{"id":"https://openalex.org/W3194952564","doi":"https://doi.org/10.1109/icip42928.2021.9506539","title":"A Diagnostic Study Of Visual Question Answering With Analogical Reasoning","display_name":"A Diagnostic Study Of Visual Question Answering With Analogical Reasoning","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3194952564","doi":"https://doi.org/10.1109/icip42928.2021.9506539","mag":"3194952564"},"language":"en","primary_location":{"id":"doi:10.1109/icip42928.2021.9506539","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip42928.2021.9506539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101830887","display_name":"Ziqi Huang","orcid":"https://orcid.org/0000-0001-8008-5873"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ziqi Huang","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015639955","display_name":"Hongyuan Zhu","orcid":"https://orcid.org/0000-0001-5177-8320"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hongyuan Zhu","raw_affiliation_strings":["I2R, A*STAR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"I2R, A*STAR","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046835504","display_name":"Ying Sun","orcid":"https://orcid.org/0000-0002-4763-6060"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ying Sun","raw_affiliation_strings":["I2R, A*STAR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"I2R, A*STAR","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056481909","display_name":"Dongkyu Choi","orcid":"https://orcid.org/0000-0001-8239-9825"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dongkyu Choi","raw_affiliation_strings":["IHPC, A*STAR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IHPC, A*STAR","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073326796","display_name":"Cheston Tan","orcid":"https://orcid.org/0000-0003-1248-4906"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Cheston Tan","raw_affiliation_strings":["I2R, A*STAR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"I2R, A*STAR","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077258552","display_name":"Joo\u2010Hwee Lim","orcid":"https://orcid.org/0000-0002-4103-3824"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Joo-Hwee Lim","raw_affiliation_strings":["Nanyang Technological University","I2R, A*STAR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"I2R, A*STAR","institution_ids":["https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2463","last_page":"2467"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9958000183105469,"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":0.9923999905586243,"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/computer-science","display_name":"Computer science","score":0.7396435737609863},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6985417604446411},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.674380362033844},{"id":"https://openalex.org/keywords/analogy","display_name":"Analogy","score":0.6600281596183777},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.608870267868042},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5503338575363159},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5126775503158569},{"id":"https://openalex.org/keywords/analogical-reasoning","display_name":"Analogical reasoning","score":0.49539268016815186},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.4836355447769165},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.47771644592285156},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.4729979634284973},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4664086103439331},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.44168901443481445},{"id":"https://openalex.org/keywords/qualitative-reasoning","display_name":"Qualitative reasoning","score":0.4285426139831543},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4191918671131134},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37190553545951843},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09248757362365723},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08579602837562561}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7396435737609863},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6985417604446411},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.674380362033844},{"id":"https://openalex.org/C521332185","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogy","level":2,"score":0.6600281596183777},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.608870267868042},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5503338575363159},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5126775503158569},{"id":"https://openalex.org/C2985612853","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogical reasoning","level":3,"score":0.49539268016815186},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.4836355447769165},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.47771644592285156},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.4729979634284973},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4664086103439331},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.44168901443481445},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.4285426139831543},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4191918671131134},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37190553545951843},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09248757362365723},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08579602837562561},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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":1,"locations":[{"id":"doi:10.1109/icip42928.2021.9506539","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip42928.2021.9506539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W632224533","https://openalex.org/W1522301498","https://openalex.org/W1927009056","https://openalex.org/W1933349210","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2194775991","https://openalex.org/W2561715562","https://openalex.org/W2891021031","https://openalex.org/W2953388933","https://openalex.org/W2962716332","https://openalex.org/W2963066927","https://openalex.org/W2963383024","https://openalex.org/W2963656855","https://openalex.org/W2963690694","https://openalex.org/W2963954913","https://openalex.org/W2969679616","https://openalex.org/W2981694290","https://openalex.org/W2988981892","https://openalex.org/W2995849700","https://openalex.org/W2995993311","https://openalex.org/W6638444622","https://openalex.org/W6640074256","https://openalex.org/W6674330103","https://openalex.org/W6754944153","https://openalex.org/W6757902542","https://openalex.org/W6768853884","https://openalex.org/W6771918413"],"related_works":["https://openalex.org/W4387158411","https://openalex.org/W2103209360","https://openalex.org/W2186704254","https://openalex.org/W1574950926","https://openalex.org/W4232231986","https://openalex.org/W2240909318","https://openalex.org/W2187663843","https://openalex.org/W123410143","https://openalex.org/W2113245685","https://openalex.org/W2050522312"],"abstract_inverted_index":{"The":[0,160],"deep":[1],"learning":[2],"community":[3],"has":[4],"made":[5],"rapid":[6],"progress":[7],"in":[8,60,88,101],"low-level":[9],"visual":[10,30],"perception":[11],"tasks":[12,22],"such":[13,23],"as":[14,24,68],"object":[15,122],"localization,":[16],"detection":[17],"and":[18,29,45,127,139,146,162],"segmentation.":[19],"However,":[20],"for":[21],"Visual":[25],"Question":[26],"Answering":[27],"(VQA)":[28],"language":[31,95],"grounding":[32],"that":[33,148],"require":[34],"high-level":[35],"reasoning":[36,117,120,156],"abilities,":[37],"huge":[38],"gaps":[39],"still":[40],"exist":[41],"between":[42],"artificial":[43],"systems":[44,150],"human":[46,144],"intelligence.":[47],"In":[48],"this":[49],"work,":[50],"we":[51,103],"perform":[52],"a":[53,72,78,93,113],"diagnostic":[54,107],"study":[55,98],"on":[56,77,121,136],"recent":[57,133],"popular":[58],"VQA":[59],"terms":[61],"of":[62,80,115],"analogical":[63,84,116,155],"reasoning.":[64],"We":[65,130],"term":[66],"it":[67],"Analogical":[69],"VQA,":[70],"where":[71],"system":[73],"needs":[74],"to":[75,82,90,168],"reason":[76],"group":[79],"images":[81],"find":[83],"relations":[85],"among":[86],"them":[87],"order":[89],"correctly":[91],"answer":[92],"natural":[94],"question.":[96],"To":[97],"the":[99,141],"task":[100],"depth,":[102],"propose":[104],"an":[105],"initial":[106],"synthetic":[108],"dataset":[109,138,161],"CLEVR-Analogy,":[110],"which":[111],"tests":[112],"range":[114],"abilities":[118],"(e.g.":[119],"attributes,":[123],"spatial":[124,158],"relationships,":[125],"existence,":[126],"arithmetic":[128],"analogies).":[129],"benchmark":[131],"various":[132],"state-of-the-art":[134],"methods":[135],"our":[137],"compare":[140],"results":[142],"against":[143],"performance,":[145],"discover":[147],"existing":[149],"fall":[151],"shorts":[152],"when":[153],"facing":[154],"involving":[157],"relationships.":[159],"code":[163],"will":[164],"be":[165],"publicly":[166],"available":[167],"facilitate":[169],"future":[170],"research.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}