{"id":"https://openalex.org/W2912371042","doi":"https://doi.org/10.48550/arxiv.1901.06706","title":"Visual Entailment: A Novel Task for Fine-Grained Image Understanding","display_name":"Visual Entailment: A Novel Task for Fine-Grained Image Understanding","publication_year":2019,"publication_date":"2019-01-20","ids":{"openalex":"https://openalex.org/W2912371042","doi":"https://doi.org/10.48550/arxiv.1901.06706","mag":"2912371042"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1901.06706","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.06706","pdf_url":"https://arxiv.org/pdf/1901.06706","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1901.06706","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xie, Ning","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19648265","display_name":"Wright State University","ror":"https://ror.org/04qk6pt94","country_code":"US","type":"education","lineage":["https://openalex.org/I19648265"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xie, Ning","raw_affiliation_strings":["Wright State University Dayton , OH , U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wright State University Dayton , OH , U.S.A","institution_ids":["https://openalex.org/I19648265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106083591","display_name":"Farley Lai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lai, Farley","raw_affiliation_strings":["NEC Laboratories America Princeton , NJ , U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Laboratories America Princeton , NJ , U.S.A","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109034509","display_name":"Derek Doran","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19648265","display_name":"Wright State University","ror":"https://ror.org/04qk6pt94","country_code":"US","type":"education","lineage":["https://openalex.org/I19648265"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Doran, Derek","raw_affiliation_strings":["Wright State University Dayton , OH , U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wright State University Dayton , OH , U.S.A","institution_ids":["https://openalex.org/I19648265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016480160","display_name":"Asim Kadav","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kadav, Asim","raw_affiliation_strings":["NEC Laboratories America Princeton , NJ , U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Laboratories America Princeton , NJ , U.S.A","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":309,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T10028","display_name":"Topic Modeling","score":0.0,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/visual-entailment","display_name":"visual entailment","score":0.9940000176429749},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"visual reasoning","score":0.8109999895095825},{"id":"https://openalex.org/keywords/flickr30k","display_name":"Flickr30k","score":0.9330000281333923},{"id":"https://openalex.org/keywords/visual-question-answering","display_name":"visual question answering","score":0.7639999985694885},{"id":"https://openalex.org/keywords/cross-modal-attention","display_name":"cross-modal attention","score":0.7749999761581421},{"id":"https://openalex.org/keywords/explainability","display_name":"explainability","score":0.796999990940094},{"id":"https://openalex.org/keywords/dataset-bias","display_name":"data bias","score":0.5109999775886536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8429203629493713},{"id":"https://openalex.org/C134752490","wikidata":"https://www.wikidata.org/wiki/Q374182","display_name":"Logical consequence","level":2,"score":0.7395602464675903},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.69964998960495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6869642734527588},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6711054444313049},{"id":"https://openalex.org/C95318506","wikidata":"https://www.wikidata.org/wiki/Q6588467","display_name":"Textual entailment","level":3,"score":0.6698975563049316},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6669485569000244},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6655247807502747},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6517313718795776},{"id":"https://openalex.org/C2778023277","wikidata":"https://www.wikidata.org/wiki/Q321703","display_name":"Premise","level":2,"score":0.5650821924209595},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.528424084186554},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.44022414088249207},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07353782653808594},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:1901.06706","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.06706","pdf_url":"https://arxiv.org/pdf/1901.06706","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:corescholar.libraries.wright.edu:cse-1656","doi":null,"is_oa":true,"landing_page_url":"https://corescholar.libraries.wright.edu/cse/657","pdf_url":null,"source":{"id":"https://openalex.org/S2737205702","display_name":"Journal of Bioresource Management","issn_l":"2309-3854","issn":["2309-3854"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["doaj","erih-plus"],"host_organization":"https://openalex.org/P4310316536","host_organization_name":"Bioresource Research Center (BRC), Islamabad","host_organization_lineage":["https://openalex.org/P4310316536"],"host_organization_lineage_names":["Bioresource Research Center (BRC), Islamabad"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science and Engineering Faculty Publications","raw_type":"text"},{"id":"pmh:oai:works.bepress.com:derek_doran-10056","doi":null,"is_oa":true,"landing_page_url":"https://works.bepress.com/derek_doran/75","pdf_url":null,"source":{"id":"https://openalex.org/S2737205702","display_name":"Journal of Bioresource Management","issn_l":"2309-3854","issn":["2309-3854"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["doaj","erih-plus"],"host_organization":"https://openalex.org/P4310316536","host_organization_name":"Bioresource Research Center (BRC), Islamabad","host_organization_lineage":["https://openalex.org/P4310316536"],"host_organization_lineage_names":["Bioresource