{"id":"https://openalex.org/W4313033760","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892438","title":"Spatio-Temporal Graph-based Semantic Compositional Network for Video Captioning","display_name":"Spatio-Temporal Graph-based Semantic Compositional Network for Video Captioning","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4313033760","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892438"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892438","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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 International Joint Conference on Neural Networks (IJCNN)","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/A5100442626","display_name":"Shun Li","orcid":"https://orcid.org/0000-0001-9003-8966"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shun Li","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University,Suzhou,China,215006"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University,Suzhou,China,215006","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012016681","display_name":"Zefan Zhang","orcid":"https://orcid.org/0000-0001-5627-050X"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ze-Fan Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University,Suzhou,China,215006"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University,Suzhou,China,215006","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029104204","display_name":"Yi Ji","orcid":"https://orcid.org/0000-0001-6965-4158"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Ji","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University,Suzhou,China,215006"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University,Suzhou,China,215006","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106406655","display_name":"Ying Li","orcid":"https://orcid.org/0009-0004-1669-1878"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Li","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University,Suzhou,China,215006"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University,Suzhou,China,215006","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058448163","display_name":"Chunping Liu","orcid":"https://orcid.org/0009-0008-1495-5138"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun-Ping Liu","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University,Suzhou,China,215006"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University,Suzhou,China,215006","institution_ids":["https://openalex.org/I3923682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100442626"],"corresponding_institution_ids":["https://openalex.org/I3923682"],"apc_list":null,"apc_paid":null,"fwci":0.1799,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.53686012,"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":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/T10812","display_name":"Human Pose and Action Recognition","score":0.9984999895095825,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9941999912261963,"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":0.8448951840400696},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.802531361579895},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6325849890708923},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6083047986030579},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5584447979927063},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.5490133166313171},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5115278959274292},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4730129539966583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4651865065097809},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.4118272662162781},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35078659653663635},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.27080512046813965},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2673390507698059},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.18587055802345276},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09341549873352051}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8448951840400696},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.802531361579895},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6325849890708923},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6083047986030579},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5584447979927063},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.5490133166313171},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5115278959274292},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4730129539966583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4651865065097809},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.4118272662162781},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35078659653663635},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27080512046813965},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2673390507698059},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.18587055802345276},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09341549873352051},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892438","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6600000262260437,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4142933201","display_name":null,"funder_award_id":"19KJA230001","funder_id":"https://openalex.org/F4320327891","funder_display_name":"Major Basic Research Project of the Natural Science Foundation of the Jiangsu Higher Education Institutions"},{"id":"https://openalex.org/G4700821500","display_name":null,"funder_award_id":"61972059,61773272,61602332","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8119277942","display_name":null,"funder_award_id":"93K172016K08","funder_id":"https://openalex.org/F4320322300","funder_display_name":"Jilin University"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322300","display_name":"Jilin University","ror":"https://ror.org/00js3aw79"},{"id":"https://openalex.org/F4320327518","display_name":"Priority Academic Program Development of Jiangsu Higher Education Institutions","ror":null},{"id":"https://openalex.org/F4320327891","display_name":"Major Basic Research Project of the Natural Science Foundation of the Jiangsu Higher Education Institutions","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1601567445","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2154652894","https://openalex.org/W2164290393","https://openalex.org/W2250539671","https://openalex.org/W2425121537","https://openalex.org/W2558834163","https://openalex.org/W2745461083","https://openalex.org/W2905145027","https://openalex.org/W2948358897","https://openalex.org/W2962990649","https://openalex.org/W2963524571","https://openalex.org/W2964350391","https://openalex.org/W2972281329","https://openalex.org/W2981750519","https://openalex.org/W2984862483","https://openalex.org/W3000303105","https://openalex.org/W3035365026","https://openalex.org/W3035372819","https://openalex.org/W3035392611","https://openalex.org/W3120164061","https://openalex.org/W3160891393","https://openalex.org/W3192261211","https://openalex.org/W3205898187","https://openalex.org/W4297733535","https://openalex.org/W6620707391","https://openalex.org/W6631190155","https://openalex.org/W6682631176","https://openalex.org/W6684090549","https://openalex.org/W6745537798","https://openalex.org/W6772619176"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4287661223","https://openalex.org/W4214591816","https://openalex.org/W4312650216","https://openalex.org/W4221155265","https://openalex.org/W3109142545","https://openalex.org/W3042849301","https://openalex.org/W2590022237"],"abstract_inverted_index":{"Video":[0,71,197],"Captioning":[1,72],"aims":[2],"to":[3,103,126,167],"generate":[4,168],"natural":[5],"language":[6,182],"descriptions":[7],"for":[8,39,70],"given":[9],"videos":[10],"and":[11,62,87,139,200],"is":[12,37,101,124],"one":[13],"of":[14,32,58,76],"the":[15,30,51,56,64,82,88,95,105,120,128,133,141,149,174],"challenging":[16],"problems":[17],"in":[18,29],"computer":[19],"vision's":[20],"high-level":[21,164],"understanding":[22],"tasks.":[23],"Existing":[24],"methods":[25],"are":[26,160],"relatively":[27],"lacking":[28],"mining":[31],"object-level":[33,142,158],"spatio-temporal":[34,60],"relationships,":[35],"which":[36],"important":[38],"generating":[40],"captions":[41,169],"with":[42,119,163],"accurate":[43],"object":[44],"information.":[45],"In":[46,74],"this":[47],"paper,":[48],"we":[49,80],"improve":[50],"existing":[52,207],"SCN-LSTM":[53],"method":[54,190],"from":[55],"perspective":[57],"modeling":[59],"relationships":[61,78,107],"propose":[63,81],"Spatio-Temporal":[65],"Graph-based":[66],"Semantic":[67],"Compositional":[68],"Network":[69],"(STG-SCN).":[73],"terms":[75],"spatial-temporal":[77],"modeling,":[79],"Spatial":[83],"Relation":[84,90],"Graph":[85,91,96],"(SRG)":[86],"Temporal":[89],"(TRG)":[92],"based":[93],"on":[94,116,148,195],"Attention":[97],"Network,":[98],"respectively.":[99],"SRG":[100],"employed":[102],"establish":[104],"spatial":[106],"between":[108,131],"spatially":[109],"Neighboring":[110],"objects":[111,134],"within":[112],"each":[113],"keyframe":[114],"conditioned":[115],"their":[117],"correlation":[118],"current":[121],"keyframe.":[122],"TRG":[123],"used":[125],"model":[127],"temporal":[129],"relationship":[130],"all":[132],"at":[135],"different":[136],"time":[137],"steps":[138],"incorporates":[140],"information":[143,159],"into":[144],"frame-level":[145],"features.":[146],"Based":[147],"proposed":[150,189],"Semantics":[151],"Guided":[152],"Decoder,":[153],"visual":[154,176],"representations":[155],"enhanced":[156],"by":[157],"dynamically":[161],"fused":[162],"semantic":[165],"concepts":[166],"that":[170,187],"not":[171],"only":[172],"consider":[173],"global":[175],"content":[177],"but":[178],"also":[179],"have":[180],"stronger":[181],"expressiveness.":[183],"Extended":[184],"experiments":[185],"show":[186],"our":[188],"achieves":[191],"significant":[192],"performance":[193],"gains":[194],"Microsoft":[196,201],"Description":[198],"(MSVD)":[199],"Research":[202],"Video-to-Text":[203],"(MSR-VTT)":[204],"datasets,":[205],"outperforming":[206],"methods.":[208]},"counts_by_year":[{"year":2024,"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"}