{"id":"https://openalex.org/W2137881638","doi":"https://doi.org/10.1109/cvpr.2012.6247739","title":"Describing the scene as a whole: Joint object detection, scene classification and semantic segmentation","display_name":"Describing the scene as a whole: Joint object detection, scene classification and semantic segmentation","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W2137881638","doi":"https://doi.org/10.1109/cvpr.2012.6247739","mag":"2137881638"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2012.6247739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2012.6247739","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/A5011274467","display_name":"Jian Yao","orcid":"https://orcid.org/0000-0002-9134-5084"},"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"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jian Yao","raw_affiliation_strings":["TTI-Chicago, USA","TTI Chicago"],"affiliations":[{"raw_affiliation_string":"TTI-Chicago, USA","institution_ids":["https://openalex.org/I160992636"]},{"raw_affiliation_string":"TTI Chicago","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070642269","display_name":"Sanja Fidler","orcid":"https://orcid.org/0000-0003-1040-3260"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"S. Fidler","raw_affiliation_strings":["University of Toronto, Canada","University of Toronto"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058557954","display_name":"Raquel Urtasun","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. Urtasun","raw_affiliation_strings":["TTI-Chicago, USA","TTI Chicago"],"affiliations":[{"raw_affiliation_string":"TTI-Chicago, USA","institution_ids":["https://openalex.org/I160992636"]},{"raw_affiliation_string":"TTI Chicago","institution_ids":["https://openalex.org/I160992636"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011274467"],"corresponding_institution_ids":["https://openalex.org/I160992636"],"apc_list":null,"apc_paid":null,"fwci":30.8095,"has_fulltext":false,"cited_by_count":391,"citation_normalized_percentile":{"value":0.99771599,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"702","last_page":"709"},"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/T10036","display_name":"Advanced Neural Network 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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9995999932289124,"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/inference","display_name":"Inference","score":0.8426790237426758},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8043071627616882},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.7106838226318359},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6529363393783569},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5907273292541504},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5884660482406616},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5883898735046387},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5542888045310974},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5288953185081482},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5277450680732727},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5161965489387512},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.44095516204833984},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4129640460014343},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.25759780406951904}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8426790237426758},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8043071627616882},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7106838226318359},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6529363393783569},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5907273292541504},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5884660482406616},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5883898735046387},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5542888045310974},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5288953185081482},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5277450680732727},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5161965489387512},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.44095516204833984},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4129640460014343},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25759780406951904},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cvpr.2012.6247739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2012.6247739","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:CiteSeerX.psu:10.1.1.296.8555","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.296.8555","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ttic.uchicago.edu/~rurtasun/publications/yao_et_al_cvpr12.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.305.1516","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.305.1516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ttic.uchicago.edu/~yaojian/Paper_Holistic.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W59895198","https://openalex.org/W1479789543","https://openalex.org/W1610707153","https://openalex.org/W1748750709","https://openalex.org/W1994259434","https://openalex.org/W2009685382","https://openalex.org/W2017814585","https://openalex.org/W2031489346","https://openalex.org/W2055349880","https://openalex.org/W2061202859","https://openalex.org/W2079937789","https://openalex.org/W2100588357","https://openalex.org/W2103897297","https://openalex.org/W2107640784","https://openalex.org/W2110158442","https://openalex.org/W2111161343","https://openalex.org/W2116445618","https://openalex.org/W2128680590","https://openalex.org/W2128962821","https://openalex.org/W2145567954","https://openalex.org/W2149698896","https://openalex.org/W2152513128","https://openalex.org/W2161236525","https://openalex.org/W2162820221","https://openalex.org/W2163166770","https://openalex.org/W2163766261","https://openalex.org/W2168356304","https://openalex.org/W2533218643","https://openalex.org/W2952793010","https://openalex.org/W4230931186","https://openalex.org/W6628729794","https://openalex.org/W6636212864","https://openalex.org/W6637730771","https://openalex.org/W6676328599","https://openalex.org/W6676664992","https://openalex.org/W6677695560","https://openalex.org/W6682110070","https://openalex.org/W6940791371","https://openalex.org/W6996185213"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2487162673","https://openalex.org/W2378211422","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W2988126442","https://openalex.org/W4287991909"],"abstract_inverted_index":{"In":[0],"this":[1,107],"paper":[2],"we":[3,45,135],"propose":[4],"an":[5],"approach":[6,141],"to":[7,58,115,128,159],"holistic":[8,155],"scene":[9,34],"understanding":[10],"that":[11,55],"reasons":[12],"jointly":[13],"about":[14,122],"regions,":[15],"location,":[16],"class":[17,26],"and":[18,37,51,98,119],"spatial":[19],"extent":[20],"of":[21,24,74,80],"objects,":[22],"presence":[23],"a":[25,68,86,137],"in":[27,39,162],"the":[28,33,48,60,78,123,126,130,143,146],"image,":[29],"as":[30,32,44,111],"well":[31],"type.":[35],"Learning":[36],"inference":[38,131],"our":[40,117,154],"model":[41,156],"are":[42],"efficient":[43],"reason":[46],"at":[47],"segment":[49],"level,":[50],"introduce":[52,136],"auxiliary":[53],"variables":[54,70],"allow":[56],"us":[57,114],"decompose":[59],"inherent":[61],"high-order":[62],"potentials":[63,66],"into":[64],"pairwise":[65],"between":[67],"few":[69],"with":[71],"small":[72],"number":[73,79],"states":[75],"(at":[76],"most":[77],"classes).":[81],"Inference":[82],"is":[83,108,157],"done":[84],"via":[85],"convergent":[87],"message-passing":[88],"algorithm,":[89],"which,":[90],"unlike":[91],"graph-cuts":[92],"inference,":[93],"has":[94],"no":[95],"submodularity":[96],"restrictions":[97],"does":[99],"not":[100],"require":[101],"potential":[102],"specific":[103],"moves.":[104],"We":[105],"believe":[106],"very":[109],"important,":[110],"it":[112],"allows":[113],"encode":[116],"ideas":[118],"prior":[120],"knowledge":[121],"problem":[124],"without":[125],"need":[127],"change":[129],"engine":[132],"every":[133],"time":[134],"new":[138],"potential.":[139],"Our":[140],"outperforms":[142],"state-of-the-art":[144],"on":[145],"MSRC-21":[147],"benchmark,":[148],"while":[149],"being":[150],"much":[151],"faster.":[152],"Importantly,":[153],"able":[158],"improve":[160],"performance":[161],"all":[163],"tasks.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":28},{"year":2019,"cited_by_count":50},{"year":2018,"cited_by_count":41},{"year":2017,"cited_by_count":41},{"year":2016,"cited_by_count":54},{"year":2015,"cited_by_count":61},{"year":2014,"cited_by_count":34},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}