{"id":"https://openalex.org/W4390479118","doi":"https://doi.org/10.1145/3595916.3626432","title":"Research on Multi-Person Pose Estimation Based on YOLO and Decoupled Multi-Level Feature Layers Fusion","display_name":"Research on Multi-Person Pose Estimation Based on YOLO and Decoupled Multi-Level Feature Layers Fusion","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4390479118","doi":"https://doi.org/10.1145/3595916.3626432"},"language":"en","primary_location":{"id":"doi:10.1145/3595916.3626432","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3595916.3626432","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626432","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626432","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039070168","display_name":"Bin Zheng","orcid":"https://orcid.org/0000-0002-5181-9150"},"institutions":[{"id":"https://openalex.org/I56934997","display_name":"Changsha University of Science and Technology","ror":"https://ror.org/03yph8055","country_code":"CN","type":"education","lineage":["https://openalex.org/I56934997"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Zheng","raw_affiliation_strings":["CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY: CHANGSHA, CN, CN"],"raw_orcid":"https://orcid.org/0000-0002-5181-9150","affiliations":[{"raw_affiliation_string":"CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY: CHANGSHA, CN, CN","institution_ids":["https://openalex.org/I56934997"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101572646","display_name":"He Zhang","orcid":"https://orcid.org/0009-0003-3374-5500"},"institutions":[{"id":"https://openalex.org/I56934997","display_name":"Changsha University of Science and Technology","ror":"https://ror.org/03yph8055","country_code":"CN","type":"education","lineage":["https://openalex.org/I56934997"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Zhang","raw_affiliation_strings":["CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY: CHANGSHA, CN, CN"],"raw_orcid":"https://orcid.org/0009-0003-3374-5500","affiliations":[{"raw_affiliation_string":"CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY: CHANGSHA, CN, CN","institution_ids":["https://openalex.org/I56934997"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103280349","display_name":"Jin Lu","orcid":"https://orcid.org/0009-0002-4987-1256"},"institutions":[{"id":"https://openalex.org/I56934997","display_name":"Changsha University of Science and Technology","ror":"https://ror.org/03yph8055","country_code":"CN","type":"education","lineage":["https://openalex.org/I56934997"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Jin","raw_affiliation_strings":["CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY: CHANGSHA, CN, CN"],"raw_orcid":"https://orcid.org/0009-0002-4987-1256","affiliations":[{"raw_affiliation_string":"CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY: CHANGSHA, CN, CN","institution_ids":["https://openalex.org/I56934997"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I56934997"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9966999888420105,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/pose","display_name":"Pose","score":0.8908067941665649},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7828567624092102},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6101810336112976},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.544067919254303},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5379348993301392},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5261927247047424},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.5011470317840576},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.49941539764404297},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4601597785949707},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44061216711997986},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4146782457828522},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4082774519920349},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3864253759384155},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34862542152404785},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.23989653587341309},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2117924690246582}],"concepts":[{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.8908067941665649},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7828567624092102},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6101810336112976},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.544067919254303},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5379348993301392},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5261927247047424},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.5011470317840576},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.49941539764404297},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4601597785949707},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44061216711997986},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4146782457828522},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4082774519920349},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3864253759384155},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34862542152404785},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.23989653587341309},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2117924690246582},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3595916.3626432","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3595916.3626432","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626432","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3595916.3626432","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3595916.3626432","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626432","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390479118.pdf","grobid_xml":"https://content.openalex.org/works/W4390479118.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2175012183","https://openalex.org/W2194775991","https://openalex.org/W2307770531","https://openalex.org/W2578797046","https://openalex.org/W2752782242","https://openalex.org/W2883780447","https://openalex.org/W2916798096","https://openalex.org/W2962730651","https://openalex.org/W2962954622","https://openalex.org/W2963163009","https://openalex.org/W2963402313","https://openalex.org/W2964221239","https://openalex.org/W2982083293","https://openalex.org/W3034399482","https://openalex.org/W3035414587","https://openalex.org/W3119205652","https://openalex.org/W3162418282","https://openalex.org/W3177052299","https://openalex.org/W3184439416","https://openalex.org/W4229890965","https://openalex.org/W4292787291","https://openalex.org/W4312914534","https://openalex.org/W4386076325","https://openalex.org/W6893711219"],"related_works":["https://openalex.org/W4237171675","https://openalex.org/W3036286480","https://openalex.org/W4287027631","https://openalex.org/W3192357901","https://openalex.org/W2387360586","https://openalex.org/W2952736415","https://openalex.org/W3209723314","https://openalex.org/W3205398323","https://openalex.org/W2883297582","https://openalex.org/W4295519653"],"abstract_inverted_index":{"Multi-person":[0],"pose":[1,63,77],"estimation":[2,64],"is":[3],"fundamental":[4],"research":[5],"in":[6,99],"the":[7,53,57,68,91,94,103,138,142],"fields":[8],"of":[9,105],"AIGC,":[10],"multimedia":[11],"understanding,virtual":[12],"reality,":[13],"human-computer":[14],"interaction,":[15],"etc.":[16,135],"Existing":[17],"algorithms":[18],"have":[19],"problems":[20],"such":[21],"as":[22,141],"large":[23],"computational":[24,44],"complexity,":[25],"low":[26],"accuracy,":[27],"and":[28,66,76,145],"an":[29],"inability":[30],"to":[31,38],"effectively":[32],"predict":[33],"occlusions,":[34],"making":[35],"them":[36],"difficult":[37],"deploy":[39],"on":[40],"devices":[41],"with":[42,90,116],"limited":[43],"resources.":[45],"This":[46],"paper":[47,101],"introduces":[48],"coordinate":[49,120],"attention":[50],"mechanisms":[51],"within":[52],"YOLOv7tiny":[54],"framework,":[55],"improves":[56],"OKS":[58],"loss":[59],"function":[60],"tailored":[61],"for":[62],"tasks,":[65],"proposes":[67],"FDPose":[69],"method":[70],"that":[71,88],"decouples":[72],"bounding":[73],"box":[74],"detection":[75],"regression":[78,121],"tasks":[79],"by":[80,107,112],"fusing":[81],"different":[82],"feature":[83],"layers.":[84],"Experimental":[85],"results":[86],"show":[87],"compared":[89],"original":[92],"algorithm,":[93],"standard":[95],"version":[96],"FDPose-n":[97,125],"used":[98],"this":[100],"reduces":[102],"number":[104],"parameters":[106],"14.8%":[108],"while":[109],"improving":[110],"AP":[111,128],"9.7%.":[113],"In":[114],"comparison":[115],"some":[117],"similarly":[118],"sized":[119],"based":[122],"bottom-up":[123],"algorithms,":[124],"achieves":[126],"higher":[127],"than":[129],"Associative":[130],"Embedding,":[131],"DeepPose,":[132],"YOLOv5s-pose,":[133],"YOLOv8n-pose,":[134],"We":[136],"use":[137],"CrowdPose":[139],"dataset":[140],"training":[143],"set":[144],"without":[146],"any":[147],"pre-trained":[148],"weights.":[149]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}