{"id":"https://openalex.org/W4417009261","doi":"https://doi.org/10.1109/wacv61042.2026.00519","title":"DF-Mamba: Deformable State Space Modeling for 3D Hand Pose Estimation in Interactions","display_name":"DF-Mamba: Deformable State Space Modeling for 3D Hand Pose Estimation in Interactions","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4417009261","doi":"https://doi.org/10.1109/wacv61042.2026.00519"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00519","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00519","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.02727","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032963399","display_name":"Yifan Zhou","orcid":"https://orcid.org/0000-0001-9517-1571"},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Zhou","raw_affiliation_strings":["Institute of Science Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo","institution_ids":["https://openalex.org/I4400009020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040126789","display_name":"Takehiko Ohkawa","orcid":"https://orcid.org/0000-0003-2329-8797"},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Takehiko Ohkawa","raw_affiliation_strings":["Institute of Science Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo","institution_ids":["https://openalex.org/I4400009020"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guwenxiao Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Guwenxiao Zhou","raw_affiliation_strings":["Institute of Science Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo","institution_ids":["https://openalex.org/I4400009020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035761466","display_name":"Kanoko Goto","orcid":null},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Kanoko Goto","raw_affiliation_strings":["Institute of Science Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo","institution_ids":["https://openalex.org/I4400009020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113319829","display_name":"Takumi Hirose","orcid":null},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Takumi Hirose","raw_affiliation_strings":["Institute of Science Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo","institution_ids":["https://openalex.org/I4400009020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000254206","display_name":"Yusuke Sekikawa","orcid":"https://orcid.org/0000-0003-1111-5949"},"institutions":[{"id":"https://openalex.org/I67530263","display_name":"Denso (United States)","ror":"https://ror.org/02w314k38","country_code":"US","type":"company","lineage":["https://openalex.org/I4210132650","https://openalex.org/I67530263"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yusuke Sekikawa","raw_affiliation_strings":["Denso IT Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Denso IT Laboratory","institution_ids":["https://openalex.org/I67530263"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101261291","display_name":"Nakamasa Inoue","orcid":"https://orcid.org/0009-0006-1145-0914"},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Nakamasa Inoue","raw_affiliation_strings":["Institute of Science Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo","institution_ids":["https://openalex.org/I4400009020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0253313,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5352","last_page":"5363"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.8892999887466431,"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":0.8892999887466431,"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":0.04670000076293945,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.03099999949336052,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6189000010490417},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6162999868392944},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5842000246047974},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.5644000172615051},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5482000112533569},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5066999793052673},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.48570001125335693},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.4097000062465668}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7555999755859375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7421000003814697},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6189000010490417},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6162999868392944},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5842000246047974},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5760999917984009},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.5644000172615051},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5482000112533569},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5066999793052673},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.48570001125335693},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4097000062465668},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4027999937534332},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.303600013256073},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00519","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00519","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.02727","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.02727","pdf_url":"https://arxiv.org/pdf/2512.02727","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"},{"id":"doi:10.48550/arxiv.2512.02727","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.02727","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.02727","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.02727","pdf_url":"https://arxiv.org/pdf/2512.02727","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modeling":[0],"daily":[1],"hand":[2,25,33],"interactions":[3],"often":[4],"struggles":[5],"with":[6,183],"severe":[7],"occlusions,":[8],"such":[9,31,76],"as":[10,207,209],"when":[11],"two":[12],"hands":[13],"overlap,":[14],"which":[15],"highlights":[16],"the":[17,41,60,94,143,170,177,216],"need":[18],"for":[19,48,72,84,108,149],"robust":[20],"feature":[21,73,110],"learning":[22],"in":[23,112],"3D":[24,65,85,113,181],"pose":[26],"estimation":[27],"(HPE).":[28],"To":[29,97],"handle":[30],"occluded":[32,49],"images,":[34],"it":[35],"is":[36,127],"vital":[37],"to":[38,88,92,129,187],"effectively":[39],"learn":[40],"relationship":[42],"between":[43],"local":[44,150],"image":[45,162,218],"features":[46,151,159],"(e.g.,":[47,54],"joints)":[50],"and":[51,75,105,142,200,204,211,222,227],"global":[52,95,131,171],"context":[53,132],"cues":[55,133,167],"from":[56],"inter-joints,":[57],"inter-hands,":[58],"or":[59],"scene).":[61],"However,":[62],"most":[63],"current":[64],"HPE":[66,86,114],"methods":[67],"still":[68],"rely":[69],"on":[70,194,224],"ResNet":[71],"extraction,":[74],"CNN\u2019s":[77],"inductive":[78],"bias":[79],"may":[80],"not":[81],"be":[82],"optimal":[83],"due":[87],"its":[89],"limited":[90],"capability":[91],"model":[93],"context.":[96,172],"address":[98],"this":[99],"limitation,":[100],"we":[101],"propose":[102],"an":[103,161],"effective":[104],"efficient":[106],"framework":[107],"visual":[109],"extraction":[111],"using":[115],"recent":[116],"state":[117,140,146],"space":[118],"modeling":[119,141],"(i.e.,":[120],"Mamba),":[121],"dubbed":[122],"Deformable":[123],"Mamba":[124],"(DF-Mamba).":[125],"DF-Mamba":[126,214],"designed":[128],"capture":[130],"beyond":[134],"standard":[135],"convolution":[136],"through":[137],"Mamba\u2019s":[138],"selective":[139],"proposed":[144],"deformable":[145,155],"scanning.":[147],"Specifically,":[148],"after":[152],"convolution,":[153],"our":[154],"scanning":[156],"aggregates":[157],"these":[158],"within":[160],"while":[163],"selectively":[164],"preserving":[165],"useful":[166],"that":[168],"represent":[169],"This":[173],"approach":[174],"significantly":[175],"improves":[176],"accuracy":[178],"of":[179],"structured":[180],"HPE,":[182],"comparable":[184],"inference":[185],"speed":[186],"ResNet-50.":[188],"Our":[189],"experiments":[190],"involve":[191],"extensive":[192],"evaluations":[193],"five":[195],"divergent":[196],"datasets":[197,226],"including":[198,220],"single-hand":[199],"two-hand":[201],"scenarios,":[202],"hand-only":[203],"hand-object":[205],"interactions,":[206],"well":[208],"RGB":[210],"depth-based":[212],"estimation.":[213],"outperforms":[215],"latest":[217],"backbones,":[219],"VMamba":[221],"Spatial-Mamba,":[223],"all":[225],"achieves":[228],"state-of-the-art":[229],"performance.":[230]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-12-04T00:00:00"}