{"id":"https://openalex.org/W2071730211","doi":"https://doi.org/10.1145/2502081.2502089","title":"Learning latent spatio-temporal compositional model for human action recognition","display_name":"Learning latent spatio-temporal compositional model for human action recognition","publication_year":2013,"publication_date":"2013-10-21","ids":{"openalex":"https://openalex.org/W2071730211","doi":"https://doi.org/10.1145/2502081.2502089","mag":"2071730211"},"language":"en","primary_location":{"id":"doi:10.1145/2502081.2502089","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2502081.2502089","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1502.00258","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xiaodan Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodan Liang","raw_affiliation_strings":["Sun Yat-Sen University, GuangZhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University, GuangZhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Lin","raw_affiliation_strings":["Sun Yat-Sen University, GuangZhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University, GuangZhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":null,"display_name":"Liangliang Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liangliang Cao","raw_affiliation_strings":["IBM Research, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, New York, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"263","last_page":"272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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/T10812","display_name":"Human Pose and Action Recognition","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987000226974487,"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":0.9811000227928162,"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/action","display_name":"Action (physics)","score":0.6207000017166138},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5127999782562256},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5076000094413757},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.48249998688697815},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.47909998893737793},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.39419999718666077},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3312000036239624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7504000067710876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6444000005722046},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6207000017166138},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5127999782562256},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5076000094413757},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.48249998688697815},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47909998893737793},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41029998660087585},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.39419999718666077},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.2944999933242798},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2937000095844269},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2815000116825104},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2574000060558319},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2502081.2502089","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2502081.2502089","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM international conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1502.00258","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1502.00258","pdf_url":"https://arxiv.org/pdf/1502.00258","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1502.00258","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1502.00258","pdf_url":"https://arxiv.org/pdf/1502.00258","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W7859433","https://openalex.org/W1211924006","https://openalex.org/W1979246310","https://openalex.org/W1994205671","https://openalex.org/W1996343625","https://openalex.org/W2002585172","https://openalex.org/W2012045439","https://openalex.org/W2020163092","https://openalex.org/W2027081450","https://openalex.org/W2052487339","https://openalex.org/W2061685007","https://openalex.org/W2073190439","https://openalex.org/W2081314772","https://openalex.org/W2097342496","https://openalex.org/W2100916003","https://openalex.org/W2104128303","https://openalex.org/W2108333036","https://openalex.org/W2111645492","https://openalex.org/W2114361838","https://openalex.org/W2123477621","https://openalex.org/W2126574503","https://openalex.org/W2128158057","https://openalex.org/W2137275576","https://openalex.org/W2139117248","https://openalex.org/W2142194269","https://openalex.org/W2144761450","https://openalex.org/W2161029186","https://openalex.org/W2162670331","https://openalex.org/W2163292664","https://openalex.org/W2166765763","https://openalex.org/W2168356304","https://openalex.org/W2169255714","https://openalex.org/W2171274443","https://openalex.org/W2171544105","https://openalex.org/W2533503513","https://openalex.org/W2533739470","https://openalex.org/W2547062449","https://openalex.org/W3106138329","https://openalex.org/W4205969993","https://openalex.org/W4246695531"],"related_works":[],"abstract_inverted_index":{"Action":[0],"recognition":[1],"is":[2,45],"an":[3,16,30,121],"important":[4],"problem":[5,13],"in":[6,26,91,149],"multimedia":[7],"understanding.":[8],"This":[9],"paper":[10],"addresses":[11],"this":[12,55],"by":[14],"building":[15],"expressive":[17],"compositional":[18],"action":[19,24,96,201],"model.":[20],"We":[21],"model":[22,58,82,156],"one":[23],"instance":[25],"the":[27,68,102,118,130,142,169,173,179,183,214],"video":[28,99],"with":[29,178,182],"ensemble":[31],"of":[32,37,43,51,71,89,175,185,220],"spatio-temporal":[33,191,208],"compositions:":[34],"a":[35,49,61,87,160],"number":[36],"discrete":[38],"temporal":[39,138,153],"anchor":[40,122,139],"frames,":[41],"each":[42],"which":[44,166],"further":[46],"decomposed":[47],"to":[48,66,109],"layout":[50],"deformable":[52],"parts.":[53],"In":[54],"way,":[56],"our":[57,195,221],"can":[59],"identify":[60],"Spatio-Temporal":[62],"And-Or":[63],"Graph":[64],"(STAOG)":[65],"represent":[67],"latent":[69],"structure":[70],"actions":[72],"\\emph{e.g.}":[73],"triple":[74],"jumping,":[75],"swinging":[76],"and":[77,128,152,193],"high":[78],"jumping.":[79],"The":[80,210],"STAOG":[81],"comprises":[83],"four":[84],"layers:":[85],"(i)":[86],"batch":[88],"leaf-nodes":[90,113,148,176],"bottom":[92],"for":[93,114,124,134],"detecting":[94],"various":[95],"parts":[97],"within":[98,120],"patches;":[100],"(ii)":[101],"or-nodes":[103],"over":[104,137,223],"bottom,":[105],"i.e.":[106],"switch":[107],"variables":[108],"activate":[110],"their":[111],"children":[112],"structural":[115,170],"variability;":[116],"(iii)":[117],"and-nodes":[119],"frame":[123],"verifying":[125],"spatial":[126,151],"composition;":[127],"(iv)":[129],"root-node":[131],"at":[132],"top":[133],"aggregating":[135],"scores":[136],"frames.":[140],"Moreover,":[141],"contextual":[143],"interactions":[144],"are":[145],"defined":[146],"between":[147],"both":[150],"domains.":[154],"For":[155],"training,":[157],"we":[158],"develop":[159],"novel":[161],"weakly":[162],"supervised":[163],"learning":[164],"algorithm":[165],"iteratively":[167],"determines":[168],"configuration":[171],"(e.g.":[172],"production":[174],"associated":[177],"or-nodes)":[180],"along":[181],"optimization":[184],"multi-layer":[186],"parameters.":[187],"By":[188],"fully":[189],"exploiting":[190],"compositions":[192],"interactions,":[194],"approach":[196,222],"handles":[197],"well":[198],"large":[199],"intra-class":[200],"variance":[202],"(\\emph{e.g.}":[203],"different":[204],"views,":[205],"individual":[206],"appearances,":[207],"structures).":[209],"experimental":[211],"results":[212],"on":[213],"challenging":[215],"databases":[216],"demonstrate":[217],"superior":[218],"performance":[219],"other":[224],"methods.":[225]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2016-06-24T00:00:00"}