{"id":"https://openalex.org/W3036848992","doi":"https://doi.org/10.1109/tcyb.2020.2997034","title":"Chinese Image Caption Generation via Visual Attention and Topic Modeling","display_name":"Chinese Image Caption Generation via Visual Attention and Topic Modeling","publication_year":2020,"publication_date":"2020-06-22","ids":{"openalex":"https://openalex.org/W3036848992","doi":"https://doi.org/10.1109/tcyb.2020.2997034","mag":"3036848992","pmid":"https://pubmed.ncbi.nlm.nih.gov/32568717"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2020.2997034","doi":"https://doi.org/10.1109/tcyb.2020.2997034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2020.2997034","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-a","fnege-4","jufo-3","ki-jl-2","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"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 Cybernetics","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","pubmed"],"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/A5021380974","display_name":"Maofu Liu","orcid":"https://orcid.org/0000-0002-3732-4354","observed_orcids":["https://orcid.org/0000-0002-3732-4354"]},"institutions":[{"id":"https://openalex.org/I43922553","display_name":"Wuhan University of Science and Technology","ror":"https://ror.org/00e4hrk88","country_code":"CN","type":"education","lineage":["https://openalex.org/I43922553"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maofu Liu","raw_affiliation_strings":["School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China","Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-3732-4354","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I43922553"]},{"raw_affiliation_string":"Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, Wuhan, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047496283","display_name":"Huijun Hu","orcid":"https://orcid.org/0000-0003-1086-4788","observed_orcids":["https://orcid.org/0000-0003-1086-4788"]},"institutions":[{"id":"https://openalex.org/I43922553","display_name":"Wuhan University of Science and Technology","ror":"https://ror.org/00e4hrk88","country_code":"CN","type":"education","lineage":["https://openalex.org/I43922553"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huijun Hu","raw_affiliation_strings":["School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China","Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-1086-4788","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I43922553"]},{"raw_affiliation_string":"Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, Wuhan, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100746147","display_name":"Lingjun Li","orcid":"https://orcid.org/0000-0001-9143-838X","observed_orcids":["https://orcid.org/0000-0001-9143-838X"]},"institutions":[{"id":"https://openalex.org/I43922553","display_name":"Wuhan University of Science and Technology","ror":"https://ror.org/00e4hrk88","country_code":"CN","type":"education","lineage":["https://openalex.org/I43922553"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingjun Li","raw_affiliation_strings":["School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China","Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I43922553"]},{"raw_affiliation_string":"Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, Wuhan, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103426906","display_name":"Yan Ping Yu","orcid":"https://orcid.org/0000-0002-5210-3971","observed_orcids":["https://orcid.org/0000-0002-5210-3971"]},"institutions":[{"id":"https://openalex.org/I43922553","display_name":"Wuhan University of Science and Technology","ror":"https://ror.org/00e4hrk88","country_code":"CN","type":"education","lineage":["https://openalex.org/I43922553"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Yu","raw_affiliation_strings":["School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China","Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I43922553"]},{"raw_affiliation_string":"Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, Wuhan, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075938343","display_name":"Weili Guan","orcid":"https://orcid.org/0000-0002-5658-5509","observed_orcids":["https://orcid.org/0000-0002-5658-5509"]},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Weili Guan","raw_affiliation_strings":["Faculty of Information Technology, Monash University (Clayton Campus), Clayton, VIC, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Monash University (Clayton Campus), Clayton, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":null,"fwci":2.8681,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":{"value":0.91892951,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"52","issue":"2","first_page":"1247","last_page":"1257"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":9.999999747378752e-05,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0,"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/image-captioning","display_name":"image captioning","score":0.7950000166893005},{"id":"https://openalex.org/keywords/visual-attention","display_name":"visual attention","score":0.9419999718666077},{"id":"https://openalex.org/keywords/topic-modeling","display_name":"topic modeling","score":0.996999979019165},{"id":"https://openalex.org/keywords/cross-modal-representation","display_name":"cross-modal representation","score":0.515999972820282}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8949856758117676},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8233075141906738},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6565763354301453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.623560905456543},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5850210189819336},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.4993715286254883},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4632747173309326},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45678457617759705},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4480040669441223},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3575631380081177},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D002681","descriptor_name":"China","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2020.2997034","doi":"https://doi.org/10.1109/tcyb.2020.2997034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2020.2997034","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-a","fnege-4","jufo-3","ki-jl-2","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"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 