Research Center (BRC), Islamabad"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Derek Doran","raw_type":"text"},{"id":"doi:10.48550/arxiv.1901.06706","doi":"https://doi.org/10.48550/arxiv.1901.06706","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1901.06706","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1901.06706","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.06706","pdf_url":"https://arxiv.org/pdf/1901.06706","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2912371042.pdf","grobid_xml":"https://content.openalex.org/works/W2912371042.grobid-xml"},"referenced_works_count":77,"referenced_works":["https://openalex.org/W92662927","https://openalex.org/W806995027","https://openalex.org/W1514535095","https://openalex.org/W1525961042","https://openalex.org/W1575833922","https://openalex.org/W1686810756","https://openalex.org/W1849277567","https://openalex.org/W1897507002","https://openalex.org/W1924770834","https://openalex.org/W2045254372","https://openalex.org/W2077069816","https://openalex.org/W2087451659","https://openalex.org/W2116705992","https://openalex.org/W2118463056","https://openalex.org/W2123024445","https://openalex.org/W2146897752","https://openalex.org/W2185175083","https://openalex.org/W2189070436","https://openalex.org/W2190067570","https://openalex.org/W2195388612","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2282821441","https://openalex.org/W2424413254","https://openalex.org/W2481240925","https://openalex.org/W2550553598","https://openalex.org/W2558535589","https://openalex.org/W2560645892","https://openalex.org/W2563399268","https://openalex.org/W2579549467","https://openalex.org/W2583695460","https://openalex.org/W2591644541","https://openalex.org/W2597603852","https://openalex.org/W2607855566","https://openalex.org/W2608787653","https://openalex.org/W2613404084","https://openalex.org/W2616247523","https://openalex.org/W2624614404","https://openalex.org/W2626778328","https://openalex.org/W2734498959","https://openalex.org/W2745132836","https://openalex.org/W2745166287","https://openalex.org/W2745461083","https://openalex.org/W2754191212","https://openalex.org/W2760103357","https://openalex.org/W2776207810","https://openalex.org/W2786209943","https://openalex.org/W2790415926","https://openalex.org/W2791148095","https://openalex.org/W2804243936","https://openalex.org/W2806070179","https://openalex.org/W2806075129","https://openalex.org/W2807535589","https://openalex.org/W2808416189","https://openalex.org/W2884093133","https://openalex.org/W2893064646","https://openalex.org/W2949650786","https://openalex.org/W2949906242","https://openalex.org/W2950179405","https://openalex.org/W2950500611","https://openalex.org/W2951619830","https://openalex.org/W2952228917","https://openalex.org/W2953084091","https://openalex.org/W2953212746","https://openalex.org/W2962685628","https://openalex.org/W2962729168","https://openalex.org/W2962749469","https://openalex.org/W2963066927","https://openalex.org/W2963097937","https://openalex.org/W2963224792","https://openalex.org/W2963383024","https://openalex.org/W2963453030","https://openalex.org/W2963649796","https://openalex.org/W2963650529","https://openalex.org/W2963758027","https://openalex.org/W2964138343","https://openalex.org/W2964225075"],"related_works":["https://openalex.org/W2901479108","https://openalex.org/W4312336279","https://openalex.org/W4387968416","https://openalex.org/W4312239809","https://openalex.org/W4409584661","https://openalex.org/W3015608264","https://openalex.org/W4416280643","https://openalex.org/W7220708873","https://openalex.org/W4414880786","https://openalex.org/W4288055855"],"abstract_inverted_index":{"Existing":[0],"visual":[1],"reasoning":[2,33],"datasets":[3],"such":[4],"as":[5,81],"Visual":[6,59,136],"Question":[7],"Answering":[8],"(VQA),":[9],"often":[10],"suffer":[11],"from":[12],"biases":[13],"conditioned":[14],"on":[15,114],"the":[16,35,48,98,102,115,142,162],"question,":[17],"image":[18,99],"or":[19],"answer":[20],"distributions.":[21],"The":[22,87,170],"recently":[23],"proposed":[24],"CLEVR":[25],"dataset":[26,36,111,172],"addresses":[27],"these":[28],"limitations":[29],"and":[30,39,44,121,130,151],"requires":[31],"fine-grained":[32],"but":[34],"is":[37,70,94,173],"synthetic":[38],"consists":[40],"of":[41,64,89,164],"similar":[42],"objects":[43],"sentence":[45,80],"structures":[46],"across":[47],"dataset.":[49,123],"In":[50],"this":[51,106],"paper,":[52],"we":[53,108,160],"introduce":[54],"a":[55,68,77,90,110,132],"new":[56],"inference":[57],"task,":[58,107],"Entailment":[60,85,137],"(VE)":[61],"-":[62],"consisting":[63],"image-sentence":[65],"pairs":[66],"whereby":[67],"premise":[69],"defined":[71],"by":[72],"an":[73],"image,":[74],"rather":[75],"than":[76],"natural":[78],"language":[79],"in":[82],"traditional":[83],"Textual":[84],"tasks.":[86],"goal":[88],"trained":[91],"VE":[92,143],"model":[93,133],"to":[95,140,148],"predict":[96],"whether":[97],"semantically":[100],"entails":[101],"text.":[103],"To":[104],"realize":[105],"build":[109,131],"SNLI-VE":[112,171],"based":[113,157],"Stanford":[116],"Natural":[117],"Language":[118],"Inference":[119],"corpus":[120],"Flickr30k":[122],"We":[124],"evaluate":[125],"various":[126],"existing":[127],"VQA":[128,156],"baselines":[129],"called":[134],"Explainable":[135],"(EVE)":[138],"system":[139],"address":[141],"task.":[144],"EVE":[145,165],"achieves":[146],"up":[147],"71%":[149],"accuracy":[150],"outperforms":[152],"several":[153],"other":[154],"state-of-the-art":[155],"models.":[158],"Finally,":[159],"demonstrate":[161],"explainability":[163],"through":[166],"cross-modal":[167],"attention":[168],"visualizations.":[169],"publicly":[174],"available":[175],"at":[176],"https://github.com/":[177],"necla-ml/SNLI-VE.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":24},{"year":2025,"cited_by_count":42},{"year":2024,"cited_by_count":54},{"year":2023,"cited_by_count":74},{"year":2022,"cited_by_count":59},{"year":2021,"cited_by_count":34},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":5}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2019-02-21T00:00:00"}