{"id":"https://openalex.org/W2081369115","doi":"https://doi.org/10.1145/2407746.2407782","title":"Basic level scene understanding","display_name":"Basic level scene understanding","publication_year":2012,"publication_date":"2012-11-28","ids":{"openalex":"https://openalex.org/W2081369115","doi":"https://doi.org/10.1145/2407746.2407782","mag":"2081369115"},"language":"en","primary_location":{"id":"doi:10.1145/2407746.2407782","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2407746.2407782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIGGRAPH Asia 2012 Technical Briefs","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/A5040082544","display_name":"Jianxiong Xiao","orcid":"https://orcid.org/0000-0001-9605-0341"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianxiong Xiao","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053907649","display_name":"Bryan Russell","orcid":"https://orcid.org/0000-0001-8656-543X"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryan C. Russell","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016775802","display_name":"James Hays","orcid":"https://orcid.org/0000-0001-7016-4252"},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Hays","raw_affiliation_strings":["Brown University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084653483","display_name":"Krista A. Ehinger","orcid":"https://orcid.org/0000-0003-2247-3020"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krista A. Ehinger","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021257546","display_name":"Aude Oliva","orcid":"https://orcid.org/0000-0002-6920-914X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aude Oliva","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085020955","display_name":"Antonio Torralba","orcid":"https://orcid.org/0000-0003-4915-0256"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonio Torralba","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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":0.9998000264167786,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9998000264167786,"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":0.787116527557373},{"id":"https://openalex.org/keywords/viewpoints","display_name":"Viewpoints","score":0.6739299893379211},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6240534782409668},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5903216600418091},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5792323350906372},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5184528231620789},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4904486835002899},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4450996220111847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.787116527557373},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.6739299893379211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6240534782409668},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5903216600418091},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5792323350906372},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5184528231620789},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4904486835002899},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4450996220111847},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2407746.2407782","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2407746.2407782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIGGRAPH Asia 2012 Technical Briefs","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[{"id":"https://openalex.org/G5034810420","display_name":null,"funder_award_id":"MURI N000141010933","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G5480122230","display_name":"RI:  Small:  Hierarchical Visual Scene Understanding","funder_award_id":"1016862","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7763882568","display_name":null,"funder_award_id":"747120","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1583341642","https://openalex.org/W1768450320","https://openalex.org/W2009627211","https://openalex.org/W2017814585","https://openalex.org/W2031248101","https://openalex.org/W2047901762","https://openalex.org/W2070148066","https://openalex.org/W2078566374","https://openalex.org/W2090426641","https://openalex.org/W2118824402","https://openalex.org/W2123020895","https://openalex.org/W2160398734","https://openalex.org/W2544953446","https://openalex.org/W3035258717"],"related_works":["https://openalex.org/W2385368906","https://openalex.org/W2902924992","https://openalex.org/W2626642044","https://openalex.org/W2619807045","https://openalex.org/W2114275278","https://openalex.org/W1489511283","https://openalex.org/W2974914859","https://openalex.org/W2026565050","https://openalex.org/W2110244802","https://openalex.org/W949345935"],"abstract_inverted_index":{"An":[0],"early":[1],"goal":[2],"of":[3,42,69,86,104,109,121,127,152,185],"computer":[4],"vision":[5],"was":[6],"to":[7,27,37,81,91,158,180],"build":[8],"a":[9,15,67,93,119,148],"system":[10,179],"that":[11,45],"could":[12],"automatically":[13],"understand":[14],"3D":[16,29,150,183],"scene":[17,75,96,129,187],"just":[18],"by":[19],"looking.":[20],"This":[21,50,77],"requires":[22],"not":[23],"only":[24],"the":[25,39,62,84,107,128,132,141,156,182,186],"ability":[26,157],"extract":[28,181],"information":[30,33],"from":[31],"image":[32],"alone,":[34],"but":[35],"also":[36,101],"handle":[38],"large":[40],"variety":[41,108],"different":[43,74],"environments":[44],"comprise":[46,171],"our":[47,53],"visual":[48],"world.":[49],"paper":[51],"summarizes":[52],"recent":[54],"efforts":[55],"toward":[56,147],"these":[57,112],"goals.":[58],"First,":[59],"we":[60,116,144],"describe":[61,145],"SUN":[63,133],"database,":[64],"which":[65,169],"is":[66],"collection":[68],"annotated":[70],"images":[71,124],"spanning":[72],"908":[73],"categories.":[76],"database":[78,120,134],"allows":[79],"us":[80],"systematically":[82],"study":[83],"space":[85],"possible":[87],"everyday":[88,153,173],"scenes":[89],"and":[90,97,135,167,175,188],"establish":[92],"benchmark":[94],"for":[95,125],"object":[98],"recognition.":[99],"We":[100],"explore":[102],"ways":[103],"coping":[105],"with":[106],"viewpoints":[110],"within":[111,140],"scenes.":[113],"For":[114],"this,":[115],"have":[117,136],"introduced":[118],"360\u00b0":[122],"panoramic":[123],"many":[126,172],"categories":[130],"in":[131,162,191],"explored":[137],"viewpoint":[138],"recognition":[139],"environments.":[142],"Finally,":[143],"steps":[146],"unified":[149],"parsing":[151],"scenes:":[154],"(i)":[155],"localize":[159],"geometric":[160],"primitives":[161],"images,":[163],"such":[164],"as":[165],"cuboids":[166],"cylinders,":[168],"often":[170],"objects,":[174],"(ii)":[176],"an":[177,192],"integrated":[178],"structure":[184],"objects":[189],"depicted":[190],"image.":[193]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}