{"id":"https://openalex.org/W4376481269","doi":"https://doi.org/10.1109/tmm.2023.3275874","title":"Learning to Agree on Vision Attention for Visual Commonsense Reasoning","display_name":"Learning to Agree on Vision Attention for Visual Commonsense Reasoning","publication_year":2023,"publication_date":"2023-05-12","ids":{"openalex":"https://openalex.org/W4376481269","doi":"https://doi.org/10.1109/tmm.2023.3275874"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3275874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3275874","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/A5001893388","display_name":"Zhenyang Li","orcid":"https://orcid.org/0000-0002-4694-1231"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenyang Li","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0002-4694-1231","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054313646","display_name":"Yangyang Guo","orcid":"https://orcid.org/0000-0001-8691-5372"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yangyang Guo","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-8691-5372","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053685797","display_name":"Kejie Wang","orcid":"https://orcid.org/0000-0003-0595-6856"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kejie Wang","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-0595-6856","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015170265","display_name":"Fan Liu","orcid":"https://orcid.org/0000-0002-4547-3982"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Fan Liu","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4547-3982","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1476-0273","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016415049","display_name":"Mohan Kankanhalli","orcid":"https://orcid.org/0000-0002-4846-2015"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mohan Kankanhalli","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4846-2015","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001893388"],"corresponding_institution_ids":["https://openalex.org/I80143920"],"apc_list":null,"apc_paid":null,"fwci":1.6485,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85917883,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"26","issue":null,"first_page":"1065","last_page":"1075"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9940000176429749,"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":0.9901000261306763,"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/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.9110127091407776},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7893117070198059},{"id":"https://openalex.org/keywords/commonsense-knowledge","display_name":"Commonsense knowledge","score":0.7843855619430542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5660754442214966},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3793456256389618},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.1834174394607544}],"concepts":[{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.9110127091407776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7893117070198059},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.7843855619430542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5660754442214966},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3793456256389618},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.1834174394607544}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3275874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3275874","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4300000071525574}],"awards":[{"id":"https://openalex.org/G3596831556","display_name":null,"funder_award_id":"62172261","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2001832483","https://openalex.org/W2069870183","https://openalex.org/W2137983211","https://openalex.org/W2149427297","https://openalex.org/W2194775991","https://openalex.org/W2471094925","https://openalex.org/W2525778437","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2759653627","https://openalex.org/W2765903581","https://openalex.org/W2886641317","https://openalex.org/W2887978863","https://openalex.org/W2896457183","https://openalex.org/W2914699769","https://openalex.org/W2950635152","https://openalex.org/W2962749469","https://openalex.org/W2963115613","https://openalex.org/W2963150697","https://openalex.org/W2963191264","https://openalex.org/W2963717374","https://openalex.org/W2964345214","https://openalex.org/W2970231061","https://openalex.org/W2997591391","https://openalex.org/W2998356391","https://openalex.org/W3021007069","https://openalex.org/W3026441479","https://openalex.org/W3090449556","https://openalex.org/W3094502228","https://openalex.org/W3104152799","https://openalex.org/W3115819524","https://openalex.org/W3176896951","https://openalex.org/W3177224328","https://openalex.org/W3184784418","https://openalex.org/W3194633557","https://openalex.org/W3206218097","https://openalex.org/W3210279979","https://openalex.org/W3216470601","https://openalex.org/W4200475325","https://openalex.org/W4225683910","https://openalex.org/W4284692930","https://openalex.org/W4297999738","https://openalex.org/W4304092731","https://openalex.org/W4312305353","https://openalex.org/W4312864639","https://openalex.org/W4385567175","https://openalex.org/W6631190155","https://openalex.org/W6719057275","https://openalex.org/W6727690538","https://openalex.org/W6728881024","https://openalex.org/W6766904570","https://openalex.org/W6767194493","https://openalex.org/W6767211374","https://openalex.org/W6767362881","https://openalex.org/W6769264886","https://openalex.org/W6779473860","https://openalex.org/W6798805250"],"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":{"Visual":[0],"Commonsense":[1],"Reasoning":[2],"(VCR)":[3],"remains":[4],"a":[5,24,76,89,98,171],"significant":[6],"yet":[7],"challenging":[8],"research":[9],"problem":[10],"in":[11,88,108],"the":[12,32,36,61,65,103,112,124,132,145,155,164,175,180,183,186,192,195],"realm":[13],"of":[14,116,182,185,194],"visual":[15,78],"reasoning.":[16],"A":[17],"VCR":[18,156],"model":[19,71],"generally":[20],"aims":[21],"at":[22],"answering":[23,38],"textual":[25],"question":[26],"regarding":[27],"an":[28],"image,":[29],"followed":[30],"by":[31],"rationale":[33],"prediction":[34],"for":[35,101],"preceding":[37],"process.":[39,110],"Though":[40],"these":[41,85],"two":[42,54,66,86,114,125,187],"processes":[43,87,126,188],"are":[44,119],"sequential":[45],"and":[46,144,149],"intertwined,":[47],"existing":[48],"methods":[49],"always":[50],"consider":[51],"them":[52],"as":[53,189,191],"independent":[55],"matching-based":[56],"instances.":[57],"They,":[58],"therefore,":[59],"ignore":[60],"pivotal":[62],"relationship":[63],"between":[64],"processes,":[67],"leading":[68],"to":[69,82,122,127,140],"sub-optimal":[70],"performance.":[72],"This":[73],"paper":[74],"presents":[75],"novel":[77],"attention":[79,105,117,143,165],"alignment":[80,166],"method":[81,139,169],"efficaciously":[83],"handle":[84],"unified":[90],"framework.":[91],"To":[92],"achieve":[93],"this,":[94],"we":[95],"first":[96],"design":[97],"re-attention":[99],"module":[100],"aggregating":[102],"vision":[104],"map":[106],"produced":[107],"each":[109],"Thereafter,":[111],"resultant":[113],"sets":[115],"maps":[118],"carefully":[120],"aligned":[121],"guide":[123],"make":[128],"decisions":[129],"based":[130],"on":[131,154],"same":[133],"image":[134],"regions.":[135],"We":[136],"apply":[137],"this":[138],"both":[141],"conventional":[142],"recent":[146],"Transformer":[147],"models":[148],"carry":[150],"out":[151],"extensive":[152],"experiments":[153],"benchmark":[157],"dataset.":[158],"The":[159],"results":[160],"demonstrate":[161],"that":[162],"with":[163],"module,":[167],"our":[168],"achieves":[170],"considerable":[172],"improvement":[173],"over":[174],"baseline":[176],"methods,":[177],"evidently":[178],"revealing":[179],"feasibility":[181],"coupling":[184],"well":[190],"effectiveness":[193],"proposed":[196],"method.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}