{"id":"https://openalex.org/W4375869270","doi":"https://doi.org/10.1109/icassp49357.2023.10094852","title":"Visual Graph Reasoning Network","display_name":"Visual Graph Reasoning Network","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869270","doi":"https://doi.org/10.1109/icassp49357.2023.10094852"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5079078418","display_name":"Dingbang Li","orcid":"https://orcid.org/0009-0004-9775-1683"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dingbang Li","raw_affiliation_strings":["East China Normal University"],"affiliations":[{"raw_affiliation_string":"East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398281","display_name":"Xin Lin","orcid":"https://orcid.org/0000-0001-6913-4654"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Lin","raw_affiliation_strings":["East China Normal University"],"affiliations":[{"raw_affiliation_string":"East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101931026","display_name":"Haibin Cai","orcid":"https://orcid.org/0000-0003-1398-6676"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibin Cai","raw_affiliation_strings":["East China Normal University"],"affiliations":[{"raw_affiliation_string":"East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004120702","display_name":"Wenzhou Chen","orcid":"https://orcid.org/0000-0002-1443-1077"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhou Chen","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5079078418"],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":0.123,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.3738319,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9979000091552734,"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":0.9973999857902527,"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":0.7870550155639648},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4675869941711426},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3082774877548218}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7870550155639648},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4675869941711426},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3082774877548218}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1933349210","https://openalex.org/W2250539671","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2787119853","https://openalex.org/W2799263800","https://openalex.org/W2916723116","https://openalex.org/W2963518342","https://openalex.org/W2963521239","https://openalex.org/W2964118342","https://openalex.org/W2966683369","https://openalex.org/W2990045899","https://openalex.org/W2998631105","https://openalex.org/W3035497460","https://openalex.org/W3106210592","https://openalex.org/W4226397046","https://openalex.org/W4297749157","https://openalex.org/W4320167334","https://openalex.org/W4385245566","https://openalex.org/W6748270630","https://openalex.org/W6748581942","https://openalex.org/W6752083267","https://openalex.org/W6848935878"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Visual":[0,96,124,129],"question":[1],"answering":[2],"(VQA)":[3],"is":[4],"a":[5,91,128],"fundamental":[6],"and":[7,22,55,107,115,141],"challenging":[8],"cross-modal":[9,82],"task.":[10],"This":[11],"task":[12],"requires":[13],"the":[14,19,25,29,74,81,86,112,117,123],"model":[15,111,138],"to":[16,73,104,110],"fully":[17],"understand":[18,34],"image\u2019s":[20],"content":[21,36],"reason":[23],"out":[24],"answer":[26],"based":[27,38],"on":[28,39,122,139],"question.":[30],"Existing":[31],"VQA":[32],"models":[33,61,149],"visual":[35,78],"mainly":[37],"bottom-up":[40,58],"or":[41],"grid":[42,70],"features.":[43],"However,":[44],"both":[45],"types":[46],"of":[47,57,76,85],"vision":[48],"features":[49,59,71],"have":[50],"some":[51],"drawbacks.":[52],"The":[53,143],"discreteness":[54],"independence":[56],"pre-vent":[60],"from":[62],"adequately":[63],"performing":[64],"relational":[65],"reasoning.":[66],"Image":[67],"segmentation":[68],"by":[69],"leads":[72],"fragmentation":[75],"meaningful":[77],"regions,":[79],"limiting":[80],"alignment":[83],"capability":[84],"model.":[87],"Therefore,":[88],"we":[89,126],"proposed":[90],"more":[92],"flexible":[93],"method":[94],"called":[95],"Graph.":[97],"It":[98],"can":[99,150],"connect":[100],"different":[101],"patches":[102],"according":[103],"semantic":[105],"similarity":[106],"spatial":[108],"relevance":[109],"potential":[113],"relationships":[114],"cluster":[116],"adjacent":[118],"homologous":[119],"patches.":[120],"Based":[121],"Graph,":[125],"designed":[127],"Graph":[130],"Reasoning":[131],"Network":[132],"for":[133],"VQA.":[134],"We":[135],"evaluated":[136],"our":[137,148],"GQA":[140],"VQA-v2.":[142],"experimental":[144],"results":[145],"show":[146],"that":[147],"achieve":[151],"excellent":[152],"performance":[153],"between":[154],"single":[155],"models.":[156]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}