{"id":"https://openalex.org/W3217195652","doi":"https://doi.org/10.3390/s21237982","title":"Attention-Guided Image Captioning through Word Information","display_name":"Attention-Guided Image Captioning through Word Information","publication_year":2021,"publication_date":"2021-11-30","ids":{"openalex":"https://openalex.org/W3217195652","doi":"https://doi.org/10.3390/s21237982","mag":"3217195652","pmid":"https://pubmed.ncbi.nlm.nih.gov/34883986"},"language":"en","primary_location":{"id":"doi:10.3390/s21237982","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s21237982","pdf_url":"https://www.mdpi.com/1424-8220/21/23/7982/pdf?version=1638250410","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/21/23/7982/pdf?version=1638250410","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082223646","display_name":"Ziwei Tang","orcid":"https://orcid.org/0000-0001-6780-8432"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziwei Tang","raw_affiliation_strings":["School of Printing and Packaging, Wuhan University, Wuhan 430072, China"],"raw_orcid":"https://orcid.org/0000-0001-6780-8432","affiliations":[{"raw_affiliation_string":"School of Printing and Packaging, Wuhan University, Wuhan 430072, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005954246","display_name":"Yaohua Yi","orcid":"https://orcid.org/0000-0003-2456-6845"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yaohua Yi","raw_affiliation_strings":["School of Printing and Packaging, Wuhan University, Wuhan 430072, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Printing and Packaging, Wuhan University, Wuhan 430072, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077419123","display_name":"Hao Sheng","orcid":"https://orcid.org/0000-0003-3116-1897"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Sheng","raw_affiliation_strings":["School of Printing and Packaging, Wuhan University, Wuhan 430072, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Printing and Packaging, Wuhan University, Wuhan 430072, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005954246"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":0.3881,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.62424213,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"21","issue":"23","first_page":"7982","last_page":"7982"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9947999715805054,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9735999703407288,"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/closed-captioning","display_name":"Closed captioning","score":0.9808927178382874},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.8465760946273804},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7339671850204468},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.636808454990387},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5643990635871887},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5546843409538269},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.551741898059845},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5506219863891602},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.532714307308197},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41012075543403625},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12384620308876038},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11868089437484741}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9808927178382874},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.8465760946273804},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7339671850204468},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.636808454990387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5643990635871887},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5546843409538269},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.551741898059845},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5506219863891602},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.532714307308197},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41012075543403625},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12384620308876038},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11868089437484741},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D001288","descriptor_name":"Attention","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001288","descriptor_name":"Attention","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001288","descriptor_name":"Attention","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.3390/s21237982","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s21237982","pdf_url":"https://www.mdpi.com/1424-8220/21/23/7982/pdf?version=1638250410","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:34883986","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34883986","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":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:doaj.org/article:f02ad3ab351e4c98ac9609686df8a2b4","is_oa":true,"landing_page_url":"https://doaj.org/article/f02ad3ab351e4c98ac9609686df8a2b4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 21, Iss 23, p 7982 (2021)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/21/23/7982/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s21237982","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors; Volume 21; Issue 23; Pages: 7982","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:8659425","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8659425","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s21237982","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s21237982","pdf_url":"https://www.mdpi.com/1424-8220/21/23/7982/pdf?version=1638250410","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2269336750","display_name":null,"funder_award_id":"No. 2021YFB2206200","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3217195652.pdf"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W8316075","https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W2019370496","https://openalex.org/W2066134726","https://openalex.org/W2101105183","https://openalex.org/W2108598243","https://openalex.org/W2117539524","https://openalex.org/W2157331557","https://openalex.org/W2277195237","https://openalex.org/W2506483933","https://openalex.org/W2550553598","https://openalex.org/W2552161745","https://openalex.org/W2558834163","https://openalex.org/W2567070169","https://openalex.org/W2575842049","https://openalex.org/W2625940279","https://openalex.org/W2745461083","https://openalex.org/W2787802257","https://openalex.org/W2885013662","https://openalex.org/W2890531016","https://openalex.org/W2962765188","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963971014","https://openalex.org/W2964018924","https://openalex.org/W2987327987","https://openalex.org/W3006277995","https://openalex.org/W3015437081","https://openalex.org/W3038571929","https://openalex.org/W3039115681","https://openalex.org/W3070078896","https://openalex.org/W3127216151","https://openalex.org/W3134428106","https://openalex.org/W3136792391","https://openalex.org/W3176587734","https://openalex.org/W6639118148","https://openalex.org/W6679436768","https://openalex.org/W6729046916"],"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/W3217195652"],"abstract_inverted_index":{"Image":[0,141],"captioning":[1,11],"generates":[2],"written":[3],"descriptions":[4],"of":[5,26,129,149],"an":[6],"image.":[7],"In":[8,34],"recent":[9],"image":[10,46],"research,":[12],"attention":[13,42,72,99,104],"regions":[14],"seldom":[15],"cover":[16],"all":[17],"objects,":[18],"and":[19,28,57,63,74,101,137,146,154],"generated":[20],"captions":[21],"may":[22,29],"lack":[23],"the":[24,54,71,76,88,107,111],"details":[25],"objects":[27],"remain":[30],"far":[31],"from":[32,90],"reality.":[33],"this":[35],"paper,":[36],"we":[37,84],"propose":[38],"a":[39,130,138,150,155,160],"word":[40,51,56,68,97,103],"guided":[41,98],"(WGA)":[43],"method":[44],"for":[45],"captioning.":[47],"First,":[48],"WGA":[49,66,86,118],"extracts":[50],"information":[52,69],"using":[53],"embedded":[55],"memory":[58],"cell":[59],"by":[60],"applying":[61],"transformation":[62],"multiplication.":[64,82],"Then,":[65],"applies":[67],"to":[70,94],"results":[73,128,148],"obtains":[75],"attended":[77],"feature":[78],"vectors":[79],"via":[80],"elementwise":[81],"Finally,":[83],"apply":[85],"with":[87,126],"words":[89],"different":[91],"time":[92],"steps":[93],"obtain":[95],"previous":[96],"(PW)":[100],"current":[102],"(CW)":[105],"in":[106],"decoder.":[108],"Experiments":[109],"on":[110,159],"MSCOCO":[112],"dataset":[113],"show":[114],"that":[115],"our":[116],"proposed":[117],"can":[119],"achieve":[120],"competitive":[121],"performance":[122],"against":[123],"state-of-the-art":[124],"methods,":[125],"PW":[127],"39.1":[131,151],"Bilingual":[132],"Evaluation":[133,143],"Understudy":[134],"score":[135,144,153,158],"(BLEU-4)":[136],"127.6":[139],"Consensus-Based":[140],"Description":[142],"(CIDEr-D);":[145],"CW":[147],"BLEU-4":[152],"127.2":[156],"CIDER-D":[157],"Karpathy":[161],"test":[162],"split.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-24T13:16:06.693445","created_date":"2025-10-10T00:00:00"}
