{"id":"https://openalex.org/W3170072367","doi":"https://doi.org/10.1109/icme51207.2021.9428310","title":"Exploring Explicit And Implicit Visual Relationships For Image Captioning","display_name":"Exploring Explicit And Implicit Visual Relationships For Image Captioning","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3170072367","doi":"https://doi.org/10.1109/icme51207.2021.9428310","mag":"3170072367"},"language":"en","primary_location":{"id":"doi:10.1109/icme51207.2021.9428310","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5060506632","display_name":"Zeliang Song","orcid":null},"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/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeliang Song","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103179009","display_name":"Xiaofei Zhou","orcid":"https://orcid.org/0000-0001-9354-1209"},"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/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofei Zhou","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9934999942779541,"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":0.9900000095367432,"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":0.9716061353683472},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8396703004837036},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6327385902404785},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5928629636764526},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5527938604354858},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.542698323726654},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5263394117355347},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4538570046424866},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.43795472383499146},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4302710294723511},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.29156774282455444}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9716061353683472},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8396703004837036},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6327385902404785},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5928629636764526},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5527938604354858},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.542698323726654},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5263394117355347},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4538570046424866},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.43795472383499146},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4302710294723511},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29156774282455444},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme51207.2021.9428310","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2159564241","https://openalex.org/W2220981600","https://openalex.org/W2277195237","https://openalex.org/W2506483933","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2751092903","https://openalex.org/W2765440071","https://openalex.org/W2890531016","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963536419","https://openalex.org/W2986670728","https://openalex.org/W3034655362","https://openalex.org/W3035160838","https://openalex.org/W6630875275","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6725318829","https://openalex.org/W6754778999","https://openalex.org/W6898505805"],"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":{"Image":[0],"captioning":[1,25],"is":[2],"one":[3],"of":[4,33,51,129],"the":[5,31,48,52,107,125],"most":[6],"challenging":[7],"tasks":[8],"in":[9,36],"AI,":[10],"which":[11],"aims":[12],"to":[13,72,95],"automatically":[14],"generate":[15],"textual":[16],"sentences":[17],"for":[18,23,76],"an":[19,37],"image.":[20],"Recent":[21],"methods":[22],"image":[24,38,77],"follow":[26],"encoder-decoder":[27],"framework":[28],"that":[29],"transforms":[30],"sequence":[32],"salient":[34],"regions":[35],"into":[39],"natural":[40],"language":[41],"descriptions.":[42],"However,":[43],"these":[44],"models":[45],"usually":[46],"lack":[47],"comprehensive":[49],"undemanding":[50],"contextual":[53],"interactions":[54,105],"reflected":[55],"on":[56,137],"various":[57],"visual":[58,70],"relationships":[59,71],"between":[60],"objects.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65,80,102,133],"explore":[66],"explicit":[67],"and":[68,87,127,141],"implicit":[69],"enrich":[73],"region-level":[74],"representations":[75,114],"captioning.":[78],"Explicitly,":[79],"build":[81],"semantic":[82],"graph":[83,90],"over":[84],"object":[85],"pairs":[86],"exploit":[88],"gated":[89],"convolutional":[91],"networks":[92],"(Gated":[93],"GCN)":[94],"selectively":[96],"aggregate":[97],"local":[98],"neighbors\u2019":[99],"information.":[100],"Implicitly,":[101],"draw":[103],"global":[104],"among":[106],"detected":[108],"objects":[109],"through":[110],"region-based":[111],"bidirectional":[112],"encoder":[113],"from":[115],"transformers":[116],"(Region":[117],"BERT)":[118],"without":[119],"extra":[120],"relational":[121],"annotations.":[122],"To":[123],"evaluate":[124],"effectiveness":[126],"superiority":[128],"our":[130],"proposed":[131],"method,":[132],"conduct":[134],"extensive":[135],"experiments":[136],"Microsoft":[138],"COCO":[139],"bench-mark":[140],"achieve":[142],"remarkable":[143],"improvements":[144],"compared":[145],"with":[146],"strong":[147],"baselines.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-27T08:26:11.824852","created_date":"2025-10-10T00:00:00"}