{"id":"https://openalex.org/W7118776676","doi":"https://doi.org/10.1109/indin64977.2025.11279684","title":"MiTPose: Multi-Granularity Guided Vision Transformer for Human Pose Estimation","display_name":"MiTPose: Multi-Granularity Guided Vision Transformer for Human Pose Estimation","publication_year":2025,"publication_date":"2025-07-12","ids":{"openalex":"https://openalex.org/W7118776676","doi":"https://doi.org/10.1109/indin64977.2025.11279684"},"language":null,"primary_location":{"id":"doi:10.1109/indin64977.2025.11279684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/indin64977.2025.11279684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 23rd International Conference on Industrial Informatics (INDIN)","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/A5102761127","display_name":"Yunfeng Wu","orcid":"https://orcid.org/0009-0006-2403-6114"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yunfeng Wu","raw_affiliation_strings":["School of Advanced Technology, Xi’an Jiaotong-Liverpool University,Suzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University,Suzhou,China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qizhong Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qizhong Gao","raw_affiliation_strings":["University of Liverpool,Department of Computer Science,Liverpool,UK"],"affiliations":[{"raw_affiliation_string":"University of Liverpool,Department of Computer Science,Liverpool,UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026006304","display_name":"Yize Liu","orcid":"https://orcid.org/0009-0004-4775-996X"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yize Liu","raw_affiliation_strings":["School of Advanced Technology, Xi’an Jiaotong-Liverpool University,Suzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University,Suzhou,China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jun Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Sun","raw_affiliation_strings":["School of Advanced Technology, Xi’an Jiaotong-Liverpool University,Suzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University,Suzhou,China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082241975","display_name":"Zhangyu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuozhi Li","raw_affiliation_strings":["School of Advanced Technology, Xi’an Jiaotong-Liverpool University,Suzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University,Suzhou,China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122007095","display_name":"Yuhao Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuhao Jin","raw_affiliation_strings":["University of Liverpool,Department of Computer Science,Liverpool,UK"],"affiliations":[{"raw_affiliation_string":"University of Liverpool,Department of Computer Science,Liverpool,UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122006908","display_name":"Yong Yue","orcid":null},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Yue","raw_affiliation_strings":["School of Advanced Technology, Xi’an Jiaotong-Liverpool University,Suzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University,Suzhou,China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121987813","display_name":"Xiaohui Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohui Zhu","raw_affiliation_strings":["School of Advanced Technology, Xi’an Jiaotong-Liverpool University,Suzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University,Suzhou,China","institution_ids":["https://openalex.org/I69356397"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5102761127"],"corresponding_institution_ids":["https://openalex.org/I69356397"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.64777889,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9545999765396118,"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":0.9545999765396118,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.007899999618530273,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T12740","display_name":"Gait Recognition and Analysis","score":0.006300000008195639,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.7229999899864197},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5315999984741211},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5070000290870667},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4844000041484833},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.3912999927997589},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.3797999918460846},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3790000081062317},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.3693999946117401}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7246999740600586},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.7229999899864197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6746000051498413},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5315999984741211},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5080999732017517},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5070000290870667},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4844000041484833},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3912999927997589},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3790000081062317},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.3693999946117401},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/indin64977.2025.11279684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/indin64977.2025.11279684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 23rd International Conference on Industrial Informatics (INDIN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5065794587135315,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2113325037","https://openalex.org/W2307770531","https://openalex.org/W2916798096","https://openalex.org/W2963402313","https://openalex.org/W2963474899","https://openalex.org/W2963598138","https://openalex.org/W2964221239","https://openalex.org/W2964304707","https://openalex.org/W2989604896","https://openalex.org/W3034399482","https://openalex.org/W3034742259","https://openalex.org/W3036708415","https://openalex.org/W3171398643","https://openalex.org/W3176892444","https://openalex.org/W3203925315","https://openalex.org/W4229890965","https://openalex.org/W4312314406","https://openalex.org/W4313127332","https://openalex.org/W4386071462","https://openalex.org/W4386076493","https://openalex.org/W4390873058","https://openalex.org/W4403295588"],"related_works":[],"abstract_inverted_index":{"Two-dimensional":[0],"human":[1,36,92],"pose":[2,37,93,179],"estimation":[3,94,180],"(HPE)":[4],"has":[5,31],"been":[6],"extensively":[7],"applied":[8],"across":[9],"various":[10],"domains,":[11],"including":[12],"behavioral":[13],"analysis,":[14],"identity":[15],"verification,":[16],"and":[17,50,63,100,123,131,156,165],"automated":[18],"industrial":[19],"manufacturing.":[20],"Compared":[21],"to":[22,73,127,143,182],"convolutional":[23],"neural":[24],"networks":[25],"(CNNs),":[26],"the":[27,45,65,71,145,168],"Vision":[28,89],"Transformer":[29,90],"(ViT)":[30],"demonstrated":[32],"impressive":[33],"results":[34],"in":[35,68,151,178],"estimation.":[38],"However,":[39],"two":[40],"main":[41],"challenges":[42],"arise:":[43],"(1)":[44],"complexity":[46],"of":[47,118,147],"image":[48],"size":[49],"parameters":[51],"grows":[52],"quadratically,":[53],"making":[54],"traditional":[55,148],"ViT":[56],"unsuitable":[57],"for":[58,91,102,160],"deployment":[59],"on":[60,167],"edge":[61],"devices,":[62],"(2)":[64],"attention":[66],"mechanism":[67],"transformers":[69],"lacks":[70],"ability":[72],"capture":[74],"local":[75,153],"fine-grained":[76,154],"perception.":[77],"To":[78],"address":[79,144],"these":[80],"issues,":[81],"we":[82,106,137],"propose":[83],"a":[84,119,139,157],"novel":[85,140],"method":[86],"Multi-Granularity":[87,141],"guided":[88],"(MiTPOSE),":[95],"which":[96,116],"integrates":[97],"both":[98],"CNN":[99],"transformer":[101],"feature":[103,134],"encoding.":[104],"Specifically,":[105],"introduce":[107],"an":[108],"improved":[109],"SCConv":[110],"encoder":[111],"with":[112],"Global":[113],"Response":[114],"Normalization,":[115],"consists":[117],"spatial":[120],"reconstruction":[121,125],"unit":[122,126],"channel":[124],"reduce":[128],"redundant":[129],"computations":[130],"enhance":[132],"representative":[133],"learning.":[135],"Furthermore,":[136],"incorporate":[138],"block":[142],"shortcomings":[146],"self-attention":[149],"mechanisms":[150],"capturing":[152],"details,":[155],"lightweight":[158],"decoder":[159],"keypoint":[161],"detection.":[162],"Comprehensive":[163],"evaluations":[164],"tests":[166],"COCO":[169],"benchmark":[170],"datasets":[171],"demonstrate":[172],"that":[173],"MiTPose":[174],"achieves":[175],"competitive":[176],"performance":[177],"compared":[181],"state-of-the-art":[183],"methods.":[184]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2026-01-08T00:00:00"}