{"id":"https://openalex.org/W4366351904","doi":"https://doi.org/10.1109/tpami.2023.3268093","title":"Visual Reasoning: From State to Transformation","display_name":"Visual Reasoning: From State to Transformation","publication_year":2023,"publication_date":"2023-04-19","ids":{"openalex":"https://openalex.org/W4366351904","doi":"https://doi.org/10.1109/tpami.2023.3268093","pmid":"https://pubmed.ncbi.nlm.nih.gov/37074901"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3268093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3268093","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.01668","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100714795","display_name":"Xin Hong","orcid":"https://orcid.org/0000-0003-1524-9362"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Hong","raw_affiliation_strings":["CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China","CAS Key Lab of Network Data Science and Technology , Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1524-9362","affiliations":[{"raw_affiliation_string":"CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"CAS Key Lab of Network Data Science and Technology , Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101616866","display_name":"Yanyan Lan","orcid":"https://orcid.org/0000-0002-7811-3262"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyan Lan","raw_affiliation_strings":["Institute of AI Industrial Research, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7811-3262","affiliations":[{"raw_affiliation_string":"Institute of AI Industrial Research, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004759804","display_name":"Liang Pang","orcid":"https://orcid.org/0000-0003-1161-8546"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Pang","raw_affiliation_strings":["Data Intelligence System Research Center, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1161-8546","affiliations":[{"raw_affiliation_string":"Data Intelligence System Research Center, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088621320","display_name":"Jiafeng Guo","orcid":"https://orcid.org/0000-0002-9509-8674"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiafeng Guo","raw_affiliation_strings":["CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China","CAS Key Lab of Network Data Science and Technology , Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9509-8674","affiliations":[{"raw_affiliation_string":"CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"CAS Key Lab of Network Data Science and Technology , Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029998682","display_name":"Xueqi Cheng","orcid":"https://orcid.org/0000-0002-5201-8195"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqi Cheng","raw_affiliation_strings":["CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China","CAS Key Lab of Network Data Science and Technology , Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5201-8195","affiliations":[{"raw_affiliation_string":"CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"CAS Key Lab of Network Data Science and Technology , Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5318,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.65134528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"45","issue":"9","first_page":"11352","last_page":"11364"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9921000003814697,"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":0.9882000088691711,"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-reasoning","display_name":"Visual reasoning","score":0.7706656455993652},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7242711186408997},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.708829402923584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6076642870903015},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4492649734020233},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3476727306842804},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.343085914850235}],"concepts":[{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.7706656455993652},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7242711186408997},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.708829402923584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6076642870903015},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4492649734020233},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3476727306842804},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.343085914850235},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2023.3268093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3268093","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:37074901","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37074901","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:2305.01668","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.01668","pdf_url":"https://arxiv.org/pdf/2305.01668","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":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.01668","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.01668","pdf_url":"https://arxiv.org/pdf/2305.01668","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":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G779182229","display_name":null,"funder_award_id":"2022YFB3103704","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G986537704","display_name":null