{"id":"https://openalex.org/W4412030750","doi":"https://doi.org/10.1109/tmm.2025.3586122","title":"Synthesizing Multi-Person and Rare Pose Images for Human Pose Estimation","display_name":"Synthesizing Multi-Person and Rare Pose Images for Human Pose Estimation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412030750","doi":"https://doi.org/10.1109/tmm.2025.3586122"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3586122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3586122","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ink.library.smu.edu.sg/sis_research/10151","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113022461","display_name":"Liuqing Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liuqing Zhao","raw_affiliation_strings":["School of Anhui University and the Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Anhui University and the Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001982809","display_name":"Zichen Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zichen Tian","raw_affiliation_strings":["School of Computing and Information Systems, Singapore Management University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029558462","display_name":"Peng Zou","orcid":"https://orcid.org/0000-0001-8777-9413"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zou","raw_affiliation_strings":["School of Computing and Information Systems, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029727770","display_name":"Richang Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Richang Hong","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101633158","display_name":"Qianru Sun","orcid":"https://orcid.org/0000-0003-2689-317X"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qianru Sun","raw_affiliation_strings":["School of Computing and Information Systems, Singapore Management University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5113022461"],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13757731,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"6568","last_page":"6580"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9965000152587891,"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":0.991599977016449,"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/pose","display_name":"Pose","score":0.8654297590255737},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8106096982955933},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7116684913635254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7037175297737122},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.5930254459381104},{"id":"https://openalex.org/keywords/articulated-body-pose-estimation","display_name":"Articulated body pose estimation","score":0.42837560176849365},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3618640899658203}],"concepts":[{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.8654297590255737},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8106096982955933},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7116684913635254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7037175297737122},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.5930254459381104},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.42837560176849365},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3618640899658203}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2025.3586122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3586122","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-11151","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/10151","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-11151","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/10151","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5586753922","display_name":null,"funder_award_id":"U23B2031","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2771558241","https://openalex.org/W2958537753","https://openalex.org/W2961553857","https://openalex.org/W2962784628","https://openalex.org/W2962954622","https://openalex.org/W2962982136","https://openalex.org/W2963402313","https://openalex.org/W2963876278","https://openalex.org/W2976669726","https://openalex.org/W2982103617","https://openalex.org/W3009436916","https://openalex.org/W3014641072","https://openalex.org/W3088599578","https://openalex.org/W3108651438","https://openalex.org/W3153288312","https://openalex.org/W3154906787","https://openalex.org/W3169891778","https://openalex.org/W4221037335","https://openalex.org/W4296437753","https://openalex.org/W4304080729","https://openalex.org/W4304092040","https://openalex.org/W4309368547","https://openalex.org/W4312252891","https://openalex.org/W4312933868","https://openalex.org/W4313007980","https://openalex.org/W4313127332","https://openalex.org/W4319299671","https://openalex.org/W4319300086","https://openalex.org/W4323338522","https://openalex.org/W4376272380","https://openalex.org/W4377079868","https://openalex.org/W4380880503","https://openalex.org/W4386075664","https://openalex.org/W4387695265","https://openalex.org/W4388263958","https://openalex.org/W4388283688","https://openalex.org/W4390577888","https://openalex.org/W4390871780","https://openalex.org/W4390873054","https://openalex.org/W4390873645","https://openalex.org/W4390970362","https://openalex.org/W4393148714","https://openalex.org/W4394596460","https://openalex.org/W4400527363","https://openalex.org/W4401946970","https://openalex.org/W4402702976","https://openalex.org/W4402704533","https://openalex.org/W4402776182","https://openalex.org/W4409263137","https://openalex.org/W4409264051"],"related_works":["https://openalex.org/W2113785214","https://openalex.org/W2946083937","https://openalex.org/W2798721181","https://openalex.org/W4299867837","https://openalex.org/W4386075737","https://openalex.org/W2951583186","https://openalex.org/W1974260915","https://openalex.org/W4382141741","https://openalex.org/W2088028039","https://openalex.org/W1968716783"],"abstract_inverted_index":{"Human":[0],"pose":[1,159,174,178,250],"estimation":[2],"(HPE)":[3],"models":[4,84],"underperform":[5],"in":[6,26,105,217],"recognizing":[7],"rare":[8,24,43,113,137,165],"poses":[9,104,114,138,206,223],"because":[10],"they":[11],"suffer":[12],"from":[13,95],"data":[14,32,41,67,79,251],"imbalance":[15],"problems":[16],"(i.e.,":[17],"there":[18],"are":[19,215],"few":[20],"image":[21,144,196,255],"samples":[22],"for":[23,42,101,142],"poses)":[25],"their":[27],"training":[28],"datasets.":[29],"From":[30],"a":[31,148,157,194],"perspective,":[33],"the":[34,46,58,62,66,69,77,96,132,152,189,220,225],"most":[35],"intuitive":[36],"solution":[37],"is":[38,74,169,179,201],"to":[39,57,75,112,130,163],"synthesize":[40,164],"poses.":[44,166],"Specifically,":[45],"rule-based":[47],"methods":[48],"apply":[49],"manual":[50],"manipulations":[51],"(such":[52,85,118],"as":[53,86,119],"Cutout":[54],"and":[55,88,90,139,176,186,207,224,242,253,258,266],"GridMask)":[56],"existing":[59],"data,":[60,175],"so":[61],"limited":[63],"diversity":[64,221],"of":[65,184,210,219,222,227],"constrains":[68],"model.":[70],"An":[71],"alternative":[72],"method":[73,247],"learn":[76],"underlying":[78],"distribution":[80],"via":[81],"deep":[82],"generative":[83],"ControlNet":[87],"HumanSD)":[89],"then":[91],"sample":[92],"\u201cnew":[93],"data\u201d":[94],"distribution.":[97],"This":[98,167],"works":[99],"well":[100],"generating":[102],"frequent":[103],"common":[106],"scenes,":[107,141],"but":[108],"suffers":[109],"when":[110],"applied":[111],"or":[115],"complex":[116,140,211],"scenes":[117],"multiple":[120,204],"persons":[121],"with":[122,181],"overlapping":[123],"limbs).":[124],"In":[125,151,188],"this":[126],"paper,":[127],"we":[128,155,192,231],"aim":[129],"address":[131],"above":[133],"two":[134],"issues,":[135],"i.e.,":[136],"person":[143,254],"generation.":[145],"We":[146,244],"propose":[147],"two-stage":[149],"method.":[150],"first":[153],"stage,":[154,191],"design":[156],"controllable":[158,216],"generator":[160,168,197],"named":[161,198],"PoseFactory":[162],"specifically":[170],"trained":[171],"on":[172,203,235],"augmented":[173],"each":[177],"labelled":[180],"its":[182,261],"level":[183],"difficulty":[185],"rarity.":[187],"second":[190],"introduce":[193],"multi-person":[195],"MultipGenerator.":[199],"It":[200],"conditioned":[202],"human":[205],"textual":[208],"descriptions":[209],"scenes.":[212,228],"Both":[213],"stages":[214],"terms":[218],"complexity":[226],"For":[229],"evaluation,":[230],"conduct":[232],"extensive":[233],"experiments":[234],"three":[236],"widely":[237],"used":[238],"datasets:":[239],"MS-COCO,":[240],"HumanArt,":[241],"OCHuman.":[243],"compare":[245],"our":[246],"against":[248],"traditional":[249],"augmentation":[252],"generation":[256],"methods,":[257],"it":[259],"demonstrates":[260],"superior":[262],"performance":[263],"both":[264],"quantitatively":[265],"qualitatively.":[267]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}