{"id":"https://openalex.org/W4312413737","doi":"https://doi.org/10.1109/dsit55514.2022.9943834","title":"A Multi-Layer Attention Network for Visual Commonsense Reasoning","display_name":"A Multi-Layer Attention Network for Visual Commonsense Reasoning","publication_year":2022,"publication_date":"2022-07-22","ids":{"openalex":"https://openalex.org/W4312413737","doi":"https://doi.org/10.1109/dsit55514.2022.9943834"},"language":"en","primary_location":{"id":"doi:10.1109/dsit55514.2022.9943834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsit55514.2022.9943834","pdf_url":null,"source":{"id":"https://openalex.org/S4363608293","display_name":"2022 5th International Conference on Data Science and Information Technology (DSIT)","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 5th International Conference on Data Science and Information Technology (DSIT)","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/A5100457807","display_name":"Wenqi Zhang","orcid":"https://orcid.org/0000-0002-8312-0184"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenqi Zhang","raw_affiliation_strings":["School of Computer Science and Technology Qilu University of Technology,Jinan,China","School of Computer Science and Technology Qilu University of Technology, Jinan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology Qilu University of Technology,Jinan,China","institution_ids":["https://openalex.org/I152269853"]},{"raw_affiliation_string":"School of Computer Science and Technology Qilu University of Technology, Jinan, China","institution_ids":["https://openalex.org/I152269853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041251474","display_name":"Yongchao Gao","orcid":"https://orcid.org/0000-0002-4732-4112"},"institutions":[{"id":"https://openalex.org/I4210158984","display_name":"National Supercomputing Center in Wuxi","ror":"https://ror.org/04ypjrs34","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210158984"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongchao Gao","raw_affiliation_strings":["Shandong Computer Science Center (National Supercomputing Center in Jinan),Jinan,China","Shandong Computer Science Center (National Supercomputing Center in Jinan), Jinan, China"],"affiliations":[{"raw_affiliation_string":"Shandong Computer Science Center (National Supercomputing Center in Jinan),Jinan,China","institution_ids":["https://openalex.org/I4210158984"]},{"raw_affiliation_string":"Shandong Computer Science Center (National Supercomputing Center in Jinan), Jinan, China","institution_ids":["https://openalex.org/I4210158984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102393593","display_name":"Heng Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158984","display_name":"National Supercomputing Center in Wuxi","ror":"https://ror.org/04ypjrs34","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210158984"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Qian","raw_affiliation_strings":["Shandong Computer Science Center (National Supercomputing Center in Jinan),Jinan,China","Shandong Computer Science Center (National Supercomputing Center in Jinan), Jinan, China"],"affiliations":[{"raw_affiliation_string":"Shandong Computer Science Center (National Supercomputing Center in Jinan),Jinan,China","institution_ids":["https://openalex.org/I4210158984"]},{"raw_affiliation_string":"Shandong Computer Science Center (National Supercomputing Center in Jinan), Jinan, China","institution_ids":["https://openalex.org/I4210158984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010062912","display_name":"Hongli Lyu","orcid":"https://orcid.org/0000-0001-8630-3536"},"institutions":[{"id":"https://openalex.org/I72541430","display_name":"Lakehead University","ror":"https://ror.org/023p7mg82","country_code":"CA","type":"education","lineage":["https://openalex.org/I72541430"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hongli Lyu","raw_affiliation_strings":["Lakehead University Thunder Bay,Department of Engineering,Canada","Department of Engineering, Lakehead University Thunder Bay, Canada"],"affiliations":[{"raw_affiliation_string":"Lakehead University Thunder Bay,Department of Engineering,Canada","institution_ids":["https://openalex.org/I72541430"]},{"raw_affiliation_string":"Department of Engineering, Lakehead University Thunder