{"id":"https://openalex.org/W3118655135","doi":"https://doi.org/10.1109/tcyb.2020.3041595","title":"Automatically Generating Natural Language Descriptions of Images by a Deep Hierarchical Framework","display_name":"Automatically Generating Natural Language Descriptions of Images by a Deep Hierarchical Framework","publication_year":2021,"publication_date":"2021-01-05","ids":{"openalex":"https://openalex.org/W3118655135","doi":"https://doi.org/10.1109/tcyb.2020.3041595","mag":"3118655135","pmid":"https://pubmed.ncbi.nlm.nih.gov/33400668"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2020.3041595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2020.3041595","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,"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"},"type":"article","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/A5101561234","display_name":"Lin Huo","orcid":"https://orcid.org/0000-0002-8704-0923"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lin Huo","raw_affiliation_strings":["China-ASEAN Research Institute, Guangxi University, Nanning, China"],"affiliations":[{"raw_affiliation_string":"China-ASEAN Research Institute, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101797092","display_name":"Lin Bai","orcid":"https://orcid.org/0000-0002-2324-9779"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Bai","raw_affiliation_strings":["School of Computer, Electronics and Information, Guangxi University, Nanning, China"],"affiliations":[{"raw_affiliation_string":"School of Computer, Electronics and Information, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074330876","display_name":"Shang\u2010Ming Zhou","orcid":"https://orcid.org/0000-0002-0719-9353"},"institutions":[{"id":"https://openalex.org/I181647926","display_name":"University of Strathclyde","ror":"https://ror.org/00n3w3b69","country_code":"GB","type":"education","lineage":["https://openalex.org/I181647926"]},{"id":"https://openalex.org/I897542642","display_name":"University of Plymouth","ror":"https://ror.org/008n7pv89","country_code":"GB","type":"education","lineage":["https://openalex.org/I897542642"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shang-Ming Zhou","raw_affiliation_strings":["Scottish Digital Health and Care Institute, University of Strathclyde, Glasgow, U.K","Department of Computer and Information Sciences, University of Strathclyde, Glasgow, U.K","Centre for Health Technology, University of Plymouth, Plymouth, U.K"],"affiliations":[{"raw_affiliation_string":"Scottish Digital Health and Care Institute, University of Strathclyde, Glasgow, U.K","institution_ids":["https://openalex.org/I181647926"]},{"raw_affiliation_string":"Department of Computer and Information Sciences, University of Strathclyde, Glasgow, U.K","institution_ids":["https://openalex.org/I181647926"]},{"raw_affiliation_string":"Centre for Health Technology, University of Plymouth, Plymouth, U.K","institution_ids":["https://openalex.org/I897542642"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101561234"],"corresponding_institution_ids":["https://openalex.org/I150807315"],"apc_list":null,"apc_paid":null,"fwci":1.1652,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.79945064,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"52","issue":"8","first_page":"7441","last_page":"7452"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9925000071525574,"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":0.9872999787330627,"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":0.8493515253067017},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7544831037521362},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7185775637626648},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6332534551620483},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5587575435638428},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5498247146606445},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5270305275917053},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4755149483680725},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.47278663516044617},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4695967435836792},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.45612823963165283},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.45018988847732544},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.44693195819854736},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.430936723947525},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41683119535446167},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40711817145347595},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.09758138656616211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8493515253067017},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7544831037521362},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7185775637626648},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6332534551620483},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5587575435638428},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5498247146606445},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5270305275917053},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4755149483680725},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.47278663516044617},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4695967435836792},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.45612823963165283},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.45018988847732544},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.44693195819854736},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.430936723947525},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41683119535446167},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40711817145347595},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.09758138656616211},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","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":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1109/tcyb.2020.3041595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2020.3041595","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,"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:33400668","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33400668","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,"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":null},{"id":"pmh:oai:strathprints.strath.ac.uk:79014","is_oa":false,"landing_page_url":"https://strathprints.strath.ac.uk/view/author/540498.