{"id":"https://openalex.org/W4407806377","doi":"https://doi.org/10.1109/iccv51701.2025.01152","title":"ModSkill: Physical Character Skill Modularization","display_name":"ModSkill: Physical Character Skill Modularization","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4407806377","doi":"https://doi.org/10.1109/iccv51701.2025.01152"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.14140","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057871003","display_name":"Yiming Huang","orcid":"https://orcid.org/0000-0001-8259-1681"},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiming Huang","raw_affiliation_strings":["University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059487131","display_name":"Zhiyang Dou","orcid":"https://orcid.org/0000-0003-0186-8269"},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiyang Dou","raw_affiliation_strings":["University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101996555","display_name":"Lingjie Liu","orcid":"https://orcid.org/0000-0002-5765-1213"},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lingjie Liu","raw_affiliation_strings":["University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36788626"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01718303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12394","last_page":"12404"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.847000002861023,"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"}},"topics":[{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.847000002861023,"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/character","display_name":"Character (mathematics)","score":0.8356696367263794},{"id":"https://openalex.org/keywords/modular-programming","display_name":"Modular programming","score":0.8296140432357788},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.43097391724586487},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2343462109565735},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1386685073375702},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.04725179076194763}],"concepts":[{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.8356696367263794},{"id":"https://openalex.org/C88482812","wikidata":"https://www.wikidata.org/wiki/Q6453666","display_name":"Modular programming","level":2,"score":0.8296140432357788},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43097391724586487},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2343462109565735},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1386685073375702},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.04725179076194763}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.14140","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.14140","pdf_url":"https://arxiv.org/pdf/2502.14140","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,"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.2502.14140","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.14140","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.14140","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.14140","pdf_url":"https://arxiv.org/pdf/2502.14140","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,"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2095911326","https://openalex.org/W2393702438","https://openalex.org/W2391644119","https://openalex.org/W2060456459","https://openalex.org/W2368574244","https://openalex.org/W2372613066","https://openalex.org/W2354835639"],"abstract_inverted_index":{"Human":[0],"motion":[1,35,58,122,153],"is":[2],"highly":[3],"diverse":[4,161],"and":[5,54,155],"dynamic,":[6],"posing":[7],"challenges":[8],"for":[9,19,32,80,104,160],"imitation":[10],"learning":[11,68,129,141],"algorithms":[12],"that":[13,71,92,100,137],"aim":[14],"to":[15,52,56,125],"generalize":[16,53],"motor":[17],"skills":[18,75,79],"controlling":[20],"simulated":[21],"characters.":[22],"Previous":[23],"methods":[24,149],"typically":[25],"rely":[26],"on":[27],"a":[28,39,65,87],"universal":[29],"full-body":[30,41,74,152],"controller":[31],"tracking":[33,132,154],"reference":[34],"(tracking-based":[36],"model)":[37],"or":[38],"unified":[40],"skill":[42,67,88,98,140,158],"embedding":[43],"space":[44],"(skill":[45],"embedding).":[46],"However,":[47],"these":[48],"approaches":[49],"often":[50],"struggle":[51],"scale":[55],"larger":[57],"datasets.":[59],"In":[60],"this":[61,138],"work,":[62],"we":[63],"introduce":[64],"novel":[66],"framework,":[69,142],"ModSkill,":[70],"decouples":[72],"complex":[73],"into":[76,96],"compositional,":[77],"modular":[78,97],"independent":[81],"body":[82,106],"parts.":[83],"Our":[84,134],"framework":[85],"features":[86],"modularization":[89],"attention":[90],"layer":[91],"processes":[93],"policy":[94,128],"observations":[95],"embeddings":[99,159],"guide":[101],"low-level":[102],"controllers":[103],"each":[105],"part.":[107],"We":[108],"also":[109],"propose":[110],"an":[111],"Active":[112],"Skill":[113],"Learning":[114],"approach":[115],"with":[116],"Generative":[117],"Adaptive":[118],"Sampling,":[119],"using":[120],"large":[121],"generation":[123],"models":[124],"adaptively":[126],"enhance":[127],"in":[130,150],"challenging":[131],"scenarios.":[133],"results":[135],"show":[136],"modularized":[139],"enhanced":[143],"by":[144],"generative":[145],"sampling,":[146],"outperforms":[147],"existing":[148],"precise":[151],"enables":[156],"reusable":[157],"goal-driven":[162],"tasks.":[163]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}