{"id":"https://openalex.org/W4405754155","doi":"https://doi.org/10.1109/tmm.2024.3521725","title":"Relation Inference Enhancement Network for Visual Commonsense Reasoning","display_name":"Relation Inference Enhancement Network for Visual Commonsense Reasoning","publication_year":2024,"publication_date":"2024-12-24","ids":{"openalex":"https://openalex.org/W4405754155","doi":"https://doi.org/10.1109/tmm.2024.3521725"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3521725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521725","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/A5005487402","display_name":"Mengqi Yuan","orcid":"https://orcid.org/0000-0001-9183-3267"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mengqi Yuan","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084003247","display_name":"Gengyun Jia","orcid":"https://orcid.org/0000-0002-0513-138X"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gengyun Jia","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044697325","display_name":"Bing-Kun Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Kun Bao","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005487402"],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":0.49,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67164361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"27","issue":null,"first_page":"2221","last_page":"2231"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.8970999717712402,"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/T10799","display_name":"Data Visualization and Analytics","score":0.8970999717712402,"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":0.8758000135421753,"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/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.8353056907653809},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8288427591323853},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6906573176383972},{"id":"https://openalex.org/keywords/commonsense-knowledge","display_name":"Commonsense knowledge","score":0.6693648099899292},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6512759923934937},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.453770250082016},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40182557702064514},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3210511803627014},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.2451307475566864},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.22076332569122314}],"concepts":[{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.8353056907653809},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8288427591323853},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6906573176383972},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.6693648099899292},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6512759923934937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.453770250082016},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40182557702064514},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3210511803627014},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.2451307475566864},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.22076332569122314}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3521725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521725","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/G4317995357","display_name":null,"funder_award_id":"61936005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5851403343","display_name":null,"funder_award_id":"62325206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7576569306","display_name":null,"funder_award_id":"62306150","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W2471094925","https://openalex.org/W2745461083","https://openalex.org/W2901505625","https://openalex.org/W2914699769","https://openalex.org/W2963115613","https://openalex.org/W2963150697","https://openalex.org/W2963717374","https://openalex.org/W2998081460","https://openalex.org/W3021007069","https://openalex.org/W3034287395","https://openalex.org/W3034655362","https://openalex.org/W3090449556","https://openalex.org/W3118856670","https://openalex.org/W3156624167","https://openalex.org/W3174690404","https://openalex.org/W3175344799","https://openalex.org/W3176896951","https://openalex.org/W3177224328","https://openalex.org/W3181758331","https://openalex.org/W3183226462","https://openalex.org/W3192587235","https://openalex.org/W3194633557","https://openalex.org/W3204924011","https://openalex.org/W3206218097","https://openalex.org/W3210192352","https://openalex.org/W4206722749","https://openalex.org/W4226538672","https://openalex.org/W4294967726","https://openalex.org/W4304092489","https://openalex.org/W4312390120","https://openalex.org/W4312864639","https://openalex.org/W4366822016","https://openalex.org/W4376481269","https://openalex.org/W4377715513","https://openalex.org/W4377971516","https://openalex.org/W4383337770","https://openalex.org/W4386275868","https://openalex.org/W4387968123","https://openalex.org/W4387969662","https://openalex.org/W4388430346","https://openalex.org/W4390873264","https://openalex.org/W4402703029","https://openalex.org/W4402754286","https://openalex.org/W6631190155","https://openalex.org/W6728881024","https://openalex.org/W6764756247","https://openalex.org/W6766904570","https://openalex.org/W6767194493","https://openalex.org/W6767211374","https://openalex.org/W6767362881","https://openalex.org/W6769264886","https://openalex.org/W6770813465","https://openalex.org/W6779473860","https://openalex.org/W6789909235","https://openalex.org/W6803578320","https://openalex.org/W6811440883","https://openalex.org/W6854336665","https://openalex.org/W6859922691"],"related_works":["https://openalex.org/W3035583586","https://openalex.org/W4320165839","https://openalex.org/W2151799802","https://openalex.org/W2196562041","https://openalex.org/W4385488510","https://openalex.org/W2073302931","https://openalex.org/W3206107299","https://openalex.org/W3082691151","https://openalex.org/W4287633646","https://openalex.org/W4378501473"],"abstract_inverted_index":{"When":[0],"presented":[1],"with":[2,42,194],"a":[3,15,20,35,120,157],"question":[4],"regarding":[5],"an":[6],"image,":[7],"Visual":[8],"Commonsense":[9],"Reasoning":[10],"(VCR)":[11],"offers":[12],"not":[13],"only":[14],"correct":[16],"answer":[17],"but":[18],"also":[19],"rationale":[21,172],"to":[22,87,104,142,177,189],"justify":[23],"the":[24,55,79,91,99,148,200,211],"answer.":[25],"Existing":[26],"methods":[27],"simply":[28],"combine":[29],"features":[30],"from":[31,62,85,98,173],"multiple":[32],"modalities":[33,76],"onto":[34],"shared":[36],"dimension":[37],"space,":[38],"which":[39,127,162],"doesn't":[40],"align":[41],"human":[43,83],"reasoning":[44,52,60,84,96,129,140,144,187],"patterns,":[45],"resulting":[46],"in":[47,73],"inadequate":[48,58,94],"cross-modal":[49,59,133,149,158],"and":[50,71,136,153,168,179,198,207],"intra-modal":[51,95,138,185],"behaviors.":[53],"On":[54,90],"one":[56],"hand,":[57,93],"arises":[61,97],"existing":[63,102],"models":[64,103],"relying":[65],"on":[66,132],"semantic":[67],"correlations":[68],"between":[69,151,166],"answers":[70,167],"rationales":[72,169],"both":[74],"textual":[75,88],"rather":[77],"than":[78],"generative":[80],"process":[81],"of":[82,101,203,210],"visual":[86],"modality.":[89],"other":[92],"incapacity":[100],"leverage":[105],"previously":[106],"acquired":[107],"object":[108,196],"relations":[109],"beyond":[110],"current":[111],"observations":[112],"like":[113],"humans.":[114],"To":[115,146],"this":[116],"end,":[117],"we":[118],"propose":[119],"novel":[121],"Relation":[122],"Inference":[123],"Enhancement":[124],"Network":[125],"(RIE-Net),":[126],"enhances":[128],"ability":[130],"based":[131],"image":[134,159],"analysis":[135,160],"introduces":[137,156,184],"relational":[139,181,186],"modules":[141,188],"memorize":[143],"knowledge.":[145],"enhance":[147,199],"association":[150],"images":[152],"rationales,":[154],"RIE-Net":[155,183],"module,":[161],"eliminates":[163],"language":[164],"bias":[165],"by":[170],"generating":[171],"images.":[174],"In":[175],"addition,":[176],"comprehend":[178],"retain":[180],"knowledge,":[182],"capture":[190],"prior":[191],"knowledge":[192],"associated":[193],"various":[195],"categories":[197],"model's":[201],"understanding":[202],"visual-spatial":[204],"relationships.":[205],"Quantitative":[206],"qualitative":[208],"evaluations":[209],"public":[212],"VCR":[213],"dataset":[214],"demonstrate":[215],"that":[216],"our":[217],"approach":[218],"performs":[219],"favorably":[220],"against":[221],"state-of-the-art":[222],"methods.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}