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4306402226","display_name":"Strathprints: The University of Strathclyde institutional repository (University of Strathclyde)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I181647926","host_organization_name":"University of Strathclyde","host_organization_lineage":["https://openalex.org/I181647926"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:pearl.plymouth.ac.uk:10026.1/18229","is_oa":false,"landing_page_url":"http://hdl.handle.net/10026.1/18229","pdf_url":null,"source":{"id":"https://openalex.org/S4306402507","display_name":"PEARL (University of Plymouth)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I897542642","host_organization_name":"University of Plymouth","host_organization_lineage":["https://openalex.org/I897542642"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6499999761581421}],"awards":[{"id":"https://openalex.org/G135095751","display_name":null,"funder_award_id":"2018GXNSFAA138085","funder_id":"https://openalex.org/F4320322768","funder_display_name":"Natural Science Foundation of Guangxi Province"},{"id":"https://openalex.org/G5659565908","display_name":null,"funder_award_id":"61966003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G926038756","display_name":null,"funder_award_id":"16ZDA0092","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"},{"id":"https://openalex.org/F4320322768","display_name":"Natural Science Foundation of Guangxi Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W8316075","https://openalex.org/W62621907","https://openalex.org/W198309925","https://openalex.org/W604956704","https://openalex.org/W1596746947","https://openalex.org/W1668438657","https://openalex.org/W1895577753","https://openalex.org/W1969616664","https://openalex.org/W1972283961","https://openalex.org/W2011511325","https://openalex.org/W2046589395","https://openalex.org/W2085639290","https://openalex.org/W2100495367","https://openalex.org/W2110933980","https://openalex.org/W2277195237","https://openalex.org/W2296385829","https://openalex.org/W2339631096","https://openalex.org/W2411037331","https://openalex.org/W2463955103","https://openalex.org/W2549599535","https://openalex.org/W2564898401","https://openalex.org/W2585123518","https://openalex.org/W2594843439","https://openalex.org/W2605736949","https://openalex.org/W2607855566","https://openalex.org/W2737599761","https://openalex.org/W2795151422","https://openalex.org/W2801004733","https://openalex.org/W2803206166","https://openalex.org/W2803620531","https://openalex.org/W2888096830","https://openalex.org/W2890531016","https://openalex.org/W2914163459","https://openalex.org/W2927558373","https://openalex.org/W2945563815","https://openalex.org/W2955882737","https://openalex.org/W2962706528","https://openalex.org/W2962968835","https://openalex.org/W2963097937","https://openalex.org/W2963649796","https://openalex.org/W2963916161","https://openalex.org/W2964225075","https://openalex.org/W3009811369","https://openalex.org/W3015857268","https://openalex.org/W3035440494","https://openalex.org/W3099457648","https://openalex.org/W4226504164","https://openalex.org/W6600334730","https://openalex.org/W6638742206"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W3009270862"],"abstract_inverted_index":{"Automatically":[0],"generating":[1,18],"an":[2,8,19,51,63,78],"accurate":[3],"and":[4,38,43,76,183,187,191,200],"meaningful":[5],"description":[6,80,123,138],"of":[7,17,26,32,50,100,180,193],"image":[9,20,52,64,79,109,122,154,195],"is":[10,112,133],"very":[11],"challenging.":[12],"However,":[13],"the":[14,24,30,34,47,68,83,97,101,108,121,142,167,178,181],"recent":[15],"scheme":[16,132],"caption":[21,65],"by":[22,66],"maximizing":[23],"likelihood":[25],"target":[27],"sentences":[28],"lacks":[29],"capacity":[31],"recognizing":[33],"human-object":[35,102],"interaction":[36,91],"(HOI)":[37],"semantic":[39],"relationship":[40],"between":[41,185],"HOIs":[42,186],"scenes,":[44],"which":[45],"are":[46],"essential":[48],"parts":[49],"caption.":[53],"This":[54],"article":[55],"proposes":[56],"a":[57,72,87,115,126,137,147,198],"novel":[58,88],"two-phase":[59],"framework":[60,165],"to":[61,95,140],"generate":[62],"addressing":[67],"above":[69],"challenges:":[70],"1)":[71],"hybrid":[73,84],"deep":[74],"learning":[75],"2)":[77],"generation.":[81],"In":[82,105,120],"deep-learning":[85],"phase,":[86,125],"factored":[89],"three-way":[90],"machine":[92],"was":[93],"proposed":[94,164],"learn":[96],"relational":[98],"features":[99],"pairs":[103],"hierarchically.":[104],"this":[106],"way,":[107],"recognition":[110],"problem":[111],"transformed":[113],"into":[114,146],"latent":[116],"structured":[117],"labeling":[118],"task.":[119],"generation":[124,144,149],"lexicalized":[127],"probabilistic":[128],"context-free":[129],"tree":[130],"growing":[131],"innovatively":[134],"integrated":[135],"with":[136],"generator":[139],"transform":[141],"descriptions":[143],"task":[145],"syntactic-tree":[148],"process.":[150],"Extensively":[151],"comparing":[152],"state-of-the-art":[153],"captioning":[155,169],"methods":[156,170],"on":[157],"benchmark":[158],"datasets,":[159],"we":[160],"demonstrated":[161],"that":[162],"our":[163],"outperformed":[166],"existing":[168],"in":[171,197],"different":[172],"ways,":[173],"such":[174],"as":[175],"significantly":[176],"improving":[177],"performance":[179],"HOI":[182],"relationships":[184],"scenes":[188],"(RHIS)":[189],"predictions,":[190],"quality":[192],"generated":[194],"captions":[196],"semantically":[199],"structurally":[201],"coherent":[202],"manner.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}