{"id":"https://openalex.org/W2805771587","doi":"https://doi.org/10.48550/arxiv.1806.00857","title":"On the Flip Side: Identifying Counterexamples in Visual Question Answering","display_name":"On the Flip Side: Identifying Counterexamples in Visual Question Answering","publication_year":2018,"publication_date":"2018-06-03","ids":{"openalex":"https://openalex.org/W2805771587","doi":"https://doi.org/10.48550/arxiv.1806.00857","mag":"2805771587"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1806.00857","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.00857","pdf_url":"https://arxiv.org/pdf/1806.00857","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1806.00857","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082051197","display_name":"Gabriel Grand","orcid":"https://orcid.org/0000-0003-1920-0021","observed_orcids":["https://orcid.org/0000-0003-1920-0021"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Grand, Gabriel","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082310362","display_name":"Aron Szanto","orcid":"https://orcid.org/0000-0003-0843-2011","observed_orcids":["https://orcid.org/0000-0003-0843-2011"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Szanto, Aron","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kim, Yoon","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kim, Yoon","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062546146","display_name":"Alexander M. Rush","orcid":"https://orcid.org/0000-0002-9900-1606","observed_orcids":["https://orcid.org/0000-0002-9900-1606"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rush, Alexander","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I136199984"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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/T11605","display_name":"Visual Attention and Saliency Detection","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"}},{"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-question-answering","display_name":"visual question answering","score":1.0},{"id":"https://openalex.org/keywords/multimodal-representation","display_name":"multimodal representation","score":0.753000020980835},{"id":"https://openalex.org/keywords/open-ended-question-answering","display_name":"open-ended question answering","score":0.5270000100135803},{"id":"https://openalex.org/keywords/model-evaluation","display_name":"model evaluation","score":0.46799999475479126}],"concepts":[{"id":"https://openalex.org/C162838799","wikidata":"https://www.wikidata.org/wiki/Q596077","display_name":"Counterexample","level":2,"score":0.8704091310501099},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8393719792366028},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7392411828041077},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7000229954719543},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6661362648010254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6249448657035828},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5695419311523438},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5675815343856812},{"id":"https://openalex.org/C3019144022","wikidata":"https://www.wikidata.org/wiki/Q4124998","display_name":"Questions and answers","level":2,"score":0.4760812819004059},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45394495129585266},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32944566011428833},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08935892581939697},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/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}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1806.00857","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.00857","pdf_url":"https://arxiv.org/pdf/1806.00857","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":"mag:2805771587","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1806.00857","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},{"id":"doi:10.48550/arxiv.1806.00857","doi":"https://doi.org/10.48550/arxiv.1806.00857","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1806.00857","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1806.00857","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.00857","pdf_url":"https://arxiv.org/pdf/1806.00857","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":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W2095705004","https://openalex.org/W2157364932","https://openalex.org/W2189070436","https://openalex.org/W2189487889","https://openalex.org/W2277195237","https://openalex.org/W2396147015","https://openalex.org/W2560730294","https://openalex.org/W2594475271","https://openalex.org/W2612257250","https://openalex.org/W2616125804","https://openalex.org/W2949650786","https://openalex.org/W2950726992","https://openalex.org/W2950761309","https://openalex.org/W2951619830","https://openalex.org/W2962749469","https://openalex.org/W2963398599","https://openalex.org/W2963890019","https://openalex.org/W2964138343"],"related_works":["https://openalex.org/W2982461533","https://openalex.org/W3206946574","https://openalex.org/W2971373693","https://openalex.org/W3141200244","https://openalex.org/W3098019619","https://openalex.org/W3047485018","https://openalex.org/W2902377675","https://openalex.org/W3204281258","https://openalex.org/W3004389737","https://openalex.org/W3093385053","https://openalex.org/W3096779235","https://openalex.org/W3089709427","https://openalex.org/W3203317685","https://openalex.org/W2963668159","https://openalex.org/W2849425149","https://openalex.org/W3092573238","https://openalex.org/W2987086322","https://openalex.org/W2747148117","https://openalex.org/W3128615853","https://openalex.org/W2496096353"],"abstract_inverted_index":{"Visual":[0],"question":[1,117],"answering":[2],"(VQA)":[3],"models":[4,52,75,85],"respond":[5],"to":[6,25,53,63,108],"open-ended":[7],"natural":[8],"language":[9],"questions":[10],"about":[11],"images.":[12,37],"While":[13,83],"VQA":[14,29,48,74,102,125],"is":[15,23,127],"an":[16,99],"increasingly":[17],"popular":[18],"area":[19],"of":[20,46,129],"research,":[21],"it":[22],"unclear":[24],"what":[26],"extent":[27],"current":[28],"architectures":[30],"learn":[31],"key":[32],"semantic":[33],"distinctions":[34],"between":[35],"visually-similar":[36],"To":[38],"investigate":[39],"this":[40,111],"question,":[41],"we":[42,91],"explore":[43],"a":[44,60,77],"reformulation":[45],"the":[47,64,94,118,124],"task":[49],"that":[50,57,93,120],"challenges":[51],"identify":[54],"counterexamples:":[55],"images":[56],"result":[58],"in":[59],"different":[61],"answer":[62],"original":[65],"question.":[66],"We":[67],"introduce":[68],"two":[69],"methods":[70],"for":[71],"evaluating":[72],"existing":[73,87,100],"against":[76],"supervised":[78],"counterexample":[79],"prediction":[80],"task,":[81],"VQA-CX.":[82],"our":[84],"surpass":[86],"benchmarks":[88],"on":[89,110,123],"VQA-CX,":[90],"find":[92],"multimodal":[95],"representations":[96],"learned":[97],"by":[98],"state-of-the-art":[101],"model":[103],"do":[104],"not":[105],"meaningfully":[106],"contribute":[107],"performance":[109,122],"task.":[112],"These":[113],"results":[114],"call":[115],"into":[116],"assumption":[119],"successful":[121],"benchmark":[126],"indicative":[128],"general":[130],"visual-semantic":[131],"reasoning":[132],"abilities.":[133]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}