Bay, Canada","institution_ids":["https://openalex.org/I72541430"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100457807"],"corresponding_institution_ids":["https://openalex.org/I152269853"],"apc_list":null,"apc_paid":null,"fwci":0.1199,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.4368316,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9986000061035156,"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":0.9973000288009644,"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":0.8006229400634766},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.7278590798377991},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6055753827095032},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5506948828697205},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5467088222503662},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5157709121704102},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5111449360847473},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.49533572793006897},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.45901691913604736},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45402461290359497},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.43218672275543213},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4222240447998047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8006229400634766},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.7278590798377991},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6055753827095032},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5506948828697205},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5467088222503662},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5157709121704102},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5111449360847473},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.49533572793006897},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.45901691913604736},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45402461290359497},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.43218672275543213},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4222240447998047},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dsit55514.2022.9943834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsit55514.2022.9943834","pdf_url":null,"source":{"id":"https://openalex.org/S4363608293","display_name":"2022 5th International Conference on Data Science and Information Technology (DSIT)","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 5th International Conference on Data Science and Information Technology (DSIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2608787653","https://openalex.org/W2896457183","https://openalex.org/W2963115613","https://openalex.org/W2963541336","https://openalex.org/W2964067226","https://openalex.org/W2970927600","https://openalex.org/W2982073904","https://openalex.org/W2982555517","https://openalex.org/W3021007069","https://openalex.org/W3034984754","https://openalex.org/W3035651653","https://openalex.org/W3090449556","https://openalex.org/W3092601801","https://openalex.org/W3120536465","https://openalex.org/W3126792443","https://openalex.org/W3135705837","https://openalex.org/W3141200244","https://openalex.org/W3152635550","https://openalex.org/W3174690404","https://openalex.org/W3185066916","https://openalex.org/W3198570286","https://openalex.org/W4205199670","https://openalex.org/W4226538672","https://openalex.org/W6736893582","https://openalex.org/W6755207826","https://openalex.org/W6767194493","https://openalex.org/W6767362881","https://openalex.org/W6769264886","https://openalex.org/W6784312857","https://openalex.org/W6789753369"],"related_works":["https://openalex.org/W4301143707","https://openalex.org/W2952745240","https://openalex.org/W3021007069","https://openalex.org/W4389518870","https://openalex.org/W3091195047","https://openalex.org/W4388093383","https://openalex.org/W2963115613","https://openalex.org/W2943368643","https://openalex.org/W2981750021","https://openalex.org/W3109639288"],"abstract_inverted_index":{"Visual":[0],"Commonsense":[1],"Reasoning":[2],"(VCR)":[3],"is":[4,57],"a":[5,53,132],"challenging":[6],"multimodal":[7],"task":[8,138],"involving":[9],"several":[10],"research":[11],"fields":[12],"such":[13],"as":[14],"vision,":[15],"cognition,":[16],"and":[17,22,48,68,82,95,107,139],"reasoning,":[18],"which":[19],"combines":[20],"images":[21],"natural":[23],"language":[24,83],"for":[25,59],"reasoning.":[26],"Existing":[27],"VCR":[28,61,123,137],"methods":[29,40],"focus":[30],"on":[31,121,146],"global":[32],"attention":[33,42,55,66,71,75,88,99],"or":[34],"use":[35],"pre-training":[36],"models,":[37],"but":[38],"these":[39],"lack":[41],"to":[43,89],"local":[44],"features":[45,79],"of":[46,80,93,143],"visual":[47,81,87,94,106],"language.":[49,96,108],"In":[50],"this":[51],"paper,":[52],"multi-layer":[54],"network":[56],"proposed":[58,129],"the":[60,91,102,110,122,128,136,141,144],"task,":[62],"including":[63],"an":[64,69,116],"intra-modal":[65,74],"module":[67,76,100],"inter-modal":[70,98],"module.":[72],"The":[73,97],"complements":[77],"important":[78],"modalities":[84],"with":[85],"fine-grained":[86],"improve":[90],"relevance":[92],"captures":[101],"internal":[103],"dependencies":[104],"between":[105],"Finally,":[109],"two":[111],"modules":[112],"are":[113],"integrated":[114],"into":[115],"end-to-end":[117],"reasoning":[118],"framework.":[119],"Experiments":[120],"large-scale":[124],"dataset":[125],"show":[126],"that":[127],"method":[130,145],"exhibits":[131],"decent":[133],"improvement":[134],"in":[135],"illustrates":[140],"effectiveness":[142],"three":[147],"subtasks.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}