{"id":"https://openalex.org/W4285603535","doi":"https://doi.org/10.24963/ijcai.2022/700","title":"AggPose: Deep Aggregation Vision Transformer for Infant Pose Estimation","display_name":"AggPose: Deep Aggregation Vision Transformer for Infant Pose Estimation","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285603535","doi":"https://doi.org/10.24963/ijcai.2022/700"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/700","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/700","pdf_url":"https://www.ijcai.org/proceedings/2022/0700.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2022/0700.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100430970","display_name":"Xu Cao","orcid":"https://orcid.org/0000-0001-8739-5196"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu Cao","raw_affiliation_strings":["New York University","Shenzhen Automatic Rehabilitation Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Shenzhen Automatic Rehabilitation Laboratory","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066940918","display_name":"Xiaoye Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162629","display_name":"Children's Hospital","ror":"https://ror.org/0511k4970","country_code":"TN","type":"healthcare","lineage":["https://openalex.org/I4210162629"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Xiaoye Li","raw_affiliation_strings":["Shenzhen Automatic Rehabilitation Laboratory","Shenzhen Baoan Women's and Children's Hospital, Jinan University","Shenzhen Baoan Women's and Childiren's Hospital, Jinan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Automatic Rehabilitation Laboratory","institution_ids":[]},{"raw_affiliation_string":"Shenzhen Baoan Women's and Children's Hospital, Jinan University","institution_ids":["https://openalex.org/I4210162629"]},{"raw_affiliation_string":"Shenzhen Baoan Women's and Childiren's Hospital, Jinan University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070206946","display_name":"Liya Ma","orcid":"https://orcid.org/0000-0003-4881-070X"},"institutions":[{"id":"https://openalex.org/I4210162629","display_name":"Children's Hospital","ror":"https://ror.org/0511k4970","country_code":"TN","type":"healthcare","lineage":["https://openalex.org/I4210162629"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Liya Ma","raw_affiliation_strings":["Shenzhen Automatic Rehabilitation Laboratory","Shenzhen Baoan Women's and Children's Hospital, Jinan University","Shenzhen Baoan Women's and Childiren's Hospital, Jinan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Automatic Rehabilitation Laboratory","institution_ids":[]},{"raw_affiliation_string":"Shenzhen Baoan Women's and Children's Hospital, Jinan University","institution_ids":["https://openalex.org/I4210162629"]},{"raw_affiliation_string":"Shenzhen Baoan Women's and Childiren's Hospital, Jinan University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060483310","display_name":"Yi Huang","orcid":"https://orcid.org/0000-0002-6915-1208"},"institutions":[{"id":"https://openalex.org/I4210152664","display_name":"Shenzhen Children's Hospital","ror":"https://ror.org/0409k5a27","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210152664"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Huang","raw_affiliation_strings":["Shenzhen Automatic Rehabilitation Laboratory","Shenzhen Children's Hospital"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Automatic Rehabilitation Laboratory","institution_ids":[]},{"raw_affiliation_string":"Shenzhen Children's Hospital","institution_ids":["https://openalex.org/I4210152664"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024195218","display_name":"Xuan Joanna Feng","orcid":"https://orcid.org/0000-0002-9439-2150"},"institutions":[{"id":"https://openalex.org/I4210152664","display_name":"Shenzhen Children's Hospital","ror":"https://ror.org/0409k5a27","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210152664"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Feng","raw_affiliation_strings":["Shenzhen Automatic Rehabilitation Laboratory","Shenzhen Children's Hospital"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Automatic Rehabilitation Laboratory","institution_ids":[]},{"raw_affiliation_string":"Shenzhen Children's Hospital","institution_ids":["https://openalex.org/I4210152664"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030259119","display_name":"Zening Chen","orcid":"https://orcid.org/0000-0002-2266-7776"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zening Chen","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070424376","display_name":"Hongwu Zeng","orcid":"https://orcid.org/0000-0002-7832-3702"},"institutions":[{"id":"https://openalex.org/I4210152664","display_name":"Shenzhen Children's Hospital","ror":"https://ror.org/0409k5a27","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210152664"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongwu Zeng","raw_affiliation_strings":["Shenzhen Children's Hospital"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Children's Hospital","institution_ids":["https://openalex.org/I4210152664"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008734591","display_name":"Jianguo Cao","orcid":"https://orcid.org/0000-0001-8781-5365"},"institutions":[{"id":"https://openalex.org/I4210152664","display_name":"Shenzhen Children's Hospital","ror":"https://ror.org/0409k5a27","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210152664"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianguo Cao","raw_affiliation_strings":["Shenzhen Automatic Rehabilitation Laboratory","Shenzhen Children's Hospital"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Automatic Rehabilitation Laboratory","institution_ids":[]},{"raw_affiliation_string":"Shenzhen Children's