{"id":"https://openalex.org/W4416749663","doi":"https://doi.org/10.1109/iros60139.2025.11246883","title":"Body-Hand Modality Expertized Networks with Cross-attention for Fine-grained Skeleton Action Recognition","display_name":"Body-Hand Modality Expertized Networks with Cross-attention for Fine-grained Skeleton Action Recognition","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749663","doi":"https://doi.org/10.1109/iros60139.2025.11246883"},"language":"en","primary_location":{"id":"doi:10.1109/iros60139.2025.11246883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246883","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.14960","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072404294","display_name":"Sinyoung Cho","orcid":"https://orcid.org/0009-0000-7991-3715"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Seungyeon Cho","raw_affiliation_strings":["KAIST,School of Computing,South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,School of Computing,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100653775","display_name":"Tae-Kyun Kim","orcid":"https://orcid.org/0000-0001-5324-439X"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tae-Kyun Kim","raw_affiliation_strings":["KAIST,School of Computing,South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,School of Computing,South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5072404294"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":1.187,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85063592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"11614","last_page":"11621"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9677000045776367,"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":0.9677000045776367,"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/T11431","display_name":"Action Observation and Synchronization","score":0.0071000000461936,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.00419999985024333,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.6220999956130981},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5622000098228455},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5073999762535095},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.49959999322891235},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4970000088214874},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4244999885559082},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4074999988079071},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.36880001425743103}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7979999780654907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7598999738693237},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.6220999956130981},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5622000098228455},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5073999762535095},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.49959999322891235},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4970000088214874},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4244999885559082},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4074999988079071},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38929998874664307},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3774999976158142},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.36880001425743103},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.35030001401901245},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros60139.2025.11246883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246883","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.14960","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.14960","pdf_url":"https://arxiv.org/pdf/2503.14960","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.14960","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.14960","pdf_url":"https://arxiv.org/pdf/2503.14960","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":30,"referenced_works":["https://openalex.org/W2054041160","https://openalex.org/W2765433083","https://openalex.org/W2944006115","https://openalex.org/W2948058585","https://openalex.org/W2963076818","https://openalex.org/W2964134613","https://openalex.org/W3202237431","https://openalex.org/W3203634062","https://openalex.org/W4282943820","https://openalex.org/W4312245820","https://openalex.org/W4312622396","https://openalex.org/W4312757522","https://openalex.org/W4386065571","https://openalex.org/W4386076379","https://openalex.org/W4386076633","https://openalex.org/W4389665476","https://openalex.org/W4390871806","https://openalex.org/W4390873451","https://openalex.org/W4393154834","https://openalex.org/W4393170627","https://openalex.org/W4402660128","https://openalex.org/W4402716112","https://openalex.org/W4402716188","https://openalex.org/W4402727383","https://openalex.org/W4402916965","https://openalex.org/W4403081605","https://openalex.org/W4404439889","https://openalex.org/W4405786102","https://openalex.org/W4413146191","https://openalex.org/W4413147259"],"related_works":[],"abstract_inverted_index":{"Skeleton-based":[0],"Human":[1],"Action":[2],"Recognition":[3,90],"(HAR)":[4],"is":[5,130],"a":[6,39,92,97,102,121,125,138],"vital":[7],"technology":[8],"in":[9,120,202],"robotics":[10],"and":[11,23,47,69,73,137,145,190,208],"human\u2013robot":[12],"interaction.":[13],"However,":[14],"most":[15],"existing":[16],"methods":[17],"concentrate":[18],"primarily":[19],"on":[20,180],"full-body":[21],"movements":[22],"often":[24,58],"overlook":[25],"subtle":[26,77],"hand":[27,61,70],"motions":[28],"that":[29,43,95,115,193],"are":[30],"critical":[31],"for":[32],"distinguishing":[33],"fine-grained":[34],"actions.":[35],"Recent":[36],"work":[37],"leverages":[38],"unified":[40,213],"graph":[41],"representation":[42],"combines":[44],"body,":[45],"hand,":[46],"foot":[48],"keypoints":[49],"to":[50,64,141,161,174,200],"capture":[51,175],"detailed":[52],"body":[53,68,169],"dynamics.":[54],"Yet,":[55],"these":[56],"models":[57],"blur":[59],"fine":[60],"details":[62],"due":[63],"the":[65,74,80,156,211],"disparity":[66],"between":[67],"action":[71,89],"characteristics":[72],"loss":[75,114],"of":[76,124,158],"features":[78,170],"during":[79],"spatial-pooling.":[81],"In":[82],"this":[83],"paper,":[84],"we":[85,153],"propose":[86],"BHaRNet":[87,194],"(Body\u2013Hand":[88],"Network),":[91],"novel":[93],"framework":[94],"augments":[96],"typical":[98],"body-expert":[99],"model":[100,106],"with":[101,111],"hand-expert":[103],"model.":[104],"Our":[105],"jointly":[107],"trains":[108],"both":[109],"streams":[110],"an":[112,133],"ensemble":[113],"fosters":[116],"cooperative":[117],"specialization,":[118],"functioning":[119],"manner":[122],"reminiscent":[123],"Mixture-of-Experts":[126],"(MoE).":[127],"Moreover,":[128],"cross-attention":[129],"employed":[131],"via":[132],"expertized":[134],"branch":[135],"method":[136],"pooling-attention":[139],"module":[140],"enable":[142],"feature-level":[143],"interactions":[144],"selectively":[146],"fuse":[147],"complementary":[148],"information.":[149],"Inspired":[150],"by":[151,164],"MMNet,":[152],"also":[154],"demonstrate":[155,192],"applicability":[157],"our":[159],"approach":[160],"multi-modal":[162],"tasks":[163],"leveraging":[165],"RGB":[166,172],"information,":[167],"where":[168],"guide":[171],"learning":[173],"richer":[176],"contextual":[177],"cues.":[178],"Experiments":[179],"large-scale":[181],"benchmarks":[182],"(NTU":[183],"RGB+D":[184,187],"60,":[185],"NTU":[186],"120,":[188],"PKU-MMD,":[189],"Northwestern-UCLA)":[191],"achieves":[195],"SOTA":[196],"accuracies\u2014improving":[197],"from":[198],"86.4%":[199],"93.0%":[201],"hand-intensive":[203],"actions\u2014while":[204],"maintaining":[205],"fewer":[206],"GFLOPs":[207],"parameters":[209],"than":[210],"relevant":[212],"methods.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}