{"id":"https://openalex.org/W2142650037","doi":"https://doi.org/10.1109/cvpr.2012.6247996","title":"Automatic discovery of groups of objects for scene understanding","display_name":"Automatic discovery of groups of objects for scene understanding","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W2142650037","doi":"https://doi.org/10.1109/cvpr.2012.6247996","mag":"2142650037"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2012.6247996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2012.6247996","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"},"type":"article","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/A5100332237","display_name":"Congcong Li","orcid":"https://orcid.org/0000-0002-1080-4331"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Congcong Li","raw_affiliation_strings":["Cornell University, USA","Cornell University"],"affiliations":[{"raw_affiliation_string":"Cornell University, USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050342343","display_name":"Devi Parikh","orcid":null},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]},{"id":"https://openalex.org/I4840577","display_name":"Toyota Technological Institute","ror":"https://ror.org/001hv0k59","country_code":"JP","type":"education","lineage":["https://openalex.org/I4840577"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"D. Parikh","raw_affiliation_strings":["Toyota Technological Institute, Chicago (TTIC), USA","Toyota Technological Institute (Chicago)#TAB#"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute, Chicago (TTIC), USA","institution_ids":["https://openalex.org/I160992636"]},{"raw_affiliation_string":"Toyota Technological Institute (Chicago)#TAB#","institution_ids":["https://openalex.org/I4840577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000454484","display_name":"Tsuhan Chen","orcid":"https://orcid.org/0000-0003-3951-7931"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tsuhan Chen","raw_affiliation_strings":["Cornell University, USA","Cornell University"],"affiliations":[{"raw_affiliation_string":"Cornell University, USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100332237"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":10.5528,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.98680943,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2735","last_page":"2742"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.7815508246421814},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7345250844955444},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6779022812843323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6754416227340698},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5331961512565613},{"id":"https://openalex.org/keywords/scene-statistics","display_name":"Scene statistics","score":0.5218355059623718},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5174322724342346},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5068038105964661},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.48954471945762634},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36557942628860474},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.12180894613265991},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08971673250198364},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.07340869307518005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7815508246421814},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7345250844955444},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6779022812843323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6754416227340698},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5331961512565613},{"id":"https://openalex.org/C197654239","wikidata":"https://www.wikidata.org/wiki/Q7430757","display_name":"Scene statistics","level":3,"score":0.5218355059623718},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5174322724342346},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5068038105964661},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.48954471945762634},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36557942628860474},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.12180894613265991},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08971673250198364},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07340869307518005},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cvpr.2012.6247996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2012.6247996","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/146132","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/146132","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus","raw_type":"Conference Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.650.3200","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.650.3200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://chenlab.ece.cornell.edu/people/congcong/publications/CVPR2012_ObjectGroup.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.662.1227","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.662.1227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://filebox.ece.vt.edu/%7Eparikh/Publications/LiParikhChen_CVPR_2012_groups_of_objects.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1566135517","https://openalex.org/W1982522767","https://openalex.org/W2010132303","https://openalex.org/W2046589395","https://openalex.org/W2048088055","https://openalex.org/W2049705550","https://openalex.org/W2077493928","https://openalex.org/W2081293863","https://openalex.org/W2099528205","https://openalex.org/W2106097867","https://openalex.org/W2110306668","https://openalex.org/W2112301665","https://openalex.org/W2119474464","https://openalex.org/W2121043743","https://openalex.org/W2128962821","https://openalex.org/W2134665698","https://openalex.org/W2137971795","https://openalex.org/W2141364309","https://openalex.org/W2142037471","https://openalex.org/W2144526807","https://openalex.org/W2152161678","https://openalex.org/W2158309968","https://openalex.org/W2158911526","https://openalex.org/W2160254296","https://openalex.org/W2162915993","https://openalex.org/W2168356304","https://openalex.org/W2186094539","https://openalex.org/W4238003328","https://openalex.org/W6681485143","https://openalex.org/W6683089593"],"related_works":["https://openalex.org/W2109586375","https://openalex.org/W2115592544","https://openalex.org/W2093773434","https://openalex.org/W1986440968","https://openalex.org/W2071302177","https://openalex.org/W4311804456","https://openalex.org/W4365135359","https://openalex.org/W2168616527","https://openalex.org/W2573606541","https://openalex.org/W2582543502"],"abstract_inverted_index":{"Objects":[0],"in":[1,7,23,116,136],"scenes":[2],"interact":[3],"with":[4,79,161],"each":[5,80],"other":[6,114],"complex":[8],"ways.":[9],"A":[10],"key":[11],"observation":[12],"is":[13,32,120],"that":[14,71,145,207],"these":[15,29],"interactions":[16,78],"manifest":[17],"themselves":[18],"as":[19,50,53],"predictable":[20],"visual":[21,138],"patterns":[22,31],"the":[24,48,54,95,103,110,117,189,195,215],"image.":[25],"Discovering":[26],"and":[27,76,106,174,176,220],"detecting":[28],"structured":[30],"an":[33,143],"important":[34],"step":[35],"towards":[36],"deeper":[37],"scene":[38,49,104,221],"understanding.":[39],"It":[40,119],"goes":[41],"beyond":[42],"using":[43,194,208],"either":[44],"individual":[45],"objects":[46,70,85,115,133,154,183,193,211],"or":[47],"a":[51,91,126,156,167,202],"whole":[52],"semantic":[55],"unit.":[56],"In":[57],"this":[58],"work,":[59],"we":[60,134,141],"promote":[61],"\"groups":[62],"of":[63,69,84,94,113,128,132,149,152,158,171,182,192,204,210,217],"objects\".":[64],"They":[65,97],"are":[66,86],"high-order":[67],"composites":[68],"demonstrate":[72],"consistent":[73],"spatial,":[74],"scale,":[75],"viewpoint":[77],"other.":[81],"These":[82],"groups":[83,148,191,209],"likely":[87,111],"to":[88,90,123],"correspond":[89],"specific":[92],"layout":[93],"scene.":[96,118],"can":[98,107,212],"thus":[99],"provide":[100],"cues":[101],"for":[102],"category":[105],"also":[108],"prime":[109],"locations":[112],"not":[121],"feasible":[122],"manually":[124],"generate":[125],"list":[127],"all":[129,179],"possible":[130],"groupings":[131],"find":[135],"our":[137],"world.":[139],"Hence,":[140],"propose":[142],"algorithm":[144],"automatically":[146],"discovers":[147],"arbitrary":[150],"numbers":[151],"participating":[153],"from":[155],"collection":[157],"images":[159],"labeled":[160],"object":[162,218],"categories.":[163],"Our":[164,199],"approach":[165],"builds":[166],"4-dimensional":[168],"transform":[169],"space":[170],"location,":[172],"scale":[173],"viewpoint,":[175],"efficiently":[177],"identifies":[178],"recurring":[180],"compositions":[181],"across":[184],"images.":[185],"We":[186],"then":[187],"model":[188],"discovered":[190],"deformable":[196],"parts-based":[197],"model.":[198],"experiments":[200],"on":[201],"variety":[203],"datasets":[205],"show":[206],"significantly":[213],"boost":[214],"performance":[216],"detection":[219],"categorization.":[222]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":16}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}