{"id":"https://openalex.org/W4415398970","doi":"https://doi.org/10.1109/icdl63968.2025.11204446","title":"Probabilistic Fusion of Deictic Gestures and Language Command: A Benchmark Dataset and Baseline Methods","display_name":"Probabilistic Fusion of Deictic Gestures and Language Command: A Benchmark Dataset and Baseline Methods","publication_year":2025,"publication_date":"2025-09-16","ids":{"openalex":"https://openalex.org/W4415398970","doi":"https://doi.org/10.1109/icdl63968.2025.11204446"},"language":null,"primary_location":{"id":"doi:10.1109/icdl63968.2025.11204446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl63968.2025.11204446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Development and Learning (ICDL)","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/A5120084054","display_name":"Michal Mikeska","orcid":null},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Michal Mikeska","raw_affiliation_strings":["Czech Technical University in Prague,Faculty of Electrical Engineering,Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Technical University in Prague,Faculty of Electrical Engineering,Czech Republic","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065125599","display_name":"Karla \u0160t\u011bp\u00e1nov\u00e1","orcid":"https://orcid.org/0000-0003-4239-2092"},"institutions":[{"id":"https://openalex.org/I4210152232","display_name":"Institute of Informatics of the Slovak Academy of Sciences","ror":"https://ror.org/04jgqpc26","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]},{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ","SK"],"is_corresponding":false,"raw_author_name":"Karla Stepanova","raw_affiliation_strings":["Czech Institute of Informatics Robotics and Cybernetics (CIIRC), Czech Technical University in Prague,Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Institute of Informatics Robotics and Cybernetics (CIIRC), Czech Technical University in Prague,Czech Republic","institution_ids":["https://openalex.org/I4210152232","https://openalex.org/I44504214"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25793499,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9380000233650208,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9380000233650208,"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/gesture","display_name":"Gesture","score":0.8373000025749207},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7110999822616577},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6593000292778015},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6054999828338623},{"id":"https://openalex.org/keywords/deixis","display_name":"Deixis","score":0.5634999871253967},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.517799973487854},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4593999981880188},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.4471000134944916}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8373000025749207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483999729156494},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7110999822616577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.666700005531311},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6593000292778015},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6054999828338623},{"id":"https://openalex.org/C13077596","wikidata":"https://www.wikidata.org/wiki/Q340015","display_name":"Deixis","level":2,"score":0.5634999871253967},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.517799973487854},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5058000087738037},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4593999981880188},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45739999413490295},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.4471000134944916},{"id":"https://openalex.org/C2982962833","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information fusion","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.3424000144004822},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29330000281333923},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.28220000863075256},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdl63968.2025.11204446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl63968.2025.11204446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1985752789","https://openalex.org/W2619383789","https://openalex.org/W4386071707","https://openalex.org/W4402727885","https://openalex.org/W4413948551"],"related_works":[],"abstract_inverted_index":{"Human":[0],"communication":[1],"relies":[2],"on":[3],"multiple":[4],"modal-ities-language,":[5],"gestures,":[6,85],"facial":[7],"expressions,":[8],"and":[9,32,51,58,82,110,116,139],"more-each":[10],"conveying":[11],"different":[12,92,102],"types":[13],"of":[14,75,137],"information":[15,47,107],"over":[16],"varying":[17,76],"time":[18],"scales.":[19],"Over":[20],"time,":[21],"humans":[22],"gradually":[23,131],"learn":[24],"to":[25,29,45],"integrate":[26],"these":[27,126],"modalities":[28,128],"understand":[30],"others":[31],"interpret":[33],"their":[34],"commands.":[35],"While":[36],"recent":[37],"advances":[38],"in":[39,61],"machine":[40],"learning":[41,93],"have":[42],"enabled":[43],"robots":[44],"fuse":[46],"from":[48,108],"images,":[49],"videos,":[50],"language":[52,80,109],"commands,":[53],"effectively":[54],"integrating":[55],"human":[56],"gestures":[57,112],"linguistic":[59],"instructions":[60],"real-world":[62],"scenarios":[63],"remains":[64],"a":[65,72],"challenge.":[66],"In":[67],"this":[68,96],"paper,":[69],"we":[70,98,120],"present":[71],"simulated":[73],"dataset":[74],"complexity,":[77],"including":[78],"ambiguous":[79,83,106],"commands":[81],"pointing":[84,111],"which":[86],"might":[87],"be":[88,130],"used":[89],"for":[90,104],"evaluating":[91],"approaches.":[94],"On":[95],"dataset,":[97],"quantitatively":[99],"compare":[100],"3":[101],"approaches":[103],"combining":[105],"-":[113],"both":[114],"learning-based":[115],"deterministic":[117],"ones.":[118],"Furthermore,":[119],"demonstrate":[121],"how":[122],"the":[123],"mapping":[124],"between":[125],"two":[127],"can":[129],"learned":[132],"with":[133],"an":[134],"increasing":[135],"number":[136],"observations":[138],"samples.":[140]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-22T00:00:00"}