{"id":"https://openalex.org/W4385767849","doi":"https://doi.org/10.24963/ijcai.2023/148","title":"XFormer: Fast and Accurate Monocular 3D Body Capture","display_name":"XFormer: Fast and Accurate Monocular 3D Body Capture","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767849","doi":"https://doi.org/10.24963/ijcai.2023/148"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/148","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/148","pdf_url":"https://www.ijcai.org/proceedings/2023/0148.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0148.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101233261","display_name":"Lihui Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I68926175","display_name":"Hoya (Japan)","ror":"https://ror.org/049vpfq31","country_code":"JP","type":"company","lineage":["https://openalex.org/I68926175"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Lihui Qian","raw_affiliation_strings":["Huya Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huya Inc","institution_ids":["https://openalex.org/I68926175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102997681","display_name":"Xintong Han","orcid":"https://orcid.org/0000-0003-2842-1803"},"institutions":[{"id":"https://openalex.org/I68926175","display_name":"Hoya (Japan)","ror":"https://ror.org/049vpfq31","country_code":"JP","type":"company","lineage":["https://openalex.org/I68926175"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Xintong Han","raw_affiliation_strings":["Huya Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huya Inc","institution_ids":["https://openalex.org/I68926175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101903127","display_name":"Faqiang Wang","orcid":"https://orcid.org/0000-0001-5317-562X"},"institutions":[{"id":"https://openalex.org/I68926175","display_name":"Hoya (Japan)","ror":"https://ror.org/049vpfq31","country_code":"JP","type":"company","lineage":["https://openalex.org/I68926175"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Faqiang Wang","raw_affiliation_strings":["Huya Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huya Inc","institution_ids":["https://openalex.org/I68926175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100773328","display_name":"Hongyu Liu","orcid":"https://orcid.org/0000-0002-4628-6388"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hongyu Liu","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021859952","display_name":"Haoye Dong","orcid":"https://orcid.org/0000-0001-8169-8890"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoye Dong","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770537","display_name":"Zhiwen Li","orcid":"https://orcid.org/0000-0001-7570-3809"},"institutions":[{"id":"https://openalex.org/I68926175","display_name":"Hoya (Japan)","ror":"https://ror.org/049vpfq31","country_code":"JP","type":"company","lineage":["https://openalex.org/I68926175"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zhiwen Li","raw_affiliation_strings":["Huya Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huya Inc","institution_ids":["https://openalex.org/I68926175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075086049","display_name":"Huawei Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huawei Wei","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101564904","display_name":"Zhe Lin","orcid":"https://orcid.org/0000-0003-1154-9907"},"institutions":[{"id":"https://openalex.org/I68926175","display_name":"Hoya (Japan)","ror":"https://ror.org/049vpfq31","country_code":"JP","type":"company","lineage":["https://openalex.org/I68926175"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zhe Lin","raw_affiliation_strings":["Huya Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huya Inc","institution_ids":["https://openalex.org/I68926175"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062094023","display_name":"Cheng\u2010Bin Jin","orcid":"https://orcid.org/0000-0001-8486-5738"},"institutions":[{"id":"https://openalex.org/I68926175","display_name":"Hoya (Japan)","ror":"https://ror.org/049vpfq31","country_code":"JP","type":"company","lineage":["https://openalex.org/I68926175"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Cheng-Bin Jin","raw_affiliation_strings":["Huya Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huya Inc","institution_ids":["https://openalex.org/I68926175"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102997681"],"corresponding_institution_ids":["https://openalex.org/I68926175"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1331","last_page":"1339"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","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/T10036","display_name":"Advanced Neural Network Applications","score":0.9970999956130981,"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/computer-science","display_name":"Computer