{"id":"https://openalex.org/W2965348796","doi":"https://doi.org/10.1109/icme.2019.00079","title":"Learning Recurrent Structure-Guided Attention Network for Multi-person Pose Estimation","display_name":"Learning Recurrent Structure-Guided Attention Network for Multi-person Pose Estimation","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2965348796","doi":"https://doi.org/10.1109/icme.2019.00079","mag":"2965348796"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2019.00079","doi":"https://doi.org/10.1109/icme.2019.00079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2019.00079","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5027006079","display_name":"Zhongwei Qiu","orcid":"https://orcid.org/0000-0001-9700-9658","observed_orcids":["https://orcid.org/0000-0001-9700-9658"]},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongwei Qiu","raw_affiliation_strings":["University of Science and Technology Beijing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102742709","display_name":"Kai Qiu","orcid":"https://orcid.org/0000-0003-2071-4425","observed_orcids":["https://orcid.org/0000-0003-2071-4425"]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Qiu","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072029041","display_name":"Jianlong Fu","orcid":"https://orcid.org/0000-0002-1025-2012","observed_orcids":["https://orcid.org/0000-0002-1025-2012"]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianlong Fu","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016681542","display_name":"Dongmei Fu","orcid":"https://orcid.org/0000-0003-3918-9448","observed_orcids":["https://orcid.org/0000-0003-3918-9448"]},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongmei Fu","raw_affiliation_strings":["University of Science and Technology Beijing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.489,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.73302825,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"418","last_page":"423"},"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/T10036","display_name":"Advanced Neural Network Applications","score":9.999999747378752e-05,"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/T11448","display_name":"Face recognition and analysis","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multi-person-pose-estimation","display_name":"multi-person pose estimation","score":1.0},{"id":"https://openalex.org/keywords/recurrent-neural-networks","display_name":"recurrent neural networks","score":0.746999979019165},{"id":"https://openalex.org/keywords/pose-refinement","display_name":"pose refinement","score":0.47699999809265137},{"id":"https://openalex.org/keywords/occlusion-handling","display_name":"occlusion handling","score":0.8090000152587891},{"id":"https://openalex.org/keywords/coco-keypoints","display_name":"COCO keypoints","score":0.675000011920929}],"concepts":[{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.816962480545044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7965712547302246},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.777894914150238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7765668630599976},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.665907621383667},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5815059542655945},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.548176109790802},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.49772217869758606},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4810764789581299},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.46406516432762146},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4494768977165222},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.43975839018821716},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42974019050598145},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4197339117527008},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4117533564567566},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17582064867019653},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14234313368797302},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07829499244689941},{"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/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2019.00079","doi":"https://doi.org/10.1109/icme.2019.00079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2019.00079","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W602397586","https://openalex.org/W1861492603","https://openalex.org/W2117539524","https://openalex.org/W2128271252","https://openalex.org/W2136391815","https://openalex.org/W2143478373","https://openalex.org/W2155394491","https://openalex.org/W2175012183","https://openalex.org/W2194775991","https://openalex.org/W2307770531","https://openalex.org/W2330914857","https://openalex.org/W2555751471","https://openalex.org/W2559085405","https://openalex.org/W2578797046","https://openalex.org/W2962992847","https://openalex.org/W2963091558","https://openalex.org/W2963402313","https://openalex.org/W2963781481","https://openalex.org/W2964221239"],"related_works":["https://openalex.org/W3046892074","https://openalex.org/W2940641446","https://openalex.org/W3082133990","https://openalex.org/W4382996872","https://openalex.org/W4400786028","https://openalex.org/W2799041509","https://openalex.org/W2968009120","https://openalex.org/W2963197583","https://openalex.org/W3130834024","https://openalex.org/W2895457201"],"abstract_inverted_index":{"Multi-person":[0],"pose":[1,48,66,95,100,141,149,158],"estimation":[2,142],"aims":[3],"to":[4,138,146],"localize":[5],"tens":[6],"of":[7,32,64,157],"human":[8,16,34,52,80],"joints":[9,53],"(e.g.,":[10],"elbow,":[11],"wrist,":[12],"etc.)":[13],"from":[14,54],"multiple":[15],"bodies":[17],"in":[18,71,78,126,180],"an":[19],"image.":[20],"Existing":[21],"approaches":[22,60],"mainly":[23],"adopt":[24],"a":[25,33,38,45,88,98,106,111,121,127,134,175],"two":[26],"stage":[27],"pipeline,":[28],"which":[29,75,115],"usually":[30],"consists":[31],"detector":[35],"(i.e.,":[36,50],"generating":[37,51],"bounding":[39,56,73],"box":[40],"for":[41,93],"each":[42,55,72],"person)":[43],"and":[44,68,110,145,153],"single":[46],"person":[47],"estimator":[49],"box).":[57],"However,":[58],"these":[59],"neglect":[61],"the":[62,155,166,171,181],"challenges":[63],"large":[65],"variations":[67],"heavy":[69],"occlusions":[70],"box,":[74],"often":[76],"results":[77,169],"imprecise":[79],"joint":[81,107,112],"localization.":[82],"In":[83],"this":[84],"paper,":[85],"we":[86],"propose":[87],"structure-guided":[89,122],"attention":[90,123],"network":[91,124,137],"(SGAN)":[92,125],"multi-person":[94],"estimation.":[96],"Specifically,":[97],"structured":[99],"representation":[101],"is":[102],"encoded":[103],"by":[104,120],"learning":[105,156],"confidence":[108],"map":[109],"association":[113],"map,":[114],"can":[116,160],"be":[117,161],"further":[118],"refined":[119],"recurrent":[128],"way.":[129],"Note":[130],"that":[131],"SGAN":[132],"enables":[133],"deep":[135],"neural":[136],"take":[139],"initial":[140],"as":[143,151],"references,":[144],"discover":[147],"multi-scale":[148],"features":[150],"completion,":[152],"thus":[154],"structures":[159],"reinforced.":[162],"Extensive":[163],"experiments":[164],"show":[165],"best":[167],"single-model":[168],"against":[170],"state-of-the-art":[172],"approaches,":[173],"with":[174],"relative":[176],"3.5%":[177],"mAP":[178],"gain":[179],"challenging":[182],"COCO":[183],"Keypoint":[184],"dataset.":[185]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2019-08-13T00:00:00"}