,"funder_award_id":"62276248","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W625018418","https://openalex.org/W1517415198","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1917989004","https://openalex.org/W1933349210","https://openalex.org/W1948251820","https://openalex.org/W1967686239","https://openalex.org/W1999215561","https://openalex.org/W2016589492","https://openalex.org/W2104657103","https://openalex.org/W2119717200","https://openalex.org/W2157331557","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2507009361","https://openalex.org/W2560730294","https://openalex.org/W2561715562","https://openalex.org/W2563717578","https://openalex.org/W2594270457","https://openalex.org/W2741631785","https://openalex.org/W2777926144","https://openalex.org/W2889167066","https://openalex.org/W2907143950","https://openalex.org/W2908510526","https://openalex.org/W2912371042","https://openalex.org/W2938232066","https://openalex.org/W2947312908","https://openalex.org/W2950635152","https://openalex.org/W2962716332","https://openalex.org/W2962749469","https://openalex.org/W2963115613","https://openalex.org/W2963518342","https://openalex.org/W2963530300","https://openalex.org/W2963890019","https://openalex.org/W2964094654","https://openalex.org/W2964303913","https://openalex.org/W2975545243","https://openalex.org/W2981774933","https://openalex.org/W2988981892","https://openalex.org/W2995993311","https://openalex.org/W3016211260","https://openalex.org/W3035084814","https://openalex.org/W3087871082","https://openalex.org/W3094502228","https://openalex.org/W3097683561","https://openalex.org/W3102616566","https://openalex.org/W3106768499","https://openalex.org/W3166396011","https://openalex.org/W3175939205","https://openalex.org/W4230563027","https://openalex.org/W4239181501","https://openalex.org/W4246119453","https://openalex.org/W4288093753","https://openalex.org/W4288262262","https://openalex.org/W4289243726","https://openalex.org/W4295312788","https://openalex.org/W4297749157","https://openalex.org/W4306982992","https://openalex.org/W4385245566","https://openalex.org/W6748270630","https://openalex.org/W6756398402","https://openalex.org/W6758704467","https://openalex.org/W6766895606","https://openalex.org/W6768276658","https://openalex.org/W6768853884","https://openalex.org/W6769024994","https://openalex.org/W6784333009","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W2353644209","https://openalex.org/W2961085424","https://openalex.org/W2593663830","https://openalex.org/W2348743188","https://openalex.org/W2902317490","https://openalex.org/W4387423451","https://openalex.org/W2025460258","https://openalex.org/W2056619254","https://openalex.org/W2046628353","https://openalex.org/W4224009465"],"abstract_inverted_index":{"Most":[0],"existing":[1],"visual":[2,38,76,184,215],"reasoning":[3,39,77,160,185],"tasks,":[4],"such":[5],"as":[6],"CLEVR":[7],"in":[8,42,63,227],"VQA,":[9],"ignore":[10],"an":[11],"important":[12,59],"factor,":[13],"i.e.,":[14,118],"transformation.":[15,95],"They":[16],"are":[17,192],"solely":[18],"defined":[19],"to":[20,46,56,90,143,169,224],"test":[21,170],"how":[22,171],"well":[23,188],"machines":[24],"understand":[25],"concepts":[26],"and":[27,84,125,167,201,220],"relations":[28],"within":[29],"static":[30],"settings,":[31,117],"like":[32],"one":[33],"image.":[34],"Such":[35],"state":[36],"driven":[37,75],"has":[40,54],"limitations":[41],"reflecting":[43],"the":[44,48,82,87,92,109,145,182,205,211],"ability":[45],"infer":[47,91],"dynamics":[49],"between":[50],"different":[51],"states,":[52,86],"which":[53],"shown":[55],"be":[57,225],"equally":[58],"for":[60],"human":[61,154],"cognition":[62],"Piaget's":[64],"theory.":[65],"To":[66],"tackle":[67],"this":[68,97,228],"problem,":[69],"we":[70,133,156],"propose":[71,157],"a":[72,99,158],"novel":[73],"transformation":[74,128,148],"(TVR)":[78],"task.":[79],"Given":[80],"both":[81],"initial":[83],"final":[85],"target":[88],"becomes":[89],"corresponding":[93],"intermediate":[94],"Following":[96],"definition,":[98],"new":[100,207,221],"synthetic":[101],"dataset":[102,137],"namely":[103],"TRANCE":[104],"is":[105],"first":[106],"constructed":[107],"on":[108,141,150,176,189,198],"basis":[110],"of":[111,116,147,213],"CLEVR,":[112],"including":[113,164],"three":[114],"levels":[115],"Basic":[119],"(single-step":[120],"transformation),":[121,124],"Event":[122],"(multi-step":[123,127],"View":[126],"with":[129],"variant":[130],"views).":[131],"Next,":[132],"build":[134],"another":[135],"real":[136],"called":[138,162],"TRANCO":[139],"based":[140],"COIN,":[142],"cover":[144],"loss":[146],"diversity":[149],"TRANCE.":[151],"Inspired":[152],"by":[153],"reasoning,":[155],"three-staged":[159],"framework":[161],"TranNet,":[163],"observing,":[165],"analyzing,":[166],"concluding,":[168],"recent":[172],"advanced":[173,218],"techniques":[174],"perform":[175,187],"TVR.":[177],"Experimental":[178],"results":[179],"show":[180],"that":[181],"state-of-the-art":[183],"models":[186],"Basic,":[190],"but":[191],"still":[193],"far":[194],"from":[195],"human-level":[196],"intelligence":[197],"Event,":[199],"View,":[200],"TRANCO.":[202],"We":[203],"believe":[204],"proposed":[206],"paradigm":[208],"will":[209],"boost":[210],"development":[212],"machine":[214],"reasoning.":[216],"More":[217],"methods":[219],"problems":[222],"need":[223],"investigated":[226],"direction.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}