{"id":"https://openalex.org/W4293518920","doi":"https://doi.org/10.1109/icme52920.2022.9859926","title":"Relational Graph Reasoning Transformer for Image Captioning","display_name":"Relational Graph Reasoning Transformer for Image Captioning","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4293518920","doi":"https://doi.org/10.1109/icme52920.2022.9859926"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859926","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 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/A5102999463","display_name":"Xinyu Xiao","orcid":"https://orcid.org/0000-0003-4895-632X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Xiao","raw_affiliation_strings":["Tencent,Shanghai,China","Tencent, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Shanghai,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067395825","display_name":"Zixun Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixun Sun","raw_affiliation_strings":["Tencent,Shanghai,China","Tencent, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Shanghai,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078082551","display_name":"Tingtian Li","orcid":"https://orcid.org/0000-0001-9124-2600"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingtian Li","raw_affiliation_strings":["Tencent,Shanghai,China","Tencent, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Shanghai,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110643048","display_name":"Yipeng Yu","orcid":"https://orcid.org/0000-0002-4212-0153"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yipeng Yu","raw_affiliation_strings":["Tencent,Shanghai,China","Tencent, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Shanghai,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":0.2774,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60311517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9980999827384949,"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":0.9958000183105469,"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":0.7089118957519531},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5755208730697632},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.5199800133705139},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49794816970825195},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4887838065624237},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.48661717772483826},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4799071252346039},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.4304080307483673},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.20115947723388672},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15087133646011353}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7089118957519531},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5755208730697632},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.5199800133705139},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49794816970825195},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4887838065624237},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.48661717772483826},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4799071252346039},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.4304080307483673},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.20115947723388672},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15087133646011353},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme52920.2022.9859926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859926","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2194775991","https://openalex.org/W2404394533","https://openalex.org/W2745461083","https://openalex.org/W2806331055","https://openalex.org/W2809418595","https://openalex.org/W2896457183","https://openalex.org/W2952688802","https://openalex.org/W2964018924","https://openalex.org/W2983141445","https://openalex.org/W2986670728","https://openalex.org/W2990818246","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3175824375","https://openalex.org/W3177244742","https://openalex.org/W4288329833","https://openalex.org/W4385245566","https://openalex.org/W6639102338","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6739901393","https://openalex.org/W6751936687","https://openalex.org/W6754778999","https://openalex.org/W6755207826","https://openalex.org/W6763643401","https://openalex.org/W6787094702","https://openalex.org/W6787735275"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W4323777661","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4287661223","https://openalex.org/W2077467526","https://openalex.org/W4387129494"],"abstract_inverted_index":{"The":[0],"current":[1],"published":[2],"methods":[3],"of":[4,12,22,38,63,134],"image":[5,15],"captioning":[6],"are":[7,44],"directly":[8],"inputting":[9],"the":[10,27,30,36,61,79,83,88,118,125,132],"features":[11],"objects":[13,31,43,68,93],"in":[14,75],"into":[16,124],"model,":[17],"and":[18,32,40,65,87,107],"introduced":[19],"a":[20,53,97,113],"variety":[21],"attention":[23],"mechanisms":[24],"to":[25,69],"capture":[26],"associations":[28],"between":[29,42,67,91],"specific":[33],"words.":[34],"But":[35],"relationships":[37,62,86],"vision":[39,64],"semantic":[41,66,89,108],"not":[45],"sufficiently":[46],"concerned.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51],"propose":[52],"relational":[54,73],"graph":[55,74,98,120],"reasoning":[56,137],"Transformer":[57,127,138],"which":[58,101],"explicitly":[59],"incorporates":[60],"construct":[70],"an":[71],"object":[72,81,103],"Transformer.":[76],"Specifically,":[77],"besides":[78],"detected":[80],"features,":[82,104],"global":[84],"spatial":[85,106],"context":[90],"different":[92],"is":[94,110,122],"attended.":[95],"Meanwhile,":[96],"structures":[99],"feature":[100,121],"correlates":[102],"their":[105],"information":[109],"reasoned":[111],"by":[112],"learned":[114],"grafting":[115],"mechanism.":[116],"Finally,":[117],"contextual":[119],"integrated":[123],"proposed":[126],"decoder.":[128],"Experimental":[129],"results":[130],"demonstrate":[131],"significance":[133],"our":[135],"relationship":[136],"model.":[139]},"counts_by_year":[{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}