"~91%.":[162]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}