{"id":"https://openalex.org/W1912967058","doi":"https://doi.org/10.1109/cvpr.2015.7298734","title":"Joint action recognition and pose estimation from video","display_name":"Joint action recognition and pose estimation from video","publication_year":2015,"publication_date":"2015-06-01","ids":{"openalex":"https://openalex.org/W1912967058","doi":"https://doi.org/10.1109/cvpr.2015.7298734","mag":"1912967058"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2015.7298734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2015.7298734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5005610577","display_name":"Bruce Xiaohan Nie","orcid":"https://orcid.org/0000-0002-2814-0369"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bruce Xiaohan Nie","raw_affiliation_strings":["Center for Vision, Cognition, Learning and Art, University of Californie, Los Angeles, USA","Center for Vision, Cognition, Learning and Art, University of California, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"Center for Vision, Cognition, Learning and Art, University of Californie, Los Angeles, USA","institution_ids":[]},{"raw_affiliation_string":"Center for Vision, Cognition, Learning and Art, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032046813","display_name":"Caiming Xiong","orcid":"https://orcid.org/0000-0003-0349-8628"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Caiming Xiong","raw_affiliation_strings":["Center for Vision, Cognition, Learning and Art, University of Californie, Los Angeles, USA","Center for Vision, Cognition, Learning and Art, University of California, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"Center for Vision, Cognition, Learning and Art, University of Californie, Los Angeles, USA","institution_ids":[]},{"raw_affiliation_string":"Center for Vision, Cognition, Learning and Art, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034228010","display_name":"Song\u2010Chun Zhu","orcid":"https://orcid.org/0009-0008-0876-8117"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Song-Chun Zhu","raw_affiliation_strings":["Center for Vision, Cognition, Learning and Art, University of Californie, Los Angeles, USA","Center for Vision, Cognition, Learning and Art, University of California, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"Center for Vision, Cognition, Learning and Art, University of Californie, Los Angeles, USA","institution_ids":[]},{"raw_affiliation_string":"Center for Vision, Cognition, Learning and Art, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005610577"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":13.6543,"has_fulltext":false,"cited_by_count":206,"citation_normalized_percentile":{"value":0.99180543,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1293","last_page":"1301"},"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9952999949455261,"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":0.8310123682022095},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.7481821775436401},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.738791823387146},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.7084070444107056},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6218789219856262},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5793185830116272},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5603969097137451},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.49904704093933105},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4946751296520233},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.47496363520622253},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4673987030982971},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.4571807384490967},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4518654942512512},{"id":"https://openalex.org/keywords/articulated-body-pose-estimation","display_name":"Articulated body pose estimation","score":0.4229007363319397},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36738085746765137},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.25750425457954407},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.06819194555282593}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8310123682022095},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.7481821775436401},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.738791823387146},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.7084070444107056},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6218789219856262},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5793185830116272},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5603969097137451},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.49904704093933105},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4946751296520233},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.47496363520622253},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4673987030982971},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.4571807384490967},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4518654942512512},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.4229007363319397},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36738085746765137},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.25750425457954407},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.06819194555282593},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cvpr.2015.7298734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2015.7298734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.872.4838","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.872.4838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Nie_Joint_Action_Recognition_2015_CVPR_paper.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W225438136","https://openalex.org/W1911783559","https://openalex.org/W1930799357","https://openalex.org/W1976546217","https://openalex.org/W1999192586","https://openalex.org/W2013640163","https://openalex.org/W2020163092","https://openalex.org/W2034014085","https://openalex.org/W2054041160","https://openalex.org/W2054990548","https://openalex.org/W2055753778","https://openalex.org/W2062236848","https://openalex.org/W2068611653","https://openalex.org/W2075563626","https://openalex.org/W2089505226","https://openalex.org/W2093949207","https://openalex.org/W2095661305","https://openalex.org/W2098528528","https://openalex.org/W2099305880","https://openalex.org/W2099972257","https://openalex.org/W2109875425","https://openalex.org/W2128271252","https://openalex.org/W2137591992","https://openalex.org/W2139019684","https://openalex.org/W2139857301","https://openalex.org/W2142194269","https://openalex.org/W2143487029","https://openalex.org/W2151274603","https://openalex.org/W2157982431","https://openalex.org/W2158234032","https://openalex.org/W2161969291","https://openalex.org/W2169852119","https://openalex.org/W2243279568","https://openalex.org/W2533739470","https://openalex.org/W2535410496","https://openalex.org/W2547062449","https://openalex.org/W2610550445","https://openalex.org/W4205969993","https://openalex.org/W4239390603","https://openalex.org/W6683323873"],"related_works":["https://openalex.org/W2033672678","https://openalex.org/W290666912","https://openalex.org/W1968716783","https://openalex.org/W2128635338","https://openalex.org/W2129348295","https://openalex.org/W2997897143","https://openalex.org/W2115571026","https://openalex.org/W2964174634","https://openalex.org/W2296685318","https://openalex.org/W4312304263"],"abstract_inverted_index":{"Action":[0],"recognition":[1,131],"and":[2,21,35,68,80,88,110,113],"pose":[3,84,135],"estimation":[4],"from":[5],"video":[6],"are":[7,62,107,115],"closely":[8],"related":[9],"tasks":[10],"for":[11,104],"understanding":[12],"human":[13],"motion,":[14],"most":[15],"methods,":[16],"however,":[17],"learn":[18],"separate":[19],"models":[20],"combine":[22],"them":[23],"sequentially.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28],"propose":[29],"a":[30],"framework":[31],"to":[32,48,65],"integrate":[33],"training":[34],"testing":[36],"of":[37,74,83],"the":[38,55,78,97],"two":[39],"tasks.":[40],"A":[41],"spatial-temporal":[42],"And-Or":[43],"graph":[44],"model":[45,76,102],"is":[46,57],"introduced":[47],"represent":[49],"action":[50,56,111,130],"at":[51,85,93],"three":[52,105],"scales.":[53],"Specifically":[54],"decomposed":[58],"into":[59],"poses":[60,114],"which":[61],"further":[63],"divided":[64],"mid-level":[66],"ST-parts":[67,92],"then":[69],"parts.":[70],"The":[71,101],"hierarchical":[72],"structure":[73],"our":[75,124],"captures":[77],"geometric":[79],"appearance":[81],"variations":[82],"each":[86],"frame":[87],"lateral":[89],"connections":[90],"between":[91],"adjacent":[94],"frames":[95],"capture":[96],"action-specific":[98],"motion":[99],"information.":[100],"parameters":[103],"scales":[106],"learned":[108],"discriminatively,":[109],"labels":[112],"efficiently":[116],"inferred":[117],"by":[118],"dynamic":[119],"programming.":[120],"Experiments":[121],"demonstrate":[122],"that":[123],"approach":[125],"achieves":[126],"state-of-art":[127],"accuracy":[128],"in":[129],"while":[132],"also":[133],"improving":[134],"estimation.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":30},{"year":2019,"cited_by_count":27},{"year":2018,"cited_by_count":22},{"year":2017,"cited_by_count":29},{"year":2016,"cited_by_count":19},{"year":2015,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}