{"id":"https://openalex.org/W4414539767","doi":"https://doi.org/10.23919/mva65244.2025.11175125","title":"Modality Selection and Skill Segmentation via Cross-Modality Attention","display_name":"Modality Selection and Skill Segmentation via Cross-Modality Attention","publication_year":2025,"publication_date":"2025-07-26","ids":{"openalex":"https://openalex.org/W4414539767","doi":"https://doi.org/10.23919/mva65244.2025.11175125"},"language":"en","primary_location":{"id":"doi:10.23919/mva65244.2025.11175125","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mva65244.2025.11175125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 19th International Conference on Machine Vision and Applications (MVA)","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/A5102918834","display_name":"Jiawei Jiang","orcid":"https://orcid.org/0000-0003-0051-0046"},"institutions":[{"id":"https://openalex.org/I161296585","display_name":"Tokyo University of Science","ror":"https://ror.org/05sj3n476","country_code":"JP","type":"education","lineage":["https://openalex.org/I161296585"]},{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jiawei Jiang","raw_affiliation_strings":["Science Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science Tokyo","institution_ids":["https://openalex.org/I161296585","https://openalex.org/I4400009020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064968116","display_name":"Kei Ota","orcid":"https://orcid.org/0000-0002-5744-3027"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kei Ota","raw_affiliation_strings":["Mitsubishi Electric"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010530960","display_name":"Devesh K. Jha","orcid":"https://orcid.org/0000-0002-7843-9545"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Devesh K. Jha","raw_affiliation_strings":["MERL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MERL","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045505869","display_name":"Asako Kanezaki","orcid":"https://orcid.org/0000-0003-3217-1405"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Asako Kanezaki","raw_affiliation_strings":["Science Tokyo &amp; RIKEN AIP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science Tokyo &amp; RIKEN AIP","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14025","display_name":"Educational Technology and Assessment","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T14025","display_name":"Educational Technology and Assessment","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9045000076293945,"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/leverage","display_name":"Leverage (statistics)","score":0.7578999996185303},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6859999895095825},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6524999737739563},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.588699996471405},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5002999901771545},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.41440001130104065}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7578999996185303},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6859999895095825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6712999939918518},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6524999737739563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6463000178337097},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.588699996471405},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5002999901771545},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44940000772476196},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.41440001130104065},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.3695000112056732},{"id":"https://openalex.org/C26486553","wikidata":"https://www.wikidata.org/wiki/Q371870","display_name":"Stimulus modality","level":3,"score":0.34049999713897705},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.2709999978542328},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/mva65244.2025.11175125","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mva65244.2025.11175125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 19th International Conference on Machine Vision and Applications (MVA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W3128894241","https://openalex.org/W3145123113","https://openalex.org/W3189699967","https://openalex.org/W4312347618","https://openalex.org/W4385430497","https://openalex.org/W4385430633","https://openalex.org/W4401415072","https://openalex.org/W4402353985","https://openalex.org/W4402354045","https://openalex.org/W4403337227","https://openalex.org/W4405785482","https://openalex.org/W4413917725"],"related_works":[],"abstract_inverted_index":{"Incorporating":[0],"additional":[1],"sensory":[2],"modalities":[3,43],"such":[4],"as":[5],"tactile":[6],"and":[7,39,68],"audio":[8],"into":[9],"foundational":[10],"robotic":[11],"models":[12],"poses":[13],"significant":[14],"challenges":[15],"due":[16],"to":[17,37,61,72],"the":[18,42,57],"curse":[19],"of":[20,59,78],"dimensionality.":[21],"This":[22],"work":[23],"addresses":[24],"this":[25,70],"issue":[26],"through":[27],"modality":[28],"selection.":[29],"We":[30],"propose":[31],"a":[32,74],"cross-modality":[33],"attention":[34],"(CMA)":[35],"mechanism":[36],"identify":[38],"selectively":[40],"utilize":[41],"that":[44],"are":[45],"most":[46],"informative":[47],"for":[48],"action":[49],"generation":[50],"at":[51],"each":[52],"timestep.":[53],"Furthermore,":[54],"we":[55],"extend":[56],"application":[58],"CMA":[60],"segment":[62],"primitive":[63],"skills":[64],"from":[65],"expert":[66],"demonstrations":[67],"leverage":[69],"segmentation":[71],"train":[73],"hierarchical":[75],"policy":[76],"capable":[77],"solving":[79],"long-horizon,":[80],"contact-rich":[81],"manipulation":[82],"tasks.":[83]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
