{"id":"https://openalex.org/W4226538672","doi":"https://doi.org/10.1609/aaai.v36i5.20536","title":"SGEITL: Scene Graph Enhanced Image-Text Learning for Visual Commonsense Reasoning","display_name":"SGEITL: Scene Graph Enhanced Image-Text Learning for Visual Commonsense Reasoning","publication_year":2022,"publication_date":"2022-06-28","ids":{"openalex":"https://openalex.org/W4226538672","doi":"https://doi.org/10.1609/aaai.v36i5.20536"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v36i5.20536","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/20536/20295","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/20536/20295","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026256051","display_name":"Zhecan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhecan Wang","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084753767","display_name":"Haoxuan You","orcid":"https://orcid.org/0000-0002-7912-4035"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoxuan You","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004824034","display_name":"Liunian Harold Li","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liunian Harold Li","raw_affiliation_strings":["University of California, Los Angeles"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052579251","display_name":"Alireza Zareian","orcid":"https://orcid.org/0000-0003-2983-9849"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alireza Zareian","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110598329","display_name":"Suji Park","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suji Park","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102861281","display_name":"Yiqing Liang","orcid":"https://orcid.org/0009-0005-1481-2194"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiqing Liang","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087096372","display_name":"Kai-Wei Chang","orcid":"https://orcid.org/0000-0001-5365-0072"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai-Wei Chang","raw_affiliation_strings":["University of California, Los Angeles"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037340457","display_name":"Shih\u2010Fu Chang","orcid":"https://orcid.org/0000-0003-1444-1205"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shih-Fu Chang","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.95,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.999831,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"36","issue":"5","first_page":"5914","last_page":"5922"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9999,"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":0.9999,"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":0.9978,"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":0.9815,"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":0.86629915},{"id":"https://openalex.org/keywords/commonsense-knowledge","display_name":"Commonsense knowledge","score":0.75649285},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.742134},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6230047},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.46855435},{"id":"https://openalex.org/keywords/visual-objects","display_name":"Visual Objects","score":0.4476534}],"concepts":[{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.86629915},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79320455},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.75649285},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.742134},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6892923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6255737},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6230047},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6063079},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.55926466},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.46855435},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.4476534},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44307464},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4365958},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33017778},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.24376088},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2053667},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v36i5.20536","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/20536/20295","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2112.08587","pdf_url":"https://arxiv.org/pdf/2112.08587","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v36i5.20536","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/20536/20295","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"score":0.44,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":39,"referenced_works":["https://openalex.org/W2077069816","https://openalex.org/W2277195237","https://openalex.org/W2525778437","https://openalex.org/W2563399268","https://openalex.org/W2579549467","https://openalex.org/W2745461083","https://openalex.org/W2795378892","https://openalex.org/W2884561390","https://openalex.org/W2886970679","https://openalex.org/W2896457183","https://openalex.org/W2962785943","https://openalex.org/W2963101956","https://openalex.org/W2963115613","https://openalex.org/W2963184176","https://openalex.org/W2963518342","https://openalex.org/W2963530300","https://openalex.org/W2963536419","https://openalex.org/W2963691377","https://openalex.org/W2963890019","https://openalex.org/W2966715458","https://openalex.org/W2968124245","https://openalex.org/W2969679616","https://openalex.org/W2969876226","https://openalex.org/W2970231061","https://openalex.org/W2997547717","https://openalex.org/W3014611590","https://openalex.org/W3016211260","https://openalex.org/W3034910302","https://openalex.org/W3035454069","https://openalex.org/W3035688398","https://openalex.org/W3038476992","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3091998909","https://openalex.org/W3094597186","https://openalex.org/W3108230874","https://openalex.org/W4288373939","https://openalex.org/W4289243726","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4320086306","https://openalex.org/W4319452576","https://openalex.org/W4313191056","https://openalex.org/W4312846625","https://openalex.org/W4302773889","https://openalex.org/W4226538672","https://openalex.org/W3116523094","https://openalex.org/W3103326498","https://openalex.org/W2982575451","https://openalex.org/W2981750021"],"abstract_inverted_index":{"Answering":[0],"complex":[1,81],"questions":[2],"about":[3],"images":[4],"is":[5,134],"an":[6],"ambitious":[7],"goal":[8],"for":[9,121,128],"machine":[10],"intelligence,":[11],"which":[12,76],"requires":[13],"a":[14,26,35,86,117,130,148,163],"joint":[15],"understanding":[16,48],"of":[17,41,56,68,186],"images,":[18],"text,":[19],"and":[20,51,71,152,170,182],"commonsense":[21,82,100],"knowledge,":[22],"as":[23,25],"well":[24],"strong":[27],"reasoning":[28],"ability.":[29],"Recently,":[30],"multimodal":[31],"Transformers":[32],"have":[33],"made":[34],"great":[36],"progress":[37],"in":[38,79,99,141,162],"the":[39,65,69,72,106,111,179,184],"task":[40],"Visual":[42],"Commonsense":[43],"Reasoning":[44],"(VCR),":[45],"by":[46],"jointly":[47],"visual":[49,96,142,156],"objects":[50,75],"text":[52],"tokens":[53],"through":[54],"layers":[55],"cross-modality":[57],"attention.":[58],"However,":[59],"these":[60],"approaches":[61],"do":[62],"not":[63],"utilize":[64],"rich":[66],"structure":[67,113,138],"scene":[70,97,107,143,157],"interactions":[73],"between":[74],"are":[77],"essential":[78],"answering":[80],"questions.":[83],"We":[84],"propose":[85,116],"Scene":[87],"Graph":[88],"Enhanced":[89],"Image-Text":[90],"Learning":[91],"(SGEITL)":[92],"framework":[93],"to":[94,104,136,150],"incorporate":[95],"graph":[98,108,119,158],"reasoning.":[101],"In":[102],"order":[103],"exploit":[105],"structure,":[109],"at":[110],"model":[112],"level,":[114],"we":[115,146],"multihop":[118],"transformer":[120],"regularizing":[122],"attention":[123],"interaction":[124],"among":[125],"hops.":[126],"As":[127],"pre-training,":[129],"scene-graph-aware":[131],"pre-training":[132],"method":[133,149],"proposed":[135,188],"leverage":[137],"knowledge":[139],"extracted":[140],"graph.":[144],"Moreover,":[145],"introduce":[147],"train":[151],"generate":[153],"domain":[154],"relevant":[155],"using":[159],"textual":[160],"annotations":[161],"weakly-supervised":[164],"manner.":[165],"Extensive":[166],"experiments":[167],"on":[168],"VCR":[169],"other":[171],"tasks":[172],"show":[173],"significant":[174],"performance":[175],"boost":[176],"compared":[177],"with":[178],"state-of-the-art":[180],"methods,":[181],"prove":[183],"efficacy":[185],"each":[187],"component.":[189]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4226538672","counts_by_year":[{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":3}],"updated_date":"2025-01-07T17:27:32.119836","created_date":"2022-05-05"}