{"id":"https://openalex.org/W4226094317","doi":"https://doi.org/10.1109/tmm.2022.3169065","title":"Scene Graph Refinement Network for Visual Question Answering","display_name":"Scene Graph Refinement Network for Visual Question Answering","publication_year":2022,"publication_date":"2022-04-22","ids":{"openalex":"https://openalex.org/W4226094317","doi":"https://doi.org/10.1109/tmm.2022.3169065"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3169065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3169065","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","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/A5071784615","display_name":"Tianwen Qian","orcid":"https://orcid.org/0000-0002-3881-4857"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianwen Qian","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373492","display_name":"Jingjing Chen","orcid":"https://orcid.org/0000-0003-3148-264X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Chen","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101499520","display_name":"Shaoxiang Chen","orcid":"https://orcid.org/0000-0002-7627-7124"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoxiang Chen","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059368105","display_name":"Bo Wu","orcid":"https://orcid.org/0000-0001-6658-6452"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Wu","raw_affiliation_strings":["MIT-IBM Watson AI Lab, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"MIT-IBM Watson AI Lab, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047962986","display_name":"Yu\u2013Gang Jiang","orcid":"https://orcid.org/0000-0002-1907-8567"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5071784615"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":5.9093,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.97312557,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"25","issue":null,"first_page":"3950","last_page":"3961"},"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/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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9896000027656555,"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/question-answering","display_name":"Question answering","score":0.7311221361160278},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6677945256233215},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5299196243286133},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4701279103755951},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.45401185750961304},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4444258511066437},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4282693564891815},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4261151850223541},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.27738794684410095}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7311221361160278},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6677945256233215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5299196243286133},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4701279103755951},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.45401185750961304},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4444258511066437},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4282693564891815},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4261151850223541},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27738794684410095},{"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/tmm.2022.3169065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3169065","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3970387658","display_name":null,"funder_award_id":"62072116","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321659","display_name":"Shanghai Education Development Foundation","ror":"https://ror.org/02kq92y46"},{"id":"https://openalex.org/F4320321881","display_name":"Shanghai Municipal Education Commission","ror":"https://ror.org/05tewj457"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1933349210","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2479423890","https://openalex.org/W2525778437","https://openalex.org/W2526198870","https://openalex.org/W2561715562","https://openalex.org/W2579549467","https://openalex.org/W2732016772","https://openalex.org/W2745461083","https://openalex.org/W2754191212","https://openalex.org/W2795378892","https://openalex.org/W2883104598","https://openalex.org/W2890531016","https://openalex.org/W2896902935","https://openalex.org/W2897152025","https://openalex.org/W2906314281","https://openalex.org/W2913618459","https://openalex.org/W2916723116","https://openalex.org/W2962716332","https://openalex.org/W2962779575","https://openalex.org/W2963101956","https://openalex.org/W2963176022","https://openalex.org/W2963224792","https://openalex.org/W2963383024","https://openalex.org/W2963518342","https://openalex.org/W2963536419","https://openalex.org/W2963717374","https://openalex.org/W2963800628","https://openalex.org/W2963902384","https://openalex.org/W2963954913","https://openalex.org/W2964072591","https://openalex.org/W2966683369","https://openalex.org/W2968124245","https://openalex.org/W2969679616","https://openalex.org/W2969876226","https://openalex.org/W2970231061","https://openalex.org/W2981851019","https://openalex.org/W2998356391","https://openalex.org/W2998631105","https://openalex.org/W3004349648","https://openalex.org/W3005881764","https://openalex.org/W3010277541","https://openalex.org/W3033697199","https://openalex.org/W3035017890","https://openalex.org/W3035356601","https://openalex.org/W3035520037","https://openalex.org/W3035733952","https://openalex.org/W3091588028","https://openalex.org/W3092903587","https://openalex.org/W3098341861","https://openalex.org/W3118500473","https://openalex.org/W3119150707","https://openalex.org/W3173223111","https://openalex.org/W3173909648","https://openalex.org/W3176896951","https://openalex.org/W3182763642","https://openalex.org/W3196122027","https://openalex.org/W3203581965","https://openalex.org/W3207576380","https://openalex.org/W3216857888","https://openalex.org/W4225868495","https://openalex.org/W4297733535","https://openalex.org/W4297749157","https://openalex.org/W6682889407","https://openalex.org/W6719057275","https://openalex.org/W6727690538","https://openalex.org/W6739901393","https://openalex.org/W6748270630","https://openalex.org/W6752083267","https://openalex.org/W6754944153","https://openalex.org/W6755207826","https://openalex.org/W6765591853","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6767279747","https://openalex.org/W6788354309","https://openalex.org/W6803023527"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W4297783004","https://openalex.org/W2914694625","https://openalex.org/W4392007279","https://openalex.org/W4387129494"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"aims":[3],"to":[4,49,78,116,161],"answer":[5],"the":[6,13,29,43,51,58,69,80,85,118,128,136,150,154,159,163,175,179],"free-form":[7],"natural":[8],"language":[9,35],"question":[10,72,129,168],"based":[11],"on":[12,174],"visual":[14],"clues":[15,132],"in":[16,54,158],"a":[17,22,90,112],"given":[18],"image.":[19],"It":[20],"is":[21],"difficult":[23],"problem":[24],"as":[25,57,127],"it":[26,66],"requires":[27],"understanding":[28],"fine-grained":[30],"structured":[31],"information":[32,156],"of":[33,71,181],"both":[34],"and":[36,120],"image":[37],"for":[38,83,123,133,167],"compositional":[39,44],"reasoning.":[40],"To":[41],"establish":[42],"reasoning,":[45],"recent":[46],"works":[47],"attempt":[48],"introduce":[50],"scene":[52,60,81],"graph":[53],"VQA.":[55],"However,":[56],"generated":[59],"graphs":[61,82],"are":[62,146,172],"usually":[63],"quite":[64],"noisy,":[65],"greatly":[67],"limits":[68],"performance":[70],"answering.":[73,169],"Therefore,":[74],"this":[75],"paper":[76],"proposes":[77],"refine":[79],"improving":[84],"effectiveness.":[86],"Specifically,":[87],"we":[88],"present":[89],"novel":[91],"<bold":[92,96,100,106],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[93,97,101,107,138],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">S</b>":[94],"cene":[95],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">G</b>":[98],"raph":[99],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">R</b>":[102],"efinement":[103],"network":[104,115,152],"(":[105],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">SGR</b>":[108],"),":[109],"which":[110],"introduces":[111],"transformer-based":[113],"refinement":[114],"enhance":[117],"object":[119],"relation":[121],"features":[122],"better":[124],"classification.":[125],"Moreover,":[126],"provides":[130],"valuable":[131],"distinguishing":[134],"whether":[135],"<inline-formula":[137],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[139],"notation=\"LaTeX\">$\\left\\langle":[140],"\\mathit{subject,":[141],"predicate,":[142],"object}":[143],"\\right\\rangle$</tex-math></inline-formula>":[144],"triplets":[145],"helpful":[147],"or":[148],"not,":[149],"SGR":[151],"exploits":[153],"semantic":[155],"presented":[157],"questions":[160],"select":[162],"most":[164],"relevant":[165],"relations":[166],"Extensive":[170],"experiments":[171],"conducted":[173],"GQA":[176],"benchmark":[177],"demonstrate":[178],"effectiveness":[180],"our":[182],"method.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}