{"id":"https://openalex.org/W2046589395","doi":"https://doi.org/10.1109/cvpr.2010.5540235","title":"Modeling mutual context of object and human pose in human-object interaction activities","display_name":"Modeling mutual context of object and human pose in human-object interaction activities","publication_year":2010,"publication_date":"2010-06-01","ids":{"openalex":"https://openalex.org/W2046589395","doi":"https://doi.org/10.1109/cvpr.2010.5540235","mag":"2046589395"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2010.5540235","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2010.5540235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE Computer Society 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/A5111952001","display_name":"Bangpeng Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bangpeng Yao","raw_affiliation_strings":["Computer Science Department, University of Stanford, USA","Computer Science Department, Stanford University, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Stanford, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Computer Science Department, Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100450462","display_name":"Li Fei-Fei","orcid":"https://orcid.org/0000-0002-7481-0810"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Fei-Fei","raw_affiliation_strings":["Computer Science Department, University of Stanford, USA","Computer Science Department, Stanford University, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Stanford, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Computer Science Department, Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5111952001"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":49.7805,"has_fulltext":false,"cited_by_count":612,"citation_normalized_percentile":{"value":0.99930452,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"17","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9994999766349792,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9994999766349792,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.992900013923645,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9868000149726868,"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":0.7671468257904053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7173525094985962},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7168738842010498},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6658986806869507},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6304860711097717},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5947183966636658},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5316973924636841},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.47999972105026245},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.47487232089042664},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4341218173503876},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4273010492324829},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3750591278076172},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35862019658088684},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3395170569419861},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06947740912437439},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.061956554651260376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7671468257904053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7173525094985962},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7168738842010498},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6658986806869507},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6304860711097717},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5947183966636658},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5316973924636841},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.47999972105026245},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.47487232089042664},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4341218173503876},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4273010492324829},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3750591278076172},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35862019658088684},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3395170569419861},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06947740912437439},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.061956554651260376},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr.2010.5540235","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2010.5540235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1511986666","https://openalex.org/W1516887802","https://openalex.org/W1528789833","https://openalex.org/W1559083155","https://openalex.org/W2022699039","https://openalex.org/W2022732461","https://openalex.org/W2030536784","https://openalex.org/W2036167211","https://openalex.org/W2050964073","https://openalex.org/W2057175746","https://openalex.org/W2057624533","https://openalex.org/W2081293863","https://openalex.org/W2098355199","https://openalex.org/W2111187045","https://openalex.org/W2113201641","https://openalex.org/W2131263044","https://openalex.org/W2132630629","https://openalex.org/W2141364309","https://openalex.org/W2142037471","https://openalex.org/W2146352414","https://openalex.org/W2157791002","https://openalex.org/W2159564241","https://openalex.org/W2161361693","https://openalex.org/W2161969291","https://openalex.org/W2163292664","https://openalex.org/W2164877691","https://openalex.org/W2169393274","https://openalex.org/W2534457893","https://openalex.org/W2962735828","https://openalex.org/W3004533406","https://openalex.org/W3097096317","https://openalex.org/W4241222664","https://openalex.org/W4285719527","https://openalex.org/W6630825005","https://openalex.org/W6631412525","https://openalex.org/W6633513350","https://openalex.org/W6674646328","https://openalex.org/W6680114966","https://openalex.org/W6680642335","https://openalex.org/W6682953061","https://openalex.org/W6683590607","https://openalex.org/W6683978607"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2114275278","https://openalex.org/W1489511283","https://openalex.org/W2974914859","https://openalex.org/W2026565050","https://openalex.org/W2110244802","https://openalex.org/W2163728705","https://openalex.org/W949345935"],"abstract_inverted_index":{"Detecting":[0],"objects":[1,55,92,173],"in":[2,15,23,96,169],"cluttered":[3],"scenes":[4],"and":[5,43,56,93,124,135,174],"estimating":[6],"articulated":[7],"human":[8,45,57,94,122,175],"body":[9,46,126],"parts":[10,47,127],"are":[11,48,128,141],"two":[12],"challenging":[13],"problems":[14],"computer":[16],"vision.":[17],"The":[18],"difficulty":[19],"is":[20],"particularly":[21],"pronounced":[22],"activities":[24],"involving":[25],"human-object":[26,97,157],"interactions":[27],"(e.g.":[28],"playing":[29],"tennis),":[30],"where":[31],"the":[32,44,71,74,88,103,114,118,120,136,139],"relevant":[33],"object":[34],"tends":[35],"to":[36,64,86],"be":[37],"small":[38],"or":[39],"only":[40],"partially":[41],"visible,":[42],"often":[49],"self-occluded.":[50],"We":[51,100],"observe,":[52],"however,":[53],"that":[54,161],"poses":[58,95],"can":[59],"serve":[60],"as":[61,107],"mutual":[62,89,163],"context":[63,90,164],"each":[65],"other":[66],"-":[67],"recognizing":[68],"one":[69],"facilitates":[70],"recognition":[72],"of":[73,91,112,138,153,156],"other.":[75],"In":[76],"this":[77],"paper":[78],"we":[79,159],"propose":[80],"a":[81,108,131,144,149],"new":[82,145],"random":[83],"field":[84],"model":[85,104,140,165],"encode":[87],"interaction":[98],"activities.":[99],"then":[101],"cast":[102],"learning":[105,110],"task":[106],"structure":[109,132],"problem,":[111],"which":[113],"structural":[115],"connectivity":[116],"between":[117],"object,":[119],"overall":[121],"pose,":[123],"different":[125],"estimated":[129,142],"through":[130],"search":[133],"approach,":[134],"parameters":[137],"by":[143],"max-margin":[146],"algorithm.":[147],"On":[148],"sports":[150],"data":[151],"set":[152],"six":[154],"classes":[155],"interactions,":[158],"show":[160],"our":[162],"significantly":[166],"outperforms":[167],"state-of-the-art":[168],"detecting":[170],"very":[171],"difficult":[172],"poses.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":45},{"year":2020,"cited_by_count":48},{"year":2019,"cited_by_count":44},{"year":2018,"cited_by_count":61},{"year":2017,"cited_by_count":44},{"year":2016,"cited_by_count":46},{"year":2015,"cited_by_count":60},{"year":2014,"cited_by_count":49},{"year":2013,"cited_by_count":43},{"year":2012,"cited_by_count":48}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}