{"id":"https://openalex.org/W2948427397","doi":"https://doi.org/10.1109/tmm.2019.2920620","title":"Learning Semantic Text Features for Web Text-Aided Image Classification","display_name":"Learning Semantic Text Features for Web Text-Aided Image Classification","publication_year":2019,"publication_date":"2019-06-03","ids":{"openalex":"https://openalex.org/W2948427397","doi":"https://doi.org/10.1109/tmm.2019.2920620","mag":"2948427397"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2019.2920620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2920620","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5041201587","display_name":"Dongzhe Wang","orcid":"https://orcid.org/0000-0002-1467-6023"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dongzhe Wang","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-1467-6023","affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066203581","display_name":"Kezhi Mao","orcid":"https://orcid.org/0000-0002-9191-8604"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kezhi Mao","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-9191-8604","affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1186,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.82104335,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"21","issue":"12","first_page":"2985","last_page":"2996"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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":0.9990000128746033,"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/T11714","display_name":"Multimodal Machine Learning Applications","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8475874662399292},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6622247695922852},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.561335027217865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5447550415992737},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.457286536693573},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35966455936431885},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33795079588890076}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8475874662399292},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6622247695922852},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.561335027217865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5447550415992737},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.457286536693573},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35966455936431885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33795079588890076},{"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:10.1109/tmm.2019.2920620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2920620","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.7599999904632568,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":109,"referenced_works":["https://openalex.org/W154472438","https://openalex.org/W1481442092","https://openalex.org/W1482034470","https://openalex.org/W1566135517","https://openalex.org/W1567302070","https://openalex.org/W1576445103","https://openalex.org/W1606858007","https://openalex.org/W1614298861","https://openalex.org/W1686810756","https://openalex.org/W1832693441","https://openalex.org/W1849277567","https://openalex.org/W1895577753","https://openalex.org/W1895989618","https://openalex.org/W1905882502","https://openalex.org/W1965963232","https://openalex.org/W1968752118","https://openalex.org/W1978394996","https://openalex.org/W2000355138","https://openalex.org/W2007510844","https://openalex.org/W2027922120","https://openalex.org/W2032723017","https://openalex.org/W2048261712","https://openalex.org/W2050183447","https://openalex.org/W2070792803","https://openalex.org/W2071168618","https://openalex.org/W2082025208","https://openalex.org/W2086478842","https://openalex.org/W2090923791","https://openalex.org/W2095288130","https://openalex.org/W2101234009","https://openalex.org/W2107250100","https://openalex.org/W2108598243","https://openalex.org/W2109808161","https://openalex.org/W2120615054","https://openalex.org/W2122751567","https://openalex.org/W2122922389","https://openalex.org/W2123024445","https://openalex.org/W2124386111","https://openalex.org/W2125263373","https://openalex.org/W2136480620","https://openalex.org/W2143017621","https://openalex.org/W2147625498","https://openalex.org/W2149557440","https://openalex.org/W2151375682","https://openalex.org/W2153579005","https://openalex.org/W2155541015","https://openalex.org/W2155893237","https://openalex.org/W2156940638","https://openalex.org/W2158899491","https://openalex.org/W2161381512","https://openalex.org/W2162915993","https://openalex.org/W2164587673","https://openalex.org/W2169177311","https://openalex.org/W2170298016","https://openalex.org/W2170738476","https://openalex.org/W2184188583","https://openalex.org/W2186094539","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2215576850","https://openalex.org/W2250539671","https://openalex.org/W2252215182","https://openalex.org/W2280985394","https://openalex.org/W2316082076","https://openalex.org/W2342543219","https://openalex.org/W2438305798","https://openalex.org/W2468075278","https://openalex.org/W2469228190","https://openalex.org/W2470673105","https://openalex.org/W2510453758","https://openalex.org/W2514167171","https://openalex.org/W2531409750","https://openalex.org/W2531675257","https://openalex.org/W2744024894","https://openalex.org/W2807978488","https://openalex.org/W2891355224","https://openalex.org/W2951359136","https://openalex.org/W2952230511","https://openalex.org/W2953320089","https://openalex.org/W2963083845","https://openalex.org/W2963921497","https://openalex.org/W3022399392","https://openalex.org/W3148472308","https://openalex.org/W4206593589","https://openalex.org/W4294170691","https://openalex.org/W4294375521","https://openalex.org/W4396952261","https://openalex.org/W6606244218","https://openalex.org/W6628998874","https://openalex.org/W6634343353","https://openalex.org/W6636510571","https://openalex.org/W6637373629","https://openalex.org/W6639204139","https://openalex.org/W6675354045","https://openalex.org/W6676141320","https://openalex.org/W6678470764","https://openalex.org/W6682691769","https://openalex.org/W6682778277","https://openalex.org/W6682974852","https://openalex.org/W6683738474","https://openalex.org/W6684872329","https://openalex.org/W6685160515","https://openalex.org/W6686207219","https://openalex.org/W6686583229","https://openalex.org/W6688476219","https://openalex.org/W6695456611","https://openalex.org/W6725355194","https://openalex.org/W6738379573","https://openalex.org/W6983682869"],"related_works":["https://openalex.org/W1663079876","https://openalex.org/W2069133146","https://openalex.org/W2017545316","https://openalex.org/W2100576949","https://openalex.org/W2159686533","https://openalex.org/W4242339654","https://openalex.org/W2349160795","https://openalex.org/W2100057527","https://openalex.org/W2493838176","https://openalex.org/W4297686120"],"abstract_inverted_index":{"The":[0,125,143],"good":[1],"generalization":[2],"performance":[3,204],"of":[4,13,60,73,89,114,122,189,200],"conventional":[5],"pattern":[6],"classifiers":[7],"often":[8],"relies":[9],"on":[10,172],"the":[11,58,70,77,82,87,90,119,136,164,167,184,198],"size":[12],"training":[14],"data":[15,43,63,75,180,190],"labeled":[16,51],"by":[17],"costly":[18],"human":[19,50],"labor.":[20],"These":[21],"days,":[22],"publicly":[23],"available":[24],"web":[25,39,42,61,83,123],"resources":[26],"grow":[27],"explosively,":[28],"and":[29,37,132,147,177,186,197],"this":[30,54],"allows":[31],"us":[32],"to":[33,64,135,162],"easily":[34],"obtain":[35],"abundant":[36],"cheap":[38],"data.":[40,52],"Yet,":[41],"are":[44,154,194],"usually":[45],"not":[46],"as":[47,49],"cooperative":[48],"In":[53],"paper,":[55],"we":[56,79],"explore":[57],"use":[59],"text":[62,84,121,127,137,145,187],"aid":[65,88],"image":[66,93],"classification.":[67],"Without":[68],"requiring":[69],"previous":[71],"collection":[72],"auxiliary":[74],"from":[76,118,140,191],"web,":[78],"directly":[80],"retrieve":[81],"information":[85],"with":[86],"powerful":[91],"reverse":[92],"search":[94],"engine.":[95],"We":[96],"develop":[97],"a":[98,157],"novel":[99],"textual":[100],"modeling":[101],"method":[102],"named":[103],"<italic":[104],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[105],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">semantic":[106],"matching":[107],"neural":[108,149],"network</i>":[109],"(SMNN)":[110],"that":[111,183],"is":[112],"capable":[113],"learning":[115],"semantic":[116],"features":[117,128,138,146,153],"associated":[120],"images.":[124],"SMNN":[126,144],"have":[129],"improved":[130],"reliability":[131],"applicability,":[133],"compared":[134],"obtained":[139],"other":[141],"methods.":[142],"convolutional":[148],"network":[150],"(CNN)":[151],"visual":[152,185],"merged":[155],"into":[156],"shared":[158],"representation,":[159],"which":[160],"learns":[161],"capture":[163],"correlations":[165],"between":[166],"two":[168],"modalities.":[169],"Experimental":[170],"results":[171],"benchmark":[173],"UIUC-Sports,":[174],"Scene-15,":[175],"Caltech-256,":[176],"Pascal":[178],"VOC-2012":[179],"sets":[181],"show":[182],"modalities":[188],"different":[192],"sources":[193],"remarkably":[195],"complementary":[196],"fusion":[199],"them":[201],"achieves":[202],"substantial":[203],"improvement.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}