{"id":"https://openalex.org/W4415524464","doi":"https://doi.org/10.1109/humanoids65713.2025.11203083","title":"Learning Multimodal Attention for Manipulating Deformable Objects with Changing States","display_name":"Learning Multimodal Attention for Manipulating Deformable Objects with Changing States","publication_year":2025,"publication_date":"2025-09-30","ids":{"openalex":"https://openalex.org/W4415524464","doi":"https://doi.org/10.1109/humanoids65713.2025.11203083"},"language":null,"primary_location":{"id":"doi:10.1109/humanoids65713.2025.11203083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids65713.2025.11203083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-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/A5066028565","display_name":"Namiko Saito","orcid":"https://orcid.org/0000-0003-4140-7643"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Namiko Saito","raw_affiliation_strings":["Waseda University,Future Robotics Organization,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Future Robotics Organization,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113189916","display_name":"Mayu Tatsumi","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mayu Tatsumi","raw_affiliation_strings":["Waseda University,Department of Modern Mechanical Engineering,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Modern Mechanical Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109709605","display_name":"Ayuna Kubo","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ayuna Kubo","raw_affiliation_strings":["Waseda University,Department of Modern Mechanical Engineering,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Modern Mechanical Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042849965","display_name":"Kanata Suzuki","orcid":"https://orcid.org/0000-0001-7122-7649"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kanata Suzuki","raw_affiliation_strings":["Waseda University,Future Robotics Organization,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Future Robotics Organization,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044544721","display_name":"Hiroshi Ito","orcid":"https://orcid.org/0000-0002-9857-8614"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Ito","raw_affiliation_strings":["Waseda University,Future Robotics Organization,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Future Robotics Organization,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080654277","display_name":"Shigeki Sugano","orcid":"https://orcid.org/0000-0002-9331-2446"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeki Sugano","raw_affiliation_strings":["Waseda University,Faculty of Science and Engineering,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Faculty of Science and Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055922202","display_name":"Tetsuya Ogata","orcid":"https://orcid.org/0000-0001-7015-0379"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Ogata","raw_affiliation_strings":["Waseda University,Faculty of Science and Engineering,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Faculty of Science and Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5066028565"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38494079,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"460","last_page":"467"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9761999845504761,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9761999845504761,"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/T11006","display_name":"BIM and Construction Integration","score":0.9258000254631042,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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":0.9025999903678894,"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/modalities","display_name":"Modalities","score":0.6114000082015991},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.5920000076293945},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5680999755859375},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5515999794006348},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.512499988079071},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5103999972343445},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.45590001344680786},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4551999866962433},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4124999940395355},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3718999922275543}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6987000107765198},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6114000082015991},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.5920000076293945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5789999961853027},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5680999755859375},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5515999794006348},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.512499988079071},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5103999972343445},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.45590001344680786},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4551999866962433},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3718999922275543},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3702000081539154},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34290000796318054},{"id":"https://openalex.org/C26486553","wikidata":"https://www.wikidata.org/wiki/Q371870","display_name":"Stimulus modality","level":3,"score":0.34209999442100525},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3411000072956085},{"id":"https://openalex.org/C94487597","wikidata":"https://www.wikidata.org/wiki/Q11101","display_name":"Sensory system","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.3278000056743622},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.32760000228881836},{"id":"https://openalex.org/C2776010242","wikidata":"https://www.wikidata.org/wiki/Q4677575","display_name":"Active perception","level":3,"score":0.31310001015663147},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27619999647140503},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2705000042915344},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2687999904155731},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.259799987077713},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.2547000050544739},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/humanoids65713.2025.11203083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids65713.2025.11203083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1188111237","display_name":null,"funder_award_id":"JPMJMS2031","funder_id":"https://openalex.org/F4320320907","funder_display_name":"Japan Science and Technology Corporation"}],"funders":[{"id":"https://openalex.org/F4320320907","display_name":"Japan Science and Technology Corporation","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1969299770","https://openalex.org/W2028418738","https://openalex.org/W2055527244","https://openalex.org/W2075673359","https://openalex.org/W2136655611","https://openalex.org/W2171130677","https://openalex.org/W2519715178","https://openalex.org/W2604382266","https://openalex.org/W2804235108","https://openalex.org/W2914093613","https://openalex.org/W2963811535","https://openalex.org/W2994446013","https://openalex.org/W3001358351","https://openalex.org/W3087141283","https://openalex.org/W3135705943","https://openalex.org/W3150384095","https://openalex.org/W4200629494","https://openalex.org/W4213417100","https://openalex.org/W4224027762","https://openalex.org/W4283390866","https://openalex.org/W4385403811","https://openalex.org/W4385430674","https://openalex.org/W4402353985","https://openalex.org/W4403337227"],"related_works":[],"abstract_inverted_index":{"To":[0,123],"support":[1],"humans":[2],"in":[3,33,42],"their":[4,43,104],"daily":[5],"lives,":[6],"robots":[7,110],"are":[8,155],"required":[9],"to":[10,12,18,111],"adapt":[11],"objects":[13,32,119],"whose":[14],"states":[15],"change":[16],"due":[17],"external":[19],"factors":[20],"such":[21,37],"as":[22,72,147],"heat":[23],"and":[24,26,39,58,61,81,107,115,153],"force,":[25],"perform":[27],"appropriate":[28],"actions":[29],"accordingly.":[30],"Many":[31],"everyday":[34],"environments":[35],"exhibit":[36],"dynamic":[38],"continuous":[40],"changes":[41],"physical":[44,136],"properties.":[45],"In":[46],"these":[47],"situations,":[48],"sensory":[49],"input":[50],"from":[51],"multiple":[52],"modalities":[53,101],"often":[54],"contains":[55],"both":[56],"valuable":[57],"noisy":[59],"information,":[60],"the":[62,73,125,128],"importance":[63],"of":[64,118,127,143],"each":[65],"sensor":[66,100],"modality":[67],"can":[68],"shift":[69],"over":[70],"time":[71],"object's":[74],"state":[75,121],"changes.":[76,122],"This":[77],"makes":[78],"real-time":[79],"perception":[80,114],"motion":[82],"generation":[83],"particularly":[84],"challenging.":[85],"We":[86],"propose":[87],"a":[88,135,140],"predictive":[89],"recurrent":[90],"neural":[91],"network":[92],"with":[93],"an":[94,148],"attention":[95],"mechanism":[96],"that":[97],"dynamically":[98],"weights":[99],"based":[102],"on":[103,134],"current":[105],"reliability":[106],"relevance,":[108],"enabling":[109],"achieve":[112],"efficient":[113],"adaptive":[116],"manipulation":[117,141],"undergoing":[120],"demonstrate":[124],"effectiveness":[126],"proposed":[129],"method,":[130],"we":[131],"validated":[132],"it":[133],"humanoid":[137],"robot,":[138],"using":[139],"task":[142],"cooking":[144],"scrambled":[145],"eggs":[146],"example":[149],"scenario.":[150],"Our":[151],"code":[152],"dataset":[154],"available":[156],"here:":[157],"https://github.com/namikosaito/CookingScrambledEgg":[158]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-24T00:00:00"}
