{"id":"https://openalex.org/W4413155897","doi":"https://doi.org/10.1109/cvpr52734.2025.00093","title":"HOP: Heterogeneous Topology-based Multimodal Entanglement for Co-Speech Gesture Generation","display_name":"HOP: Heterogeneous Topology-based Multimodal Entanglement for Co-Speech Gesture Generation","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413155897","doi":"https://doi.org/10.1109/cvpr52734.2025.00093"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":null,"display_name":"Hongye Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I36819085","display_name":"Northwest University","ror":"https://ror.org/00y7snj24","country_code":"US","type":"education","lineage":["https://openalex.org/I36819085"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongye Cheng","raw_affiliation_strings":["Northwest A&F University,College of Mechanical and Electronic Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwest A&F University,College of Mechanical and Electronic Engineering","institution_ids":["https://openalex.org/I36819085"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100417437","display_name":"Tianyu Wang","orcid":"https://orcid.org/0000-0003-0388-326X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210164150","display_name":"Shanghai Center for Brain Science and Brain-Inspired Technology","ror":"https://ror.org/0551a0y31","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210164150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyu Wang","raw_affiliation_strings":["Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University","institution_ids":["https://openalex.org/I4210164150","https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033166659","display_name":"Guangsi Shi","orcid":"https://orcid.org/0000-0003-0313-6379"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Guangsi Shi","raw_affiliation_strings":["Faculty of Engineering, Monash University,Department of Chemical and Biological Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Monash University,Department of Chemical and Biological Engineering","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zexing Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I36819085","display_name":"Northwest University","ror":"https://ror.org/00y7snj24","country_code":"US","type":"education","lineage":["https://openalex.org/I36819085"]},{"id":"https://openalex.org/I4210088176","display_name":"North West Agriculture and Forestry University","ror":null,"country_code":"CN","type":null,"lineage":["https://openalex.org/I4210088176"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zexing Zhao","raw_affiliation_strings":["College of Information Engineering, Northwest A&F University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Engineering, Northwest A&F University","institution_ids":["https://openalex.org/I36819085","https://openalex.org/I4210088176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084959430","display_name":"Yanwei Fu","orcid":"https://orcid.org/0000-0002-6595-6893"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwei Fu","raw_affiliation_strings":["School of Data Science, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"906","last_page":"916"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9968000054359436,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9968000054359436,"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"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9929999709129333,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9797999858856201,"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/quantum-entanglement","display_name":"Quantum entanglement","score":0.7188397645950317},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.7160452604293823},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6742317080497742},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.5311333537101746},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4328201413154602},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.421207457780838},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2370789647102356},{"id":"https://openalex.org/keywords/quantum","display_name":"Quantum","score":0.14272519946098328},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11883950233459473},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11464276909828186},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10513827204704285}],"concepts":[{"id":"https://openalex.org/C121040770","wikidata":"https://www.wikidata.org/wiki/Q215675","display_name":"Quantum