{"id":"https://openalex.org/W4385488496","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191560","title":"Accommodating Self-attentional Heterophily Topology into High- and Low-pass Graph Convolutional Network for Skeleton-based Action Recognition","display_name":"Accommodating Self-attentional Heterophily Topology into High- and Low-pass Graph Convolutional Network for Skeleton-based Action Recognition","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385488496","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191560"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191560","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191560","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100679851","display_name":"Chao Wei","orcid":"https://orcid.org/0000-0002-2278-7057"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Wei","raw_affiliation_strings":["Institute for Artificial Intelligence at Tsinghua University (THUAI), Tsinghua University,Beijing National Research Center for Information Science and Technology (BNRist), State Key Laboratory of Intelligent Technology and Systems,Department of Computer Science and Technology,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence at Tsinghua University (THUAI), Tsinghua University,Beijing National Research Center for Information Science and Technology (BNRist), State Key Laboratory of Intelligent Technology and Systems,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102011846","display_name":"Zhidong Deng","orcid":"https://orcid.org/0000-0001-9970-1023"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhidong Deng","raw_affiliation_strings":["Institute for Artificial Intelligence at Tsinghua University (THUAI), Tsinghua University,Beijing National Research Center for Information Science and Technology (BNRist), State Key Laboratory of Intelligent Technology and Systems,Department of Computer Science and Technology,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence at Tsinghua University (THUAI), Tsinghua University,Beijing National Research Center for Information Science and Technology (BNRist), State Key Laboratory of Intelligent Technology and Systems,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"08"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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":1.0,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9886000156402588,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9760000109672546,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.7300508618354797},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.6785385608673096},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5951366424560547},{"id":"https://openalex.org/keywords/homophily","display_name":"Homophily","score":0.553416907787323},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5517280101776123},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5338448286056519},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4929821491241455},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47028425335884094},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.45509645342826843},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.42146462202072144},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4029547870159149},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37840011715888977},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.3477782905101776},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14643722772598267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7300508618354797},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.6785385608673096},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5951366424560547},{"id":"https://openalex.org/C2779812341","wikidata":"https://www.wikidata.org/wiki/Q5891525","display_name":"Homophily","level":2,"score":0.553416907787323},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5517280101776123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5338448286056519},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4929821491241455},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47028425335884094},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.45509645342826843},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.42146462202072144},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4029547870159149},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37840011715888977},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.3477782905101776},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14643722772598267},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191560","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191560","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5541826327","display_name":null,"funder_award_id":"62176134","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1744759976","https://openalex.org/W2054041160","https://openalex.org/W2156303437","https://openalex.org/W2194775991","https://openalex.org/W2593146028","https://openalex.org/W2606294640","https://openalex.org/W2736334449","https://openalex.org/W2788778841","https://openalex.org/W2916106175","https://openalex.org/W2940457086","https://openalex.org/W2944006115","https://openalex.org/W2945848398","https://openalex.org/W2948058585","https://openalex.org/W2948246283","https://openalex.org/W2963076818","https://openalex.org/W2963524571","https://openalex.org/W2964015378","https://openalex.org/W2964097678","https://openalex.org/W2964134613","https://openalex.org/W2966210862","https://openalex.org/W2966859223","https://openalex.org/W2979683452","https://openalex.org/W3002552512","https://openalex.org/W3005644236","https://openalex.org/W3034999503","https://openalex.org/W3035050855","https://openalex.org/W3035225512","https://openalex.org/W3092462694","https://openalex.org/W3094502228","https://openalex.org/W3113067059","https://openalex.org/W3128443161","https://openalex.org/W3133964188","https://openalex.org/W3170841864","https://openalex.org/W3203634062","https://openalex.org/W4214612132","https://openalex.org/W4287757758","https://openalex.org/W4294618611","https://openalex.org/W4312744661","https://openalex.org/W4312757522","https://openalex.org/W4320060387","https://openalex.org/W4385245566","https://openalex.org/W6682864246","https://openalex.org/W6726873649","https://openalex.org/W6739901393","https://openalex.org/W6743197607","https://openalex.org/W6760001035","https://openalex.org/W6762480061","https://openalex.org/W6766929029","https://openalex.org/W6771621015","https://openalex.org/W6773226109","https://openalex.org/W6783485119","https://openalex.org/W6784094891","https://openalex.org/W6784333009","https://openalex.org/W6791149046"],"related_works":["https://openalex.org/W3185373886","https://openalex.org/W3010567961","https://openalex.org/W2588006872","https://openalex.org/W4385338594","https://openalex.org/W4200127153","https://openalex.org/W3119171992","https://openalex.org/W2011190096","https://openalex.org/W3175275009","https://openalex.org/W2036947108","https://openalex.org/W1971924293"],"abstract_inverted_index":{"In":[0],"the":[1,114,144,156],"scene":[2],"of":[3,30,146],"human":[4,17],"skeleton-based":[5,72],"action":[6,18,73,153,175],"recognition,":[7],"graph":[8,25,51],"convolutional":[9,52],"network":[10,53],"(GCN)":[11],"is":[12,27,122,137],"widely":[13],"applied":[14],"to":[15,56,90,112,124,142],"model":[16],"dynamics":[19],"and":[20,33,49,65,84,97,128,170,186],"achieves":[21],"extraordinary":[22],"results,":[23],"where":[24],"topology":[26],"in":[28,38,41,140],"charge":[29],"feature":[31],"extraction":[32,145],"plays":[34],"a":[35,46,118,129],"crucial":[36],"role":[37],"learning":[39],"representation":[40],"GCNs.":[42],"This":[43],"paper":[44],"presents":[45],"novel":[47],"high-":[48],"low-pass":[50],"(HLP-GCN),":[54],"aiming":[55],"effectively":[57],"aggregate":[58],"joint":[59],"features":[60,150],"based":[61],"on":[62,172],"learned":[63],"homophily":[64,83,104],"heterophily":[66,85,110],"topologies":[67,86,105,111],"using":[68],"self-attention":[69],"modules":[70],"for":[71,151],"recognition":[74,176],"tasks.":[75],"Specifically,":[76],"such":[77],"an":[78],"HLP-GCN":[79],"framework":[80],"first":[81],"learns":[82],"dynamically":[87],"so":[88],"as":[89],"capture":[91],"different":[92],"correlations":[93],"between":[94],"input":[95],"samples":[96],"then":[98],"combine":[99],"similar":[100],"information":[101],"arising":[102],"from":[103,109],"with":[106],"dissimilar":[107],"ones":[108],"get":[113],"final":[115],"embeddings.":[116],"Furthermore,":[117],"temporal":[119],"modeling":[120],"module":[121],"added":[123],"this":[125],"HLPGCN":[126],"framework,":[127],"new":[130],"pooling":[131],"strategy":[132],"called":[133],"global":[134],"node":[135],"(GNode)":[136],"cascaded":[138],"subsequently,":[139],"order":[141],"have":[143],"more":[147],"robust":[148],"spatiotemporal":[149],"skeleton":[152],"recognition.":[154],"Finally,":[155],"experimental":[157],"results":[158],"demonstrate":[159],"that":[160],"our":[161],"method":[162],"outperforms":[163],"previous":[164],"state-of-the-art":[165],"methods":[166],"by":[167],"0.2%,":[168],"0.4%,":[169],"0.3%":[171],"three":[173],"large-scale":[174],"datasets":[177],"including":[178],"NTU":[179,182],"RGB+D":[180,183],"X-Set,":[181],"120":[184],"X-Sub,":[185],"NW-UCLA,":[187],"respectively.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}