{"id":"https://openalex.org/W2050964073","doi":"https://doi.org/10.1109/cvpr.2010.5540234","title":"Grouplet: A structured image representation for recognizing human and object interactions","display_name":"Grouplet: A structured image representation for recognizing human and object interactions","publication_year":2010,"publication_date":"2010-06-01","ids":{"openalex":"https://openalex.org/W2050964073","doi":"https://doi.org/10.1109/cvpr.2010.5540234","mag":"2050964073"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2010.5540234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2010.5540234","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":23.2757,"has_fulltext":false,"cited_by_count":338,"citation_normalized_percentile":{"value":0.99660455,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"9","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9995999932289124,"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":0.9995999932289124,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9958999752998352,"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":0.9950000047683716,"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":0.7476198673248291},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7291954159736633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.723290741443634},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6968051791191101},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6357987523078918},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6114434003829956},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5835500955581665},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5709699392318726},{"id":"https://openalex.org/keywords/violin","display_name":"Violin","score":0.5361815094947815},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4904589354991913},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44797438383102417}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7476198673248291},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7291954159736633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.723290741443634},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6968051791191101},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6357987523078918},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6114434003829956},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5835500955581665},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5709699392318726},{"id":"https://openalex.org/C129554576","wikidata":"https://www.wikidata.org/wiki/Q8355","display_name":"Violin","level":2,"score":0.5361815094947815},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4904589354991913},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44797438383102417},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr.2010.5540234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2010.5540234","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":[{"id":"https://metadata.un.org/sdg/10","score":0.7799999713897705,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1484413656","https://openalex.org/W1566135517","https://openalex.org/W1973176103","https://openalex.org/W2030536784","https://openalex.org/W2042316011","https://openalex.org/W2046589395","https://openalex.org/W2097912557","https://openalex.org/W2099930951","https://openalex.org/W2103658758","https://openalex.org/W2104978738","https://openalex.org/W2106833577","https://openalex.org/W2120419212","https://openalex.org/W2124372976","https://openalex.org/W2124386111","https://openalex.org/W2132630629","https://openalex.org/W2143900868","https://openalex.org/W2154422044","https://openalex.org/W2155904486","https://openalex.org/W2155979701","https://openalex.org/W2162915993","https://openalex.org/W2165095705","https://openalex.org/W2165828254","https://openalex.org/W2166049352","https://openalex.org/W2168002178","https://openalex.org/W2169393274","https://openalex.org/W2169696215","https://openalex.org/W2170146448","https://openalex.org/W2170238270","https://openalex.org/W2535410496","https://openalex.org/W4205398292","https://openalex.org/W4205474846","https://openalex.org/W6628750762","https://openalex.org/W6661056839","https://openalex.org/W6680114966","https://openalex.org/W6684963293","https://openalex.org/W6685502933"],"related_works":["https://openalex.org/W3005665219","https://openalex.org/W2377398662","https://openalex.org/W2022759485","https://openalex.org/W656498565","https://openalex.org/W2036805226","https://openalex.org/W639295560","https://openalex.org/W2371135719","https://openalex.org/W2046037681","https://openalex.org/W2614360952","https://openalex.org/W2897639213"],"abstract_inverted_index":{"Psychologists":[0],"have":[1],"proposed":[2],"that":[3,63,134],"many":[4,19],"human-object":[5,143],"interaction":[6],"activities":[7],"form":[8],"unique":[9],"classes":[10],"of":[11,56,69,109,116,127],"scenes.":[12,67],"Recognizing":[13],"these":[14,65],"scenes":[15],"is":[16,29],"important":[17],"for":[18,87],"social":[20],"functions.":[21],"To":[22],"enable":[23],"a":[24,31,42,47,51,96,114,125,155],"computer":[25],"to":[26,40],"do":[27],"this":[28,89,92],"however":[30],"challenging":[32],"task.":[33,90],"Take":[34],"people-playing-musical-instrument":[35],"(PPMI)":[36],"as":[37],"an":[38,110],"example;":[39],"distinguish":[41],"person":[43,48],"playing":[44,160],"violin":[45,52],"from":[46],"just":[49],"holding":[50],"requires":[53],"subtle":[54],"distinction":[55,157],"characteristic":[57],"image":[58,72,98,111],"features":[59,119],"and":[60,120,141,163],"feature":[61,99],"arrangements":[62],"differentiate":[64],"two":[66],"Most":[68],"the":[70,106,161,167],"existing":[71],"representation":[73,100],"methods":[74],"are":[75,136],"either":[76],"too":[77,82],"coarse":[78],"(e.g.":[79,84],"BoW)":[80],"or":[81],"sparse":[83],"constellation":[85],"models)":[86],"performing":[88],"In":[91,149],"paper,":[93],"we":[94,132],"propose":[95],"new":[97],"called":[101],"\u201cgrouplet\u201d.":[102],"The":[103],"grouplet":[104],"captures":[105],"structured":[107],"information":[108],"by":[112],"encoding":[113],"number":[115],"discriminative":[117],"visual":[118],"their":[121],"spatial":[122],"configurations.":[123],"Using":[124],"dataset":[126],"7":[128],"different":[129],"PPMI":[130],"activities,":[131],"show":[133],"grouplets":[135],"more":[137],"effective":[138],"in":[139],"classifying":[140],"detecting":[142],"interactions":[144],"than":[145],"other":[146],"state-of-the-art":[147],"methods.":[148],"particular,":[150],"our":[151],"method":[152],"can":[153],"make":[154],"robust":[156],"between":[158],"humans":[159,164],"instruments":[162,168],"co-occurring":[165],"with":[166],"without":[169],"playing.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":23},{"year":2017,"cited_by_count":33},{"year":2016,"cited_by_count":44},{"year":2015,"cited_by_count":38},{"year":2014,"cited_by_count":27},{"year":2013,"cited_by_count":27},{"year":2012,"cited_by_count":19}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
