{"id":"https://openalex.org/W4407168536","doi":"https://doi.org/10.1109/lra.2025.3539086","title":"Mobile Manipulation Instruction Generation From Multiple Images With Automatic Metric Enhancement","display_name":"Mobile Manipulation Instruction Generation From Multiple Images With Automatic Metric Enhancement","publication_year":2025,"publication_date":"2025-02-05","ids":{"openalex":"https://openalex.org/W4407168536","doi":"https://doi.org/10.1109/lra.2025.3539086"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3539086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3539086","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/A5109157979","display_name":"Keizo Katsumata","orcid":null},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kei Katsumata","raw_affiliation_strings":["Keio University, Yokohama, Kanagawa, Japan"],"raw_orcid":"https://orcid.org/0009-0009-7078-457X","affiliations":[{"raw_affiliation_string":"Keio University, Yokohama, Kanagawa, Japan","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030254193","display_name":"Motonari Kambara","orcid":"https://orcid.org/0000-0002-1991-9119"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Motonari Kambara","raw_affiliation_strings":["Keio University, Yokohama, Kanagawa, Japan"],"raw_orcid":"https://orcid.org/0000-0002-1991-9119","affiliations":[{"raw_affiliation_string":"Keio University, Yokohama, Kanagawa, Japan","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115637817","display_name":"Daichi Yashima","orcid":null},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daichi Yashima","raw_affiliation_strings":["Keio University, Yokohama, Kanagawa, Japan"],"raw_orcid":"https://orcid.org/0009-0005-2087-2038","affiliations":[{"raw_affiliation_string":"Keio University, Yokohama, Kanagawa, Japan","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092489705","display_name":"Ryosuke Korekata","orcid":"https://orcid.org/0009-0008-0354-9070"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryosuke Korekata","raw_affiliation_strings":["Keio University, Yokohama, Kanagawa, Japan"],"raw_orcid":"https://orcid.org/0009-0008-0354-9070","affiliations":[{"raw_affiliation_string":"Keio University, Yokohama, Kanagawa, Japan","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033744547","display_name":"Komei Sugiura","orcid":"https://orcid.org/0000-0002-0261-0510"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Komei Sugiura","raw_affiliation_strings":["Keio University, Yokohama, Kanagawa, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0261-0510","affiliations":[{"raw_affiliation_string":"Keio University, Yokohama, Kanagawa, Japan","institution_ids":["https://openalex.org/I203951103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5109157979"],"corresponding_institution_ids":["https://openalex.org/I203951103"],"apc_list":null,"apc_paid":null,"fwci":1.0999,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.73441469,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"10","issue":"3","first_page":"3022","last_page":"3029"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11245","display_name":"Advanced Numerical Analysis Techniques","score":0.9805999994277954,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9728999733924866,"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/computer-science","display_name":"Computer science","score":0.6348443031311035},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5626634955406189},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5158552527427673},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5153307318687439},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.36626559495925903},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09405681490898132}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6348443031311035},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5626634955406189},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5158552527427673},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5153307318687439},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.36626559495925903},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09405681490898132},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3539086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3539086","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1956340063","https://openalex.org/W2193945050","https://openalex.org/W2506483933","https://openalex.org/W2963084599","https://openalex.org/W2964339842","https://openalex.org/W2965373594","https://openalex.org/W2972544311","https://openalex.org/W3034578524","https://openalex.org/W4281686064","https://openalex.org/W4312289196","https://openalex.org/W4312424618","https://openalex.org/W4386076674","https://openalex.org/W4387954093","https://openalex.org/W4390691239","https://openalex.org/W4390873167","https://openalex.org/W4392679398","https://openalex.org/W4394597381","https://openalex.org/W4394597628","https://openalex.org/W4402753771","https://openalex.org/W4402754015","https://openalex.org/W4403448419","https://openalex.org/W6791353385","https://openalex.org/W6800673378","https://openalex.org/W6811340617","https://openalex.org/W6849177959","https://openalex.org/W6850503672","https://openalex.org/W6851592950","https://openalex.org/W6851607685","https://openalex.org/W6851800889","https://openalex.org/W6857660107","https://openalex.org/W6859202844","https://openalex.org/W6873967681","https://openalex.org/W6876199980"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"We":[0],"consider":[1],"the":[2,48,72,88,92,135],"problem":[3],"of":[4,137],"generating":[5],"free-form":[6,55],"mobile":[7,59,145],"manipulation":[8,60],"instructions":[9,29,133],"based":[10,79],"on":[11,115,131],"a":[12,43,65],"target":[13,49],"object":[14,50],"image":[15,20],"and":[16,51,77,97],"receptacle":[17,52],"image.":[18],"Conventional":[19],"captioning":[21],"models":[22,114],"are":[23,33],"not":[24],"able":[25],"to":[26,53,90,128],"generate":[27,54],"appropriate":[28,98],"because":[30],"their":[31],"architectures":[32],"typically":[34],"optimized":[35],"for":[36,58,144],"single-image.":[37],"In":[38],"this":[39],"study,":[40],"we":[41,63],"propose":[42],"model":[44,89,143],"that":[45,69,102,124],"handles":[46],"both":[47,75],"instruction":[56],"sentences":[57],"tasks.":[61],"Moreover,":[62,120],"introduce":[64],"novel":[66],"training":[67],"method":[68,86,105,127],"effectively":[70],"incorporates":[71],"scores":[73],"from":[74],"learning-based":[76],"n-gram":[78],"automatic":[80,117],"evaluation":[81,118],"metrics":[82],"as":[83],"rewards.":[84],"This":[85],"enables":[87],"learn":[91],"co-occurrence":[93],"relationships":[94],"between":[95],"words":[96],"paraphrases.":[99],"Results":[100],"demonstrate":[101],"our":[103,126],"proposed":[104],"outperforms":[106],"baseline":[107],"methods":[108],"including":[109],"representative":[110],"multimodal":[111,140],"large":[112],"language":[113,132,141],"standard":[116],"metrics.":[119],"physical":[121],"experiments":[122],"reveal":[123],"using":[125],"augment":[129],"data":[130],"improves":[134],"performance":[136],"an":[138],"existing":[139],"understanding":[142],"manipulation.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}