entanglement","level":3,"score":0.7188397645950317},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.7160452604293823},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6742317080497742},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.5311333537101746},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4328201413154602},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.421207457780838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2370789647102356},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.14272519946098328},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11883950233459473},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11464276909828186},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10513827204704285},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W215088529","https://openalex.org/W1563542286","https://openalex.org/W1969681536","https://openalex.org/W1988932066","https://openalex.org/W2007337857","https://openalex.org/W2011611983","https://openalex.org/W2024536104","https://openalex.org/W2046909118","https://openalex.org/W2138147384","https://openalex.org/W2736431578","https://openalex.org/W2767290858","https://openalex.org/W2950361482","https://openalex.org/W2962795401","https://openalex.org/W2965341826","https://openalex.org/W2967443589","https://openalex.org/W2982625143","https://openalex.org/W2996570742","https://openalex.org/W3035588244","https://openalex.org/W3083173864","https://openalex.org/W3096831136","https://openalex.org/W3110095664","https://openalex.org/W3118288752","https://openalex.org/W3174836262","https://openalex.org/W3176463841","https://openalex.org/W3188493377","https://openalex.org/W3212693919","https://openalex.org/W4221142137","https://openalex.org/W4230312136","https://openalex.org/W4230429791","https://openalex.org/W4292945985","https://openalex.org/W4312674262","https://openalex.org/W4319079591","https://openalex.org/W4364377334","https://openalex.org/W4372349426","https://openalex.org/W4385764101","https://openalex.org/W4386076103","https://openalex.org/W4386142010","https://openalex.org/W4387421378","https://openalex.org/W4393157525","https://openalex.org/W4395450059","https://openalex.org/W4399039789","https://openalex.org/W4400001890","https://openalex.org/W4402727140","https://openalex.org/W4402727590","https://openalex.org/W4404356490"],"related_works":["https://openalex.org/W2537963312","https://openalex.org/W2066003895","https://openalex.org/W2349788282","https://openalex.org/W577271088","https://openalex.org/W2120801881","https://openalex.org/W1982853263","https://openalex.org/W1974473538","https://openalex.org/W2020010749","https://openalex.org/W2796116650","https://openalex.org/W2954779189"],"abstract_inverted_index":{"Co-speech":[0],"gestures":[1],"are":[2,167],"crucial":[3],"non-verbal":[4],"cues":[5],"that":[6,72,149],"enhance":[7,106],"speech":[8],"clarity":[9],"and":[10,38,49,82,102,137,157,165],"expressiveness":[11],"in":[12,20,30,35,140],"human":[13],"communication,":[14],"which":[15,120],"have":[16,27],"attracted":[17],"increasing":[18],"attention":[19],"multimodal":[21,47,63],"research.":[22],"While":[23],"the":[24,74,86,98,111,129,141],"existing":[25],"methods":[26],"made":[28],"strides":[29],"gesture":[31,70,78,160],"accuracy,":[32],"challenges":[33],"remain":[34],"generating":[36],"diverse":[37],"coherent":[39],"gestures,":[40],"as":[41],"most":[42],"approaches":[43],"assume":[44],"independence":[45],"among":[46],"inputs":[48],"lack":[50],"explicit":[51],"modeling":[52],"of":[53,88,100,143],"their":[54],"interactions.":[55],"In":[56],"this":[57],"work,":[58],"we":[59,96,109],"propose":[60],"a":[61,117],"novel":[62],"learning":[64],"method":[65],"named":[66],"HOP":[67,150],"for":[68,123],"co-speech":[69,159],"generation":[71,87],"captures":[73],"heterogeneous":[75],"entanglement":[76],"between":[77],"motion,":[79],"audio":[80,101],"rhythm,":[81],"text":[83],"semantics,":[84],"enabling":[85],"coordinated":[89],"gestures.":[90],"By":[91],"leveraging":[92],"spatiotemporal":[93],"graph":[94],"modeling,":[95],"achieve":[97],"alignment":[99],"action.":[103],"Moreover,":[104],"to":[105,132],"modality":[107],"coherence,":[108],"build":[110],"audio-text":[112],"semantic":[113],"representation":[114],"based":[115],"on":[116],"reprogramming":[118],"module,":[119],"is":[121],"beneficial":[122],"cross-modality":[124],"adaptation.":[125],"Our":[126],"approach":[127],"enables":[128],"trimodal":[130],"system":[131],"learn":[133],"each":[134],"other\u2019s":[135],"features":[136],"represent":[138],"them":[139],"form":[142],"topological":[144],"entanglement.":[145],"Extensive":[146],"experiments":[147],"demonstrate":[148],"achieves":[151],"state-of-the-art":[152],"performance,":[153],"offering":[154],"more":[155],"natural":[156],"expressive":[158],"generation.":[161],"More":[162],"information,":[163],"codes,":[164],"demos":[166],"available":[168],"here:":[169],"https://star-uu-wang.github.io/HOP/.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}