Cybernetics","raw_type":"journal-article"},{"id":"pmid:32568717","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32568717","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on cybernetics","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G7597005287","display_name":null,"funder_award_id":"11&ZD189","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1706899115","https://openalex.org/W1895577753","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W2056935845","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2131179926","https://openalex.org/W2133564696","https://openalex.org/W2135029798","https://openalex.org/W2154652894","https://openalex.org/W2156830856","https://openalex.org/W2220981600","https://openalex.org/W2418300416","https://openalex.org/W2481240925","https://openalex.org/W2519936666","https://openalex.org/W2521114121","https://openalex.org/W2550553598","https://openalex.org/W2552161745","https://openalex.org/W2560645892","https://openalex.org/W2560920409","https://openalex.org/W2611009517","https://openalex.org/W2611996841","https://openalex.org/W2735553491","https://openalex.org/W2739107216","https://openalex.org/W2745461083","https://openalex.org/W2752461516","https://openalex.org/W2768287968","https://openalex.org/W2779054585","https://openalex.org/W2780100774","https://openalex.org/W2791779647","https://openalex.org/W2797029597","https://openalex.org/W2799460201","https://openalex.org/W2803140164","https://openalex.org/W2803620531","https://openalex.org/W2808442315","https://openalex.org/W2808663243","https://openalex.org/W2884326683","https://openalex.org/W2886405166","https://openalex.org/W2887712318","https://openalex.org/W2888321701","https://openalex.org/W2888516611","https://openalex.org/W2911584214","https://openalex.org/W2915878183","https://openalex.org/W2945563815","https://openalex.org/W2945755204","https://openalex.org/W2962964140","https://openalex.org/W2963175879","https://openalex.org/W2996421194","https://openalex.org/W3002181557","https://openalex.org/W4246193833","https://openalex.org/W4308088215"],"related_works":["https://openalex.org/W2891678728","https://openalex.org/W3200264219","https://openalex.org/W4399509174","https://openalex.org/W2996421194","https://openalex.org/W4404609296","https://openalex.org/W3000712030","https://openalex.org/W4385977530","https://openalex.org/W4367050119","https://openalex.org/W3217388757","https://openalex.org/W4205212606"],"abstract_inverted_index":{"Automatic":[0],"image":[1,10,48,57,90,109,133,214,219,246,260,289],"captioning":[2,110,290],"is":[3,127,210],"to":[4,13,129,137,192,212,234],"conduct":[5],"the":[6,31,37,42,46,68,75,78,83,85,89,94,103,116,139,143,148,159,164,167,171,180,199,204,224,228,236,257,287],"cross-modal":[7],"conversion":[8],"from":[9],"visual":[11,152,160,194,215,220,229],"content":[12,80],"natural":[14,22,282],"language":[15,23],"text.":[16],"Involving":[17],"computer":[18],"vision":[19],"(CV)":[20],"and":[21,77,93,106,120,124,154,166,173,187,195,227,274,284],"processing":[24,213],"(NLP),":[25],"it":[26,126,285],"has":[27,52],"become":[28],"one":[29],"of":[30,88,96,102,175,198],"most":[32,101],"sophisticated":[33],"research":[34],"issues":[35],"in":[36,56,112,122,157,179,277,279],"artificial-intelligence":[38],"area.":[39],"Based":[40],"on":[41],"deep":[43],"neural":[44,47,184],"network,":[45],"caption":[49,134],"(NIC)":[50],"model":[51,76,150,169,189,268],"achieved":[53],"remarkable":[54],"performance":[55],"captioning,":[58],"yet":[59],"there":[60],"still":[61],"remain":[62],"some":[63],"essential":[64],"challenges,":[65],"such":[66],"as":[67],"deviation":[69,165],"between":[70,118],"descriptive":[71,275],"sentences":[72],"generated":[73,97,176],"by":[74,82],"intrinsic":[79],"expressed":[81],"image,":[84],"low":[86],"accuracy":[87,172],"scene":[91],"description,":[92],"monotony":[95],"sentences.":[98,177],"In":[99,203],"addition,":[100],"current":[104],"datasets":[105],"methods":[107,136],"for":[108,217,243],"are":[111,190,232],"English.":[113],"However,":[114],"considering":[115],"distinction":[117],"Chinese":[119,132,245,258,278],"English":[121],"syntax":[123],"semantics,":[125],"necessary":[128],"develop":[130],"specialized":[131],"generation":[135],"accommodate":[138],"difference.":[140],"To":[141,248],"solve":[142],"aforementioned":[144],"problems,":[145],"we":[146,252],"design":[147],"NICVATP2L":[149],"via":[151],"attention":[153,161,208],"topic":[155,168,188,196,225],"modeling,":[156],"which":[158],"mechanism":[162,209],"reduces":[163],"improves":[170],"diversity":[174],"Specifically,":[178],"encoding":[181],"phase,":[182,206],"convolutional":[183],"network":[185,242],"(CNN)":[186],"used":[191],"extract":[193],"features":[197,216,226,231],"input":[200],"images,":[201],"respectively.":[202],"decoding":[205],"an":[207],"applied":[211],"obtaining":[218],"region":[221,230],"features.":[222],"Finally,":[223],"combined":[233],"guide":[235],"two-layer":[237],"long":[238],"short-term":[239],"memory":[240],"(LSTM)":[241],"generating":[244],"captions.":[247],"justify":[249],"our":[250,267],"model,":[251],"have":[253],"conducted":[254],"experiments":[255],"over":[256],"AIC-ICC":[259],"dataset.":[261],"The":[262],"experimental":[263],"results":[264],"show":[265],"that":[266],"can":[269],"automatically":[270],"generate":[271],"more":[272,281],"informative":[273],"captions":[276],"a":[280],"way,":[283],"outperforms":[286],"existing":[288],"NIC":[291],"model.":[292]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":5}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2020-06-25T00:00:00"}