science","score":0.8044664859771729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.686497688293457},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.6147398352622986},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6051591038703918},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5768038630485535},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.45944416522979736},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.42129743099212646},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4150616228580475},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09906190633773804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8044664859771729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.686497688293457},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.6147398352622986},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6051591038703918},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5768038630485535},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.45944416522979736},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.42129743099212646},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4150616228580475},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09906190633773804},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2023/148","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/148","pdf_url":"https://www.ijcai.org/proceedings/2023/0148.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-130292","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=1045-0823&rft.volume=2023-August&rft.issue=&rft.date=2023&rft.spage=1331&rft.aulast=Qian&rft.aufirst=Lihui&rft.atitle=XFormer%3A+Fast+and+Accurate+Monocular+3D+Body+Capture&rft.title=IJCAI+International+Joint+Conference+on+Artificial+Intelligence","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/148","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/148","pdf_url":"https://www.ijcai.org/proceedings/2023/0148.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.41999998688697815,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767849.pdf"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W1861492603","https://openalex.org/W2080873731","https://openalex.org/W2101032778","https://openalex.org/W2103015390","https://openalex.org/W2135533529","https://openalex.org/W2137591992","https://openalex.org/W2194775991","https://openalex.org/W2483862638","https://openalex.org/W2573098616","https://openalex.org/W2578797046","https://openalex.org/W2612706635","https://openalex.org/W2758778552","https://openalex.org/W2797184202","https://openalex.org/W2798646183","https://openalex.org/W2888934629","https://openalex.org/W2895748257","https://openalex.org/W2962730651","https://openalex.org/W2963800363","https://openalex.org/W2963995996","https://openalex.org/W2964084369","https://openalex.org/W2966715458","https://openalex.org/W2971856312","https://openalex.org/W2975420824","https://openalex.org/W2981637078","https://openalex.org/W2990270790","https://openalex.org/W3035551320","https://openalex.org/W3098612954","https://openalex.org/W3103977930","https://openalex.org/W3109877674","https://openalex.org/W3140576409","https://openalex.org/W3175199633","https://openalex.org/W3199284799","https://openalex.org/W4214517305","https://openalex.org/W4214679856","https://openalex.org/W4214770715","https://openalex.org/W4231018136","https://openalex.org/W4287684414","https://openalex.org/W4287755748","https://openalex.org/W4312249545","https://openalex.org/W4312797994","https://openalex.org/W4385245566","https://openalex.org/W4385489997"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2239445980","https://openalex.org/W200819717","https://openalex.org/W2080152487","https://openalex.org/W3083152911","https://openalex.org/W3022347918"],"abstract_inverted_index":{"We":[0],"present":[1],"XFormer,":[2],"a":[3,31,63,135,147,158],"novel":[4],"human":[5,37],"mesh":[6,38],"and":[7,43,83,112,127,151,167],"motion":[8,113],"capture":[9,114],"method":[10,61,140],"that":[11,34,47,67,116],"achieves":[12],"real-time":[13],"performance":[14,164],"on":[15,97,134,146,165],"consumer":[16],"CPUs":[17],"given":[18,40],"only":[19],"monocular":[20],"images":[21,103,107],"as":[22],"input.":[23],"The":[24],"proposed":[25],"network":[26],"architecture":[27,88],"contains":[28],"two":[29,73],"branches:":[30],"keypoint":[32,81],"branch":[33,46],"estimates":[35],"3D":[36,109],"vertices":[39],"2D":[41,80],"keypoints,":[42],"an":[44],"image":[45,54,84],"makes":[48],"prediction":[49],"directly":[50],"from":[51],"the":[52,57,77,125],"RGB":[53],"features.":[55,86],"At":[56],"core":[58],"of":[59,100,130],"our":[60,131,139],"is":[62,89],"cross-modal":[64],"transformer":[65],"block":[66],"allows":[68],"information":[69],"flow":[70],"across":[71],"these":[72],"branches":[74],"by":[75],"modeling":[76],"attention":[78],"between":[79],"coordinates":[82],"spatial":[85],"Our":[87],"smartly":[90],"designed,":[91],"which":[92],"enables":[93],"us":[94],"to":[95],"train":[96],"various":[98],"types":[99],"datasets":[101,115],"including":[102],"with":[104,108,157],"2D/3D":[105],"annotations,":[106],"pseudo":[110],"labels,":[111],"do":[117],"not":[118],"have":[119],"associated":[120],"images.":[121],"This":[122],"effectively":[123],"improves":[124],"accuracy":[126],"generalization":[128],"ability":[129],"system.":[132],"Built":[133],"lightweight":[136],"backbone":[137],"(MobileNetV3),":[138],"runs":[141],"blazing":[142],"fast":[143],"(over":[144],"30fps":[145],"single":[148],"CPU":[149],"core)":[150],"still":[152],"yields":[153],"competitive":[154],"accuracy.":[155],"Furthermore,":[156],"HRNet":[159],"backbone,":[160],"XFormer":[161],"delivers":[162],"state-of-the-art":[163],"Huamn3.6":[166],"3DPW":[168],"datasets.":[169]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}