{"id":"https://openalex.org/W4415708134","doi":"https://doi.org/10.1109/icme59968.2025.11209858","title":"Mobile-StereoHPE: Real-Time Mobile 3D Hand Pose Estimation from Stereo Gray Images","display_name":"Mobile-StereoHPE: Real-Time Mobile 3D Hand Pose Estimation from Stereo Gray Images","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708134","doi":"https://doi.org/10.1109/icme59968.2025.11209858"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5101671477","display_name":"Dongfang Zhao","orcid":"https://orcid.org/0000-0002-0677-634X"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dongfang Zhao","raw_affiliation_strings":["Samsung Semiconductor Inc.,San Diego,USA"],"affiliations":[{"raw_affiliation_string":"Samsung Semiconductor Inc.,San Diego,USA","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088099537","display_name":"Menghe Zhang","orcid":"https://orcid.org/0000-0001-8681-4889"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Menghe Zhang","raw_affiliation_strings":["Samsung Semiconductor Inc.,San Diego,USA"],"affiliations":[{"raw_affiliation_string":"Samsung Semiconductor Inc.,San Diego,USA","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039560728","display_name":"Yangwen Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yangwen Liang","raw_affiliation_strings":["Samsung Semiconductor Inc.,San Diego,USA"],"affiliations":[{"raw_affiliation_string":"Samsung Semiconductor Inc.,San Diego,USA","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064680456","display_name":"Shuangquan Wang","orcid":"https://orcid.org/0000-0002-3967-9693"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuangquan Wang","raw_affiliation_strings":["Samsung Semiconductor Inc.,San Diego,USA"],"affiliations":[{"raw_affiliation_string":"Samsung Semiconductor Inc.,San Diego,USA","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113919277","display_name":"Kee-Bong Song","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kee-Bong Song","raw_affiliation_strings":["Samsung Semiconductor Inc.,San Diego,USA"],"affiliations":[{"raw_affiliation_string":"Samsung Semiconductor Inc.,San Diego,USA","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100448779","display_name":"Donghoon Kim","orcid":"https://orcid.org/0000-0002-3034-1231"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]},{"id":"https://openalex.org/I4210088807","display_name":"Samsung Pharm (South Korea)","ror":"https://ror.org/003eds368","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210088807"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Donghoon Kim","raw_affiliation_strings":["Samsung Electronics,Hwaseong-si,South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics,Hwaseong-si,South Korea","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I4210088807"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101671477"],"corresponding_institution_ids":["https://openalex.org/I4210101778"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33748383,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9448999762535095,"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":0.9448999762535095,"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":0.025699999183416367,"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":0.010499999858438969,"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/pose","display_name":"Pose","score":0.7268999814987183},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5867999792098999},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.5774999856948853},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47429999709129333},{"id":"https://openalex.org/keywords/stereopsis","display_name":"Stereopsis","score":0.4456999897956848},{"id":"https://openalex.org/keywords/stereo-image","display_name":"Stereo image","score":0.445499986410141},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4163999855518341},{"id":"https://openalex.org/keywords/feature-tracking","display_name":"Feature tracking","score":0.3610000014305115}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8230999708175659},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7633000016212463},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.7268999814987183},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6887999773025513},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5867999792098999},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.5774999856948853},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47429999709129333},{"id":"https://openalex.org/C68537008","wikidata":"https://www.wikidata.org/wiki/Q247932","display_name":"Stereopsis","level":2,"score":0.4456999897956848},{"id":"https://openalex.org/C2987632653","wikidata":"https://www.wikidata.org/wiki/Q7611220","display_name":"Stereo image","level":3,"score":0.445499986410141},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C2987395694","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Feature tracking","level":3,"score":0.3610000014305115},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C166275286","wikidata":"https://www.wikidata.org/wiki/Q190095","display_name":"Gray (unit)","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.29339998960494995},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.29280000925064087},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C158829959","wikidata":"https://www.wikidata.org/wiki/Q1640606","display_name":"Monocular vision","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2941359057","https://openalex.org/W2973857456","https://openalex.org/W3107825842","https://openalex.org/W3108655343","https://openalex.org/W3171333242","https://openalex.org/W3215845947","https://openalex.org/W4225319257","https://openalex.org/W4312395531","https://openalex.org/W4313342377","https://openalex.org/W4382457421","https://openalex.org/W4386065390","https://openalex.org/W4386076685","https://openalex.org/W4394625766","https://openalex.org/W4402715855","https://openalex.org/W4411245194"],"related_works":[],"abstract_inverted_index":{"Mobile":[0],"XR":[1,139],"scenarios":[2],"pose":[3,54],"significant":[4],"challenges":[5],"for":[6,39,50,137],"3D":[7,14,28,52,116],"bare-hand":[8],"interaction,":[9],"requiring":[10],"accurate":[11],"and":[12,47,80,119],"low-latency":[13],"hand":[15,29,53],"tracking":[16],"within":[17],"strict":[18],"computational":[19,78],"constraints.":[20],"Monocular":[21],"RGB-based":[22],"methods":[23],"struggle":[24],"with":[25,107],"estimating":[26],"absolute":[27,51],"joints,":[30],"while":[31,76],"depth":[32],"sensor":[33],"or":[34],"large-model":[35,127],"approaches":[36],"are":[37],"unsuitable":[38],"mobile":[40],"devices.":[41],"We":[42],"propose":[43],"Mobile-StereoHPE,":[44],"a":[45,66,81,112],"lightweight":[46],"efficient":[48],"framework":[49],"estimation":[55],"using":[56],"stereo":[57,73],"gray":[58],"images.":[59],"Our":[60],"approach":[61],"introduces":[62],"two":[63],"novel":[64],"components:":[65],"Feature":[67,83],"Fusion":[68],"Module":[69],"(FFM)":[70],"that":[71,87],"aggregates":[72],"image":[74],"features":[75],"minimizing":[77],"overhead,":[79],"Cross":[82],"Attention":[84],"(CFA)":[85],"module":[86],"enhances":[88],"inter-view":[89],"correspondence":[90],"learning.":[91],"These":[92],"innovations":[93],"empower":[94],"our":[95],"compact":[96],"CNN":[97],"backbone":[98],"to":[99],"achieve":[100],"state-of-the-art":[101],"accuracy":[102],"on":[103],"the":[104,108,123],"MVHand":[105],"benchmark":[106],"smallest":[109],"model":[110],"size,":[111],"33%":[113],"improvement":[114],"in":[115],"joint":[117],"accuracy,":[118],"more":[120],"than":[121],"twice":[122],"speed":[124],"of":[125],"current":[126],"methods.":[128],"Extensive":[129],"experiments":[130],"validate":[131],"Mobile-StereoHPE":[132],"as":[133],"an":[134],"ideal":[135],"solution":[136],"next-generation":[138],"applications.":[140]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}