{"id":"https://openalex.org/W2953626316","doi":"https://doi.org/10.1109/lra.2019.2926223","title":"Understanding Natural Language Instructions for Fetching Daily Objects Using GAN-Based Multimodal Target\u2013Source Classification","display_name":"Understanding Natural Language Instructions for Fetching Daily Objects Using GAN-Based Multimodal Target\u2013Source Classification","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2953626316","doi":"https://doi.org/10.1109/lra.2019.2926223","mag":"2953626316"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2019.2926223","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2019.2926223","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","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/A5039713129","display_name":"Aly Magassouba","orcid":"https://orcid.org/0000-0002-0895-5982"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Aly Magassouba","raw_affiliation_strings":["National Institute of Information and Communication Technology, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0895-5982","affiliations":[{"raw_affiliation_string":"National Institute of Information and Communication Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033744547","display_name":"Komei Sugiura","orcid":"https://orcid.org/0000-0002-0261-0510"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Komei Sugiura","raw_affiliation_strings":["National Institute of Information and Communication Technology, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0261-0510","affiliations":[{"raw_affiliation_string":"National Institute of Information and Communication Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020947045","display_name":"Anh Trinh Quoc","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Anh Trinh Quoc","raw_affiliation_strings":["National Institute of Information and Communication Technology, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communication Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114514387","display_name":"Hisashi Kawai","orcid":"https://orcid.org/0000-0002-0914-5092"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hisashi Kawai","raw_affiliation_strings":["National Institute of Information and Communication Technology, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communication Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":2.4379,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.91486112,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"4","issue":"4","first_page":"3884","last_page":"3891"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991000294685364,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991000294685364,"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/T10028","display_name":"Topic Modeling","score":0.998199999332428,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6808211803436279},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.6467846632003784},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4195248484611511},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3771698474884033},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3763439655303955},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0713491439819336}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6808211803436279},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.6467846632003784},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4195248484611511},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3771698474884033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3763439655303955},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0713491439819336},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2019.2926223","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2019.2926223","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1911553475","https://openalex.org/W1975804500","https://openalex.org/W2099471712","https://openalex.org/W2134199742","https://openalex.org/W2166912588","https://openalex.org/W2178768799","https://openalex.org/W2193945050","https://openalex.org/W2295848880","https://openalex.org/W2525778437","https://openalex.org/W2548275288","https://openalex.org/W2571175805","https://openalex.org/W2884805522","https://openalex.org/W2896457183","https://openalex.org/W2950776302","https://openalex.org/W2951523806","https://openalex.org/W2962716343","https://openalex.org/W2962899390","https://openalex.org/W2963244312","https://openalex.org/W2963250052","https://openalex.org/W2963341956","https://openalex.org/W2963470893","https://openalex.org/W2963922343","https://openalex.org/W2963951528","https://openalex.org/W2964284374","https://openalex.org/W4320013936","https://openalex.org/W6621378261","https://openalex.org/W6637373629","https://openalex.org/W6679797431","https://openalex.org/W6685777725","https://openalex.org/W6727690538","https://openalex.org/W6729482032","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0],"this":[1],"letter,":[2],"we":[3,51],"address":[4],"multimodal":[5,54],"language":[6],"understanding":[7],"with":[8,103],"unconstrained":[9],"fetching":[10,18],"instruction":[11,19],"for":[12],"domestic":[13],"service":[14],"robots.":[15],"A":[16],"typical":[17],"such":[20],"as":[21],"\u201cBring":[22],"me":[23],"the":[24,28,34,49,61,70,92],"yellow":[25],"toy":[26],"from":[27,44],"white":[29],"shelf\u201d":[30],"requires":[31],"to":[32,41],"infer":[33],"user":[35],"intention,":[36],"i.e.,":[37],"what":[38],"object":[39],"(target)":[40],"fetch":[42],"and":[43,66,83,107,112],"where":[45],"(source).":[46],"To":[47],"solve":[48],"task,":[50],"propose":[52],"a":[53,96],"target-source":[55],"classifier":[56],"model":[57],"(MTCM),":[58],"which":[59],"predicts":[60],"region-wise":[62,78],"likelihood":[63],"of":[64],"target":[65],"source":[67],"candidates":[68],"in":[69],"scene.":[71],"Unlike":[72],"other":[73],"methods,":[74],"MTCM":[75,102],"can":[76],"handle":[77],"classification":[79],"based":[80],"on":[81,95],"linguistic":[82],"visual":[84],"features.":[85],"We":[86,99],"evaluated":[87],"our":[88],"approach":[89],"that":[90],"outperformed":[91],"state-of-the-art":[93],"method":[94],"standard":[97],"dataset.":[98],"also":[100],"extended":[101],"generative":[104],"adversarial":[105],"nets,":[106],"enabled":[108],"simultaneous":[109],"data":[110],"augmentation":[111],"classification.":[113]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}