{"id":"https://openalex.org/W2998552463","doi":"https://doi.org/10.1109/lra.2019.2963649","title":"A Multimodal Target-Source Classifier With Attention Branches to Understand Ambiguous Instructions for Fetching Daily Objects","display_name":"A Multimodal Target-Source Classifier With Attention Branches to Understand Ambiguous Instructions for Fetching Daily Objects","publication_year":2020,"publication_date":"2020-01-03","ids":{"openalex":"https://openalex.org/W2998552463","doi":"https://doi.org/10.1109/lra.2019.2963649","mag":"2998552463"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2019.2963649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2019.2963649","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, 3-5 Hikaridai, Seika, Soraku, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0895-5982","affiliations":[{"raw_affiliation_string":"National Institute of Information and Communication Technology, 3-5 Hikaridai, Seika, Soraku, 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, 3-5 Hikaridai, Seika, Soraku, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0261-0510","affiliations":[{"raw_affiliation_string":"National Institute of Information and Communication Technology, 3-5 Hikaridai, Seika, Soraku, 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, 3-5 Hikaridai, Seika, Soraku, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communication Technology, 3-5 Hikaridai, Seika, Soraku, 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":1.2458,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.81630947,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"5","issue":"2","first_page":"532","last_page":"539"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9984999895095825,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9972000122070312,"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":0.7638218402862549},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.608745813369751},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5556219816207886},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.4728287160396576},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4592745900154114},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.446757048368454},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.430730938911438},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4294228255748749},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3460674285888672}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7638218402862549},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.608745813369751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5556219816207886},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.4728287160396576},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4592745900154114},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.446757048368454},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.430730938911438},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4294228255748749},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3460674285888672},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2019.2963649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2019.2963649","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":[{"id":"https://metadata.un.org/sdg/4","score":0.8299999833106995,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2367706801","display_name":"Adversarial Data Augmentation for Multimodal Language Understanding","funder_award_id":"20H04269","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W287022735","https://openalex.org/W1514535095","https://openalex.org/W1895577753","https://openalex.org/W1933349210","https://openalex.org/W1964686234","https://openalex.org/W1975804500","https://openalex.org/W2193945050","https://openalex.org/W2194775991","https://openalex.org/W2295107390","https://openalex.org/W2295848880","https://openalex.org/W2571175805","https://openalex.org/W2785892019","https://openalex.org/W2896457183","https://openalex.org/W2953626316","https://openalex.org/W2962716343","https://openalex.org/W2962858109","https://openalex.org/W2963080533","https://openalex.org/W2963176022","https://openalex.org/W2963244312","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963811535","https://openalex.org/W2963922343","https://openalex.org/W2963954913","https://openalex.org/W2964284374","https://openalex.org/W2964345792","https://openalex.org/W2966683369","https://openalex.org/W2970597249","https://openalex.org/W2972769995","https://openalex.org/W3003575346","https://openalex.org/W3030476822","https://openalex.org/W3034636873","https://openalex.org/W4385245566","https://openalex.org/W6630875275","https://openalex.org/W6697833488","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6762207533","https://openalex.org/W6762982116","https://openalex.org/W6763701032","https://openalex.org/W6765240608","https://openalex.org/W6767502062"],"related_works":["https://openalex.org/W2353179089","https://openalex.org/W2923538289","https://openalex.org/W2353125546","https://openalex.org/W2470643824","https://openalex.org/W2349635380","https://openalex.org/W2353819554","https://openalex.org/W2359488321","https://openalex.org/W2389866386","https://openalex.org/W1516679419","https://openalex.org/W190396239"],"abstract_inverted_index":{"In":[0,132],"this":[1],"study,":[2],"we":[3,77],"focus":[4],"on":[5,110,139,146],"multimodal":[6,80,106],"language":[7],"understanding":[8],"for":[9],"fetching":[10],"instructions":[11],"in":[12],"the":[13,29,42,46,54,60,79,93,98,123,130,134,147],"domestic":[14],"service":[15],"robots":[16],"context.":[17],"This":[18,49],"task":[19],"consists":[20],"of":[21,53,56,92],"predicting":[22],"a":[23,75,105,118],"target":[24],"object,":[25],"as":[26,39],"instructed":[27],"by":[28],"user,":[30],"given":[31],"an":[32,35,90],"image":[33],"and":[34,112,129],"unstructured":[36],"sentence,":[37],"such":[38,74],"\u201cBring":[40],"me":[41],"yellow":[43],"box":[44],"(from":[45],"wooden":[47],"cabinet).\u201d":[48],"is":[50,89],"challenging":[51],"because":[52],"ambiguity":[55],"natural":[57],"language,":[58],"i.e.,":[59],"relevant":[61],"information":[62],"may":[63],"be":[64,69],"missing":[65],"or":[66],"there":[67],"might":[68],"several":[70],"candidates.":[71],"To":[72],"solve":[73],"task,":[76],"propose":[78],"target-source":[81],"classifier":[82],"model":[83],"with":[84],"attention":[85,99,107],"branches":[86],"(MTCMAB),":[87],"which":[88],"extension":[91],"MTCM.":[94,131],"Our":[95],"methodology":[96],"uses":[97],"branch":[100],"network":[101],"(ABN)":[102],"to":[103],"develop":[104],"mechanism":[108],"based":[109],"linguistic":[111],"visual":[113],"inputs.":[114],"Experimental":[115],"validation":[116],"using":[117],"standard":[119],"dataset":[120],"showed":[121],"that":[122],"MTCM-AB":[124,135],"outperformed":[125],"both":[126],"state-of-the-art":[127],"methods":[128],"particular,":[133],"accuracy":[136],"was":[137,144],"90.1%":[138],"average":[140],"while":[141],"human":[142],"performance":[143],"90.3%":[145],"PFN-PIC":[148],"dataset.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":9}],"updated_date":"2026-07-09T07:52:08.696243","created_date":"2025-10-10T00:00:00"}