{"id":"https://openalex.org/W4390962052","doi":"https://doi.org/10.48550/arxiv.2401.07251","title":"3D Landmark Detection on Human Point Clouds: A Benchmark and A Dual Cascade Point Transformer Framework","display_name":"3D Landmark Detection on Human Point Clouds: A Benchmark and A Dual Cascade Point Transformer Framework","publication_year":2024,"publication_date":"2024-01-14","ids":{"openalex":"https://openalex.org/W4390962052","doi":"https://doi.org/10.48550/arxiv.2401.07251"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2401.07251","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.07251","pdf_url":"https://arxiv.org/pdf/2401.07251","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,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2401.07251","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100407242","display_name":"Fan Zhang","orcid":"https://orcid.org/0000-0003-3291-7887","observed_orcids":["https://orcid.org/0000-0003-3291-7887"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zhang, Fan","raw_affiliation_strings":["College of Big Data and Internet , Shenzhen Technology University , Shenzhen , China","Department of Electrical and Computer Engineering , Georgia Institute of Technology , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Big Data and Internet , Shenzhen Technology University , Shenzhen , China","institution_ids":["https://openalex.org/I4210152380"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering , Georgia Institute of Technology , Shenzhen , China","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103004350","display_name":"Shuyi Mao","orcid":"https://orcid.org/0009-0000-4338-687X","observed_orcids":["https://orcid.org/0009-0000-4338-687X"]},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mao, Shuyi","raw_affiliation_strings":["AI Lab , Lenovo Research , Shenzhen , China","Shenzhen Technol- ogy University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Lab , Lenovo Research , Shenzhen , China","institution_ids":["https://openalex.org/I4210156165"]},{"raw_affiliation_string":"Shenzhen Technol- ogy University","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Li, Qing","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Qing","raw_affiliation_strings":["College of Big Data and Internet , Shenzhen Technology University , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Big Data and Internet , Shenzhen Technology University , Shenzhen , China","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033413473","display_name":"Xiaojiang Peng","orcid":"https://orcid.org/0000-0002-5783-321X","observed_orcids":["https://orcid.org/0000-0002-5783-321X"]},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng, Xiaojiang","raw_affiliation_strings":["College of Big Data and Internet , Shenzhen Technology University , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Big Data and Internet , Shenzhen Technology University , Shenzhen , China","institution_ids":["https://openalex.org/I4210152380"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9423999786376953,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9423999786376953,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.041099999099969864,"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/T11448","display_name":"Face recognition and analysis","score":0.007199999876320362,"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/point-cloud-dataset","display_name":"point cloud dataset","score":0.5669999718666077},{"id":"https://openalex.org/keywords/refinenet","display_name":"RefineNet","score":0.9559999704360962},{"id":"https://openalex.org/keywords/3d-human-pose-estimation","display_name":"3D human pose estimation","score":0.7080000042915344},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.3330000042915344}],"concepts":[{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.9370986223220825},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.7567909955978394},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7354423999786377},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.6943862438201904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5728305578231812},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5036596655845642},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4658452272415161},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34090206027030945},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10589128732681274},{"id":"https://openalex.org/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical 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},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2401.07251","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.07251","pdf_url":"https://arxiv.org/pdf/2401.07251","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,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2401.07251","doi":"https://doi.org/10.48550/arxiv.2401.07251","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2401.07251","pdf_url":null,"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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2401.07251","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.07251","pdf_url":"https://arxiv.org/pdf/2401.07251","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,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390962052.pdf","grobid_xml":"https://content.openalex.org/works/W4390962052.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2797184202","https://openalex.org/W2963083779","https://openalex.org/W3094502228","https://openalex.org/W4388505075","https://openalex.org/W4388543774","https://openalex.org/W4388543778","https://openalex.org/W4388709714"],"related_works":["https://openalex.org/W3129013610","https://openalex.org/W7127645602","https://openalex.org/W4412823012","https://openalex.org/W7124858550","https://openalex.org/W4386273031","https://openalex.org/W4400717509","https://openalex.org/W3166470370","https://openalex.org/W7006140651","https://openalex.org/W4404927200","https://openalex.org/W3201095453"],"abstract_inverted_index":{"3D":[0,12,46,56,82],"landmark":[1,28,42,57,83,119,139],"detection":[2,29,43,58,84],"plays":[3],"a":[4,35,52,70,109,142],"pivotal":[5],"role":[6],"in":[7,25,44],"various":[8],"applications":[9],"such":[10],"as":[11],"registration,":[13],"pose":[14,31],"estimation,":[15,32],"and":[16,97,155],"virtual":[17],"try-on.":[18],"While":[19],"considerable":[20],"success":[21],"has":[22],"been":[23],"achieved":[24],"2D":[26],"human":[27,60,72,90],"or":[30],"there":[33],"is":[34],"notable":[36],"scarcity":[37],"of":[38,164,170],"reported":[39],"works":[40],"on":[41,59,153],"unordered":[45],"point":[47,61,73,91,134],"clouds.":[48],"This":[49,86],"paper":[50],"introduces":[51],"novel":[53],"challenge,":[54],"namely":[55],"clouds,":[62],"presenting":[63],"two":[64],"primary":[65],"contributions.":[66],"Firstly,":[67],"we":[68,107],"establish":[69],"comprehensive":[71],"cloud":[74,135],"dataset,":[75],"named":[76],"HPoint103,":[77],"designed":[78],"to":[79],"support":[80],"the":[81,124,132,156,161,168],"community.":[85],"dataset":[87,158],"comprises":[88],"103":[89],"clouds":[92],"created":[93],"with":[94,102,141,149],"commercial":[95],"software":[96],"actors,":[98],"each":[99],"manually":[100],"annotated":[101],"11":[103],"stable":[104],"landmarks.":[105],"Secondly,":[106],"propose":[108],"Dual":[110],"Cascade":[111],"Point":[112],"Transformer":[113,128],"(D-CPT)":[114],"model":[115],"for":[116],"precise":[117],"point-based":[118,151],"detection.":[120],"D-CPT":[121],"gradually":[122],"refines":[123],"landmarks":[125],"through":[126],"cascade":[127],"decoder":[129],"layers":[130],"across":[131],"entire":[133],"stream,":[136],"simultaneously":[137],"enhancing":[138],"coordinates":[140],"RefineNet":[143,172],"over":[144],"local":[145],"regions.":[146],"Comparative":[147],"evaluations":[148],"popular":[150],"methods":[152,175],"HPoint103":[154],"public":[157],"DHP19":[159],"demonstrate":[160],"dramatic":[162],"outperformance":[163],"our":[165,171],"D-CPT.":[166],"Additionally,":[167],"integration":[169],"into":[173],"existing":[174],"consistently":[176],"improves":[177],"performance.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-01-18T00:00:00"}