{"id":"https://openalex.org/W3021129795","doi":null,"title":"Diverse Visuo-Lingustic Question Answering (DVLQA) Challenge","display_name":"Diverse Visuo-Lingustic Question Answering (DVLQA) Challenge","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3021129795","mag":"3021129795"},"language":"en","primary_location":{"id":"mag:3021129795","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2005.00330","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.00330","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047561807","display_name":"Shailaja Keyur Sampat","orcid":"https://orcid.org/0009-0006-9873-3342","observed_orcids":["https://orcid.org/0009-0006-9873-3342"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shailaja Keyur Sampat","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002278578","display_name":"Yezhou Yang","orcid":"https://orcid.org/0000-0003-0126-8976","observed_orcids":["https://orcid.org/0000-0003-0126-8976"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yezhou Yang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0126-8976","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5083735830","display_name":"Chitta R. Baral","orcid":"https://orcid.org/0000-0002-7549-723X","observed_orcids":["https://orcid.org/0000-0002-7549-723X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chitta Baral","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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/T10601","display_name":"Handwritten Text Recognition Techniques","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/multimodal-question-answering","display_name":"multimodal question answering","score":0.8149999976158142},{"id":"https://openalex.org/keywords/visual-question-answering","display_name":"visual question answering","score":0.6460000276565552},{"id":"https://openalex.org/keywords/machine-reading-comprehension","display_name":"machine reading comprehension","score":0.8309999704360962},{"id":"https://openalex.org/keywords/heterogeneous-data-sources","display_name":"heterogeneous data sources","score":0.5600000023841858},{"id":"https://openalex.org/keywords/benchmark-dataset","display_name":"benchmark dataset","score":0.4869999885559082},{"id":"https://openalex.org/keywords/joint-inference","display_name":"joint inference","score":0.4189999997615814},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.6570000052452087}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.9063498973846436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8066273331642151},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5625391006469727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5401318073272705},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.531583845615387},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5270662307739258},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4928143322467804},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47692152857780457},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43871381878852844},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3021129795","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2005.00330","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3021129795","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2005.00330","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1575833922","https://openalex.org/W2058556535","https://openalex.org/W2194775991","https://openalex.org/W2561715562","https://openalex.org/W2788496822","https://openalex.org/W2793065281","https://openalex.org/W2799201136","https://openalex.org/W2936135081","https://openalex.org/W2962994687","https://openalex.org/W2963420691","https://openalex.org/W2963866616","https://openalex.org/W2964303913","https://openalex.org/W2967593235","https://openalex.org/W2970231061","https://openalex.org/W2970608575"],"related_works":["https://openalex.org/W3092013135","https://openalex.org/W4403020990","https://openalex.org/W4412107017","https://openalex.org/W4301378480","https://openalex.org/W4285126628","https://openalex.org/W2391839782","https://openalex.org/W3021000432","https://openalex.org/W4285436347","https://openalex.org/W4407049645","https://openalex.org/W2903199940"],"abstract_inverted_index":{"Existing":[0],"question":[1,67,100,115,177],"answering":[2,68,116,178],"datasets":[3],"mostly":[4],"contain":[5],"homogeneous":[6],"contexts,":[7],"based":[8],"on":[9,133],"either":[10,94],"textual":[11,90],"or":[12],"visual":[13,88,114],"information":[14,31],"alone.":[15],"On":[16],"the":[17,23,38,53,61,99,105,134,164],"other":[18],"hand,":[19],"digitalization":[20],"has":[21],"evolved":[22],"nature":[24],"of":[25,74,95,107,155],"reading":[26,79],"which":[27,143],"often":[28],"includes":[29],"integrating":[30],"across":[32],"multiple":[33],"heterogeneous":[34],"sources.":[35],"To":[36],"bridge":[37],"gap":[39],"between":[40],"two,":[41],"we":[42,168],"compile":[43],"a":[44,66,78,140,173],"Diverse":[45],"Visuo-Lingustic":[46],"Question":[47],"Answering":[48],"(DVLQA)":[49],"challenge":[50],"corpus,":[51],"where":[52,81],"task":[54],"is":[55,160],"to":[56,85,120,130],"derive":[57],"joint":[58,135],"inference":[59],"about":[60],"given":[62],"image-text":[63],"modality":[64],"in":[65],"setting.":[69],"Each":[70],"dataset":[71],"item":[72],"consists":[73],"an":[75],"image":[76],"and":[77,89,117,124,149,187],"passage,":[80],"questions":[82],"are":[83,128],"designed":[84],"combine":[86],"both":[87],"information,":[91],"i.e.":[92],"ignoring":[93],"them":[96],"would":[97],"make":[98],"unanswerable.":[101],"We":[102,137],"first":[103],"explore":[104],"combination":[106],"best":[108],"existing":[109],"deep":[110],"learning":[111],"architectures":[112],"for":[113,153,176],"machine":[118],"comprehension":[119],"solve":[121],"DVLQA":[122,170],"subsets":[123],"show":[125],"that":[126],"they":[127],"unable":[129],"reason":[131],"well":[132],"task.":[136],"then":[138],"develop":[139],"modular":[141],"method":[142],"demonstrates":[144],"slightly":[145],"better":[146],"baseline":[147],"performance":[148],"offers":[150],"more":[151],"transparency":[152],"interpretation":[154],"intermediate":[156],"outputs.":[157],"However,":[158],"this":[159,195],"still":[161],"far":[162],"behind":[163],"human":[165],"performance,":[166],"therefore":[167],"believe":[169],"will":[171,190],"be":[172,191],"challenging":[174],"benchmark":[175],"involving":[179],"reasoning":[180],"over":[181],"visuo-linguistic":[182],"context.":[183],"The":[184],"dataset,":[185],"code":[186],"public":[188],"leaderboard":[189],"made":[192],"available":[193],"at":[194],"https":[196],"URL.":[197]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2020-05-13T00:00:00"}