Hospital","institution_ids":["https://openalex.org/I4210152664"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9421,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.93960617,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5045","last_page":"5051"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9799000024795532,"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"}},{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9779999852180481,"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":0.9084540605545044},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7351320385932922},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7274665832519531},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5634518265724182},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4966939091682434},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.47337645292282104},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.42741748690605164},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4063599109649658},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3918949365615845},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.376778781414032},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1083672046661377},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08158981800079346},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06092125177383423}],"concepts":[{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.9084540605545044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7351320385932922},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7274665832519531},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5634518265724182},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4966939091682434},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47337645292282104},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.42741748690605164},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4063599109649658},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3918949365615845},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.376778781414032},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1083672046661377},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08158981800079346},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06092125177383423},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2022/700","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/700","pdf_url":"https://www.ijcai.org/proceedings/2022/0700.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2205.05277","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.05277","pdf_url":"https://arxiv.org/pdf/2205.05277","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/700","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/700","pdf_url":"https://www.ijcai.org/proceedings/2022/0700.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G1000693210","display_name":null,"funder_award_id":"SZSM 202011005","funder_id":"https://openalex.org/F4320335767","funder_display_name":"Sanming Project of Medicine in Shenzhen"}],"funders":[{"id":"https://openalex.org/F4320335767","display_name":"Sanming Project of Medicine in Shenzhen","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285603535.pdf","grobid_xml":"https://content.openalex.org/works/W4285603535.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2903831537","https://openalex.org/W2913645120","https://openalex.org/W2972362249","https://openalex.org/W3014641072","https://openalex.org/W3034399482","https://openalex.org/W3034742259","https://openalex.org/W3034750257","https://openalex.org/W3092789429","https://openalex.org/W3138516171","https://openalex.org/W3160605389","https://openalex.org/W3162547991","https://openalex.org/W3203925315","https://openalex.org/W3206810688","https://openalex.org/W3211490618","https://openalex.org/W4214508443","https://openalex.org/W4287324101","https://openalex.org/W4309442969","https://openalex.org/W4312726009","https://openalex.org/W4313156423"],"related_works":["https://openalex.org/W2964084369","https://openalex.org/W4253893311","https://openalex.org/W3089306886","https://openalex.org/W2113785214","https://openalex.org/W2798721181","https://openalex.org/W3201205132","https://openalex.org/W4312694060","https://openalex.org/W4386075737","https://openalex.org/W4393563475","https://openalex.org/W4387967917"],"abstract_inverted_index":{"Movement":[0],"and":[1,52,108,134,151],"pose":[2,27,38,50,59,106,117,141,156,170],"assessment":[3],"of":[4,20,139],"newborns":[5],"lets":[6],"experienced":[7],"pediatricians":[8],"predict":[9],"neurodevelopmental":[10],"disorders,":[11],"allowing":[12],"early":[13,78],"intervention":[14],"for":[15,25,36,57],"related":[16],"diseases.":[17],"However,":[18],"most":[19],"the":[21,77,128,137,154],"newest":[22],"AI":[23],"approaches":[24],"human":[26,58],"estimation":[28,118,157,171],"methods":[29],"focus":[30],"on":[31,104,111,167,172],"adults,":[32],"lacking":[33],"publicly":[34],"benchmark":[35],"infant":[37,49,116,140,155],"estimation.":[39,142],"In":[40],"this":[41,45],"paper,":[42],"we":[43],"fill":[44],"gap":[46],"by":[47,164],"proposing":[48],"dataset":[51,107],"Deep":[53],"Aggregation":[54],"Vision":[55],"Transformer":[56,82],"estimation,":[60],"which":[61],"introduces":[62],"a":[63],"fast":[64],"trained":[65],"full":[66],"transformer":[67],"framework":[68],"without":[69],"using":[70],"convolution":[71],"operations":[72],"to":[73,85],"extract":[74],"features":[75,130],"in":[76,153],"stages.":[79],"It":[80],"generalizes":[81],"+":[83],"MLP":[84],"high-resolution":[86],"deep":[87],"layer":[88],"aggregation":[89],"within":[90],"feature":[91],"maps,":[92],"thus":[93],"enabling":[94],"information":[95],"fusion":[96],"between":[97],"different":[98,132],"vision":[99],"levels.":[100],"We":[101,143],"pre-train":[102],"AggPose":[103,124,146,161],"COCO":[105,168],"apply":[109],"it":[110],"our":[112,160],"newly":[113],"released":[114],"large-scale":[115],"dataset.":[119,158],"The":[120],"results":[121],"show":[122,144],"that":[123,145],"could":[125],"effectively":[126],"learn":[127],"multi-scale":[129],"among":[131],"resolutions":[133],"significantly":[135],"improve":[136],"performance":[138],"outperforms":[147,162],"hybrid":[148],"model":[149],"HRFormer":[150,163],"TokenPose":[152],"Moreover,":[159],"0.8":[165],"AP":[166],"val":[169],"average.":[173],"Our":[174],"code":[175],"is":[176],"available":[177],"at":[178],"github.com/SZAR-LAB/AggPose.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}