{"id":"https://openalex.org/W4224933795","doi":"https://doi.org/10.1109/icassp43922.2022.9747541","title":"Mixed Knowledge Relation Transformer for Image Captioning","display_name":"Mixed Knowledge Relation Transformer for Image Captioning","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224933795","doi":"https://doi.org/10.1109/icassp43922.2022.9747541"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747541","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747541","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5100371624","display_name":"Tianyu Chen","orcid":"https://orcid.org/0000-0002-5101-7561"},"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":"Tianyu Chen","raw_affiliation_strings":["Guangxi Normal University,Guangxi Key Lab of Multi-source Information Mining and Security,Guilin,China,541004"],"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,Guangxi Key Lab of Multi-source Information Mining and Security,Guilin,China,541004","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100701695","display_name":"Zhixin Li","orcid":"https://orcid.org/0000-0002-5313-6134"},"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 Normal University,Guangxi Key Lab of Multi-source Information Mining and Security,Guilin,China,541004"],"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,Guangxi Key Lab of Multi-source Information Mining and Security,Guilin,China,541004","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076598143","display_name":"Jiahui Wei","orcid":"https://orcid.org/0009-0005-8060-2929"},"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":"Jiahui Wei","raw_affiliation_strings":["Guangxi Normal University,Guangxi Key Lab of Multi-source Information Mining and Security,Guilin,China,541004"],"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,Guangxi Key Lab of Multi-source Information Mining and Security,Guilin,China,541004","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060117326","display_name":"Tiantao Xian","orcid":"https://orcid.org/0000-0002-1092-9732"},"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":"Tiantao Xian","raw_affiliation_strings":["Guangxi Normal University,Guangxi Key Lab of Multi-source Information Mining and Security,Guilin,China,541004"],"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,Guangxi Key Lab of Multi-source Information Mining and Security,Guilin,China,541004","institution_ids":["https://openalex.org/I29739308"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100371624"],"corresponding_institution_ids":["https://openalex.org/I29739308"],"apc_list":null,"apc_paid":null,"fwci":0.1799,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.48082133,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4403","last_page":"4407"},"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":0.9952999949455261,"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":0.9943000078201294,"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":0.969237208366394},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7719669342041016},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7430768013000488},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6014634966850281},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5750933289527893},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5034543871879578},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.43416279554367065},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36317652463912964},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33423900604248047},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33102744817733765},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.30659013986587524},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09884154796600342}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.969237208366394},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7719669342041016},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7430768013000488},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6014634966850281},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5750933289527893},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5034543871879578},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.43416279554367065},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36317652463912964},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33423900604248047},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33102744817733765},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30659013986587524},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09884154796600342},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747541","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747541","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2056716515","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2745461083","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2983141445","https://openalex.org/W2986670728","https://openalex.org/W2990818246","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3080813890","https://openalex.org/W3096407995","https://openalex.org/W3162954998","https://openalex.org/W3174377922","https://openalex.org/W3175824375","https://openalex.org/W4288329833","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6763643401","https://openalex.org/W6775772702","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W2093143111","https://openalex.org/W4290852288"],"abstract_inverted_index":{"Internal":[0],"relationship":[1,27,60,79],"of":[2,11,21,41,85],"image":[3,12,48,73],"objects":[4,62],"has":[5],"contributed":[6],"significantly":[7],"to":[8],"the":[9,26,32,39,43,47,59,71,77,83,93],"development":[10],"captioning,":[13],"especially":[14],"when":[15],"combined":[16],"with":[17],"Transformer":[18],"architecture.":[19],"Most":[20],"these":[22],"methods":[23],"only":[24],"calculate":[25],"between":[28,34,61],"entities":[29,35],"and":[30,36,66,69,98,105],"ignore":[31],"information":[33,45,75],"background.":[37],"Besides,":[38],"way":[40],"exploring":[42],"relational":[44],"inside":[46],"can":[49],"also":[50],"be":[51],"extended.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56,88],"continually":[57],"explore":[58],"from":[63],"both":[64,103],"internal":[65,78],"external":[67],"perspectives,":[68],"embed":[70],"vital":[72],"global":[74],"into":[76],"module.":[80],"To":[81],"validate":[82],"effectiveness":[84],"our":[86],"model,":[87],"conduct":[89],"extensive":[90],"experiments":[91],"on":[92,102],"most":[94],"popular":[95],"MSCOCO":[96],"dataset,":[97],"achieve":[99],"state-of-the-art":[100],"performance":[101],"online":[104],"offline":[106],"test":[107],"sets.":[108]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}