{"id":"https://openalex.org/W7225160369","doi":"https://doi.org/10.48550/arxiv.2611.02685","title":"Geometry-Constrained Dynamic Hypergraph Convolutional Network with Contrastive Score Refinement for Skeleton-Based Action Recognition","display_name":"Geometry-Constrained Dynamic Hypergraph Convolutional Network with Contrastive Score Refinement for Skeleton-Based Action Recognition","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225160369","doi":"https://doi.org/10.48550/arxiv.2611.02685"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.02685","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02685","pdf_url":"https://arxiv.org/pdf/2611.02685","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.02685","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160516339","display_name":"Minh Ta Tran Nhat","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nhat, Minh Ta Tran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113391822","display_name":"Yuning Ye","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I163753206","display_name":"Chungbuk National University","ror":"https://ror.org/02wnxgj78","country_code":"KR","type":"education","lineage":["https://openalex.org/I163753206"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ye, Yuning","raw_affiliation_strings":["Department of Electronics Engineering Chungbuk National University Cheongju , South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics Engineering Chungbuk National University Cheongju , South Korea","institution_ids":["https://openalex.org/I163753206"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037234550","display_name":"Yuseok Ban","orcid":"https://orcid.org/0000-0003-1190-6863","observed_orcids":["https://orcid.org/0000-0003-1190-6863"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ban, Yuseok","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9990000128746033,"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":0.9990000128746033,"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":0.0003000000142492354,"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/T12290","display_name":"Human Motion and Animation","score":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/skeleton-based-action-recognition","display_name":"skeleton-based action recognition","score":1.0},{"id":"https://openalex.org/keywords/hypergraph-convolutional-network","display_name":"hypergraph convolutional network","score":0.8050000071525574},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.8820000290870667}],"concepts":[{"id":"https://openalex.org/C2781221856","wikidata":"https://www.wikidata.org/wiki/Q840247","display_name":"Hypergraph","level":2,"score":0.8648999929428101},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722599983215332},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6952999830245972},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.578499972820282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5238000154495239},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.42309999465942383},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.40689998865127563},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36719998717308044},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3248000144958496},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.31540000438690186},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.29679998755455017},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28119999170303345},{"id":"https://openalex.org/C2780186347","wikidata":"https://www.wikidata.org/wiki/Q11414","display_name":"Subnetwork","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C13540734","wikidata":"https://www.wikidata.org/wiki/Q5318996","display_name":"Dynamic network analysis","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.25949999690055847},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25200000405311584}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.02685","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02685","pdf_url":"https://arxiv.org/pdf/2611.02685","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.2611.02685","doi":"https://doi.org/10.48550/arxiv.2611.02685","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.02685","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:2611.02685","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02685","pdf_url":"https://arxiv.org/pdf/2611.02685","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":[{"id":"https://openalex.org/F4320321681","display_name":"Ministry of Trade, Industry and Energy","ror":"https://ror.org/008nkqk13"},{"id":"https://openalex.org/F4320322064","display_name":"Korea Institute for Advancement of Technology","ror":"https://ror.org/015w1qa96"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"},{"id":"https://openalex.org/F4320337407","display_name":"Division of Human Resource Development","ror":"https://ror.org/03mamvh39"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225160369.pdf","grobid_xml":"https://content.openalex.org/works/W7225160369.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4226350168","https://openalex.org/W4412924345","https://openalex.org/W7084043213","https://openalex.org/W4404035222","https://openalex.org/W4398762748","https://openalex.org/W4306177316","https://openalex.org/W4409094889","https://openalex.org/W3125955391","https://openalex.org/W7169782597","https://openalex.org/W7161634585"],"abstract_inverted_index":{"Skeleton-based":[0],"action":[1,77],"recognition":[2],"is":[3,84,188],"a":[4,69],"pivotal":[5],"task":[6],"in":[7,32],"computer":[8],"vision;":[9],"however,":[10],"conventional":[11],"Graph":[12],"Convolutional":[13,73],"Networks":[14],"(GCNs)":[15],"are":[16],"often":[17],"constrained":[18],"by":[19,121],"pairwise":[20,138],"joint":[21,61],"modeling,":[22],"which":[23,96],"fails":[24],"to":[25,40,57],"capture":[26,58],"the":[27,55,80,85,101,109,127,137,174],"intricate":[28],"high-order":[29],"interactions":[30],"inherent":[31],"human":[33],"movement.":[34],"While":[35],"recent":[36],"hypergraph-based":[37],"methods":[38],"attempt":[39],"address":[41],"this":[42,64],"limitation,":[43],"they":[44],"typically":[45],"rely":[46],"on":[47,165,181],"static":[48,130],"structures":[49],"derived":[50],"from":[51],"anatomical":[52],"priors,":[53],"lacking":[54],"flexibility":[56],"dynamic,":[59],"action-specific":[60,119,151],"correlations.":[62],"To":[63],"end,":[65],"we":[66],"propose":[67],"DyGCN,":[68,177],"Geometry-Constrained":[70,102],"Dynamic":[71,86,103],"Hypergraph":[72,87,104],"Network":[74,89],"for":[75],"skeleton-based":[76],"recognition.":[78],"At":[79],"core":[81],"of":[82,129,176],"DyGCN":[83],"Construction":[88,105],"with":[90,153],"Contrastive":[91,110],"Score":[92,111],"Refinement":[93,112],"(DyGCT)":[94],"block,":[95],"comprises":[97],"two":[98],"novel":[99],"components:":[100],"(GeoHC)":[106],"module":[107],"and":[108,171],"(CSR)":[113],"module.":[114],"Specifically,":[115],"GeoHC":[116],"dynamically":[117],"constructs":[118],"hyperedges":[120],"leveraging":[122],"geometry-constrained":[123],"second-order":[124],"compatibility,":[125],"transcending":[126],"limitations":[128],"hyperedge":[131],"structures.":[132],"Furthermore,":[133],"CSR":[134,158],"explicitly":[135],"refines":[136],"compatibility":[139],"scores":[140],"during":[141,161],"hypergraph":[142],"construction":[143],"through":[144],"prototype-based":[145],"contrastive":[146],"learning,":[147],"fostering":[148],"more":[149],"discriminative":[150],"hyperedges,":[152],"zero":[154],"inference-time":[155],"overhead":[156],"as":[157],"operates":[159],"only":[160],"training.":[162],"Extensive":[163],"experiments":[164],"NTU":[166,168],"RGB+D,":[167],"RGB+D":[169],"120,":[170],"Northwestern-UCLA":[172],"validate":[173],"effectiveness":[175],"achieving":[178],"state-of-the-art":[179],"performance":[180],"widely":[182],"used":[183],"benchmarks.":[184],"The":[185],"source":[186],"code":[187],"available":[189],"at":[190],"https://github.com/marvineta0405/DyGCN.":[191]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-04T00:00:00"}