{"id":"https://openalex.org/W2167295232","doi":"https://doi.org/10.1109/icassp.2006.1660358","title":"Automatic Image Annotation through Multi-Topic Text Categorization","display_name":"Automatic Image Annotation through Multi-Topic Text Categorization","publication_year":2006,"publication_date":"2006-08-02","ids":{"openalex":"https://openalex.org/W2167295232","doi":"https://doi.org/10.1109/icassp.2006.1660358","mag":"2167295232"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1660358","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","raw_type":"proceedings-article"},"type":"article","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/A5109192907","display_name":"Sheng Gao","orcid":"https://orcid.org/0000-0002-6090-1965"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Sheng Gao","raw_affiliation_strings":["Institute for Infocomm Research, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039835717","display_name":"Dehong Wang","orcid":"https://orcid.org/0000-0002-4157-1841"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"De-Hong Wang","raw_affiliation_strings":["Institute for Infocomm Research, Singapore","National University, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"National University, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["School of Electrical & Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical & Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5109192907"],"corresponding_institution_ids":["https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":5.6911,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.9670629,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"2","issue":null,"first_page":"II","last_page":"377"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9998999834060669,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9998999834060669,"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":0.9991000294685364,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.815204918384552},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6890001893043518},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5800215005874634},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5537042021751404},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.5366615056991577},{"id":"https://openalex.org/keywords/automatic-image-annotation","display_name":"Automatic image annotation","score":0.5136892199516296},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4962459206581116},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4656914472579956},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4636375308036804},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45813798904418945},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45360833406448364},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4464949667453766},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.43108314275741577},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4158492982387543},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4145687520503998},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3998265266418457},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36674433946609497}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.815204918384552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6890001893043518},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5800215005874634},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5537042021751404},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.5366615056991577},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.5136892199516296},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4962459206581116},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4656914472579956},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4636375308036804},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45813798904418945},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45360833406448364},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4464949667453766},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.43108314275741577},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4158492982387543},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4145687520503998},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3998265266418457},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36674433946609497},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":2,"locations":[{"id":"doi:10.1109/icassp.2006.1660358","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.655.4216","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.655.4216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ait.ac.th/%7Emdailey/cvreadings/Gao-Annotation.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1544067897","https://openalex.org/W1660390307","https://openalex.org/W1666447063","https://openalex.org/W2017822976","https://openalex.org/W2020842694","https://openalex.org/W2095844239","https://openalex.org/W2096071754","https://openalex.org/W2118714763","https://openalex.org/W2120929742","https://openalex.org/W2127411609","https://openalex.org/W2128197086","https://openalex.org/W2137471889","https://openalex.org/W2137918516","https://openalex.org/W2156336347","https://openalex.org/W2283195891","https://openalex.org/W4248892431","https://openalex.org/W4285719527","https://openalex.org/W6674793120","https://openalex.org/W6678865028"],"related_works":["https://openalex.org/W3177930984","https://openalex.org/W2052697133","https://openalex.org/W2119028572","https://openalex.org/W2376984068","https://openalex.org/W2152482390","https://openalex.org/W2365617273","https://openalex.org/W2076896210","https://openalex.org/W2093596879","https://openalex.org/W2506386910","https://openalex.org/W2117928543"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,14,22,26,31,48,53,63,66,79,129,168],"new":[3],"framework":[4],"for":[5,85,149],"automatic":[6,150],"image":[7,151],"annotation":[8,152],"through":[9],"multi-topic":[10],"text":[11,23],"categorization.":[12],"Given":[13],"test":[15,100,156],"image,":[16],"it":[17],"is":[18,39,75],"first":[19],"converted":[20],"into":[21],"document":[24,45],"using":[25],"visual":[27,54],"codebook":[28],"learnt":[29],"from":[30,108],"collection":[32],"of":[33,68,81],"training":[34],"images.":[35],"Latent":[36],"semantic":[37,117],"analysis":[38],"then":[40],"performed":[41],"on":[42,52,93,128,153,174],"the":[43,94,99,136,154,161],"tokenized":[44],"to":[46,88,91,98],"extract":[47],"feature":[49,73],"vector":[50,74],"based":[51,173],"lexicon":[55],"with":[56,78,110,132,140,146],"its":[57],"vocabulary":[58],"items":[59],"defined":[60],"as":[61],"either":[62],"codeword":[64],"or":[65,116],"co-occurrence":[67],"multiple":[69,111],"codewords.":[70],"The":[71,123],"high-dimension":[72],"finally":[76],"compared":[77,145],"set":[80,157],"topic":[82,103],"models,":[83],"one":[84],"each":[86],"concept":[87],"be":[89],"annotated,":[90],"decide":[92],"top":[95],"concepts":[96],"related":[97],"image.":[101],"These":[102],"classifiers":[104],"are":[105],"discriminatively":[106],"trained":[107],"images":[109,120],"associations,":[112],"including":[113],"spatial,":[114],"syntactic,":[115],"relationship,":[118],"between":[119],"and":[121,135,177],"concepts.":[122,143],"proposed":[124],"approach":[125],"was":[126],"evaluated":[127],"Corel":[130,155],"dataset":[131,139],"374":[133],"keywords,":[134],"TRECVID":[137],"2003":[138],"ten":[141],"selected":[142],"When":[144],"state-of-the-art":[147],"algorithms":[148],"our":[158],"system":[159],"obtained":[160],"best":[162],"results,":[163],"although":[164],"we":[165],"only":[166],"use":[167],"simple":[169],"linear":[170],"classification":[171],"model":[172],"just":[175],"texture":[176],"color":[178],"features":[179]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}