{"id":"https://openalex.org/W3162954998","doi":"https://doi.org/10.1145/3439734","title":"Integrating Scene Semantic Knowledge into Image Captioning","display_name":"Integrating Scene Semantic Knowledge into Image Captioning","publication_year":2021,"publication_date":"2021-05-11","ids":{"openalex":"https://openalex.org/W3162954998","doi":"https://doi.org/10.1145/3439734","mag":"3162954998"},"language":"en","primary_location":{"id":"doi:10.1145/3439734","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3439734","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5009693444","display_name":"Haiyang Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haiyang Wei","raw_affiliation_strings":["Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, Guilin, Guangxi, China"],"affiliations":[{"raw_affiliation_string":"Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, Guilin, Guangxi, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100701695","display_name":"Zhixin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixin Li","raw_affiliation_strings":["Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, Guilin, Guangxi, China"],"affiliations":[{"raw_affiliation_string":"Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, Guilin, Guangxi, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028931239","display_name":"Feicheng Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feicheng Huang","raw_affiliation_strings":["Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, Guilin, Guangxi, China"],"affiliations":[{"raw_affiliation_string":"Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, Guilin, Guangxi, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016469515","display_name":"Canlong Zhang","orcid":"https://orcid.org/0000-0003-4375-1405"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Canlong Zhang","raw_affiliation_strings":["Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, Guilin, Guangxi, China"],"affiliations":[{"raw_affiliation_string":"Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, Guilin, Guangxi, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053794277","display_name":"Huifang Ma","orcid":"https://orcid.org/0000-0002-5104-8982"},"institutions":[{"id":"https://openalex.org/I68986083","display_name":"Northwest Normal University","ror":"https://ror.org/00gx3j908","country_code":"CN","type":"education","lineage":["https://openalex.org/I68986083"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huifang Ma","raw_affiliation_strings":["College of Computer Science and Engineering, Northwest Normal University, Lanzhou, Gansu, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Engineering, Northwest Normal University, Lanzhou, Gansu, China","institution_ids":["https://openalex.org/I68986083"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075925664","display_name":"Zhongzhi Shi","orcid":"https://orcid.org/0000-0002-3280-1676"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongzhi Shi","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing, Institute of ComputingTechnology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing, Institute of ComputingTechnology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5009693444"],"corresponding_institution_ids":["https://openalex.org/I29739308"],"apc_list":null,"apc_paid":null,"fwci":4.0708,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.95210939,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"17","issue":"2","first_page":"1","last_page":"22"},"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":0.9987999796867371,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9951000213623047,"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/closed-captioning","display_name":"Closed captioning","score":0.9549859762191772},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8658839464187622},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.7190277576446533},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6124656200408936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5776719450950623},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5637539625167847},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.48177310824394226},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4268142879009247},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40350717306137085},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3762736916542053}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9549859762191772},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8658839464187622},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.7190277576446533},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6124656200408936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5776719450950623},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5637539625167847},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48177310824394226},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4268142879009247},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40350717306137085},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3762736916542053},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3439734","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3439734","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2302086703","https://openalex.org/W2407521645","https://openalex.org/W2506483933","https://openalex.org/W2550553598","https://openalex.org/W2552161745","https://openalex.org/W2560920409","https://openalex.org/W2564898401","https://openalex.org/W2575842049","https://openalex.org/W2600463316","https://openalex.org/W2740118378","https://openalex.org/W2745461083","https://openalex.org/W2795151422","https://openalex.org/W2890531016","https://openalex.org/W2949376505","https://openalex.org/W2962968835","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963170456","https://openalex.org/W2990069284","https://openalex.org/W3103022576","https://openalex.org/W4231510805"],"related_works":["https://openalex.org/W4320016117","https://openalex.org/W4307856881","https://openalex.org/W2901467237","https://openalex.org/W2547835662","https://openalex.org/W2971688299","https://openalex.org/W3020826863","https://openalex.org/W3111379637","https://openalex.org/W3197904250","https://openalex.org/W4283315784","https://openalex.org/W3194749251"],"abstract_inverted_index":{"Most":[0],"existing":[1],"image":[2,12,101,108],"captioning":[3],"methods":[4],"use":[5],"only":[6],"the":[7,11,15,20,28,35,39,57,62,66,70,75,79,83,95,100,107,114,119,124,132,145],"visual":[8,30,49,89,125],"information":[9,68,126,130],"of":[10,17,22,61,69,78,99],"to":[13,85,106,113,122,136,143,147],"guide":[14],"generation":[16],"captions,":[18],"lack":[19],"guidance":[21],"effective":[23],"scene":[24,96,128],"semantic":[25,97,129],"information,":[26],"and":[27,127,140,151,163,178],"current":[29],"attention":[31,50,63,80,120,135],"mechanism":[32,64,81,121],"cannot":[33],"adjust":[34],"focus":[36,58,76],"intensity":[37,59,77],"on":[38,159],"image.":[40],"In":[41,91],"this":[42],"article,":[43],"we":[44,55,93,155],"first":[45],"propose":[46],"an":[47],"improved":[48],"model.":[51,116],"At":[52],"each":[53,138],"timestep,":[54],"calculated":[56],"coefficient":[60,84],"through":[65,82,102],"context":[67],"model,":[71],"then":[72,110],"automatically":[73],"adjusted":[74],"extract":[86],"more":[87,149,175],"accurate":[88,150,176],"information.":[90],"addition,":[92],"represented":[94],"knowledge":[98],"topic":[103],"words":[104],"related":[105],"scene,":[109],"added":[111],"them":[112,142],"language":[115],"We":[117],"used":[118],"determine":[123],"that":[131,171],"model":[133,146,158],"pays":[134],"at":[137],"timestep":[139],"combined":[141],"enable":[144],"generate":[148],"scene-specific":[152],"captions.":[153],"Finally,":[154],"evaluated":[156],"our":[157,172],"Microsoft":[160],"COCO":[161],"(MSCOCO)":[162],"Flickr30k":[164],"standard":[165],"datasets.":[166],"The":[167],"experimental":[168],"results":[169],"show":[170],"approach":[173],"generates":[174],"captions":[177],"outperforms":[179],"many":[180],"recent":[181],"advanced":[182],"models":[183],"in":[184],"various":[185],"evaluation":[186],"metrics.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-31T07:56:22.981413","created_date":"2025-10-10T00:00:00"}