{"id":"https://openalex.org/W7137832818","doi":"https://doi.org/10.1609/aaai.v40i22.38956","title":"Collaborative Representation Learning for Alignment of Tactile, Language, and Vision Modalities","display_name":"Collaborative Representation Learning for Alignment of Tactile, Language, and Vision Modalities","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137832818","doi":"https://doi.org/10.1609/aaai.v40i22.38956"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i22.38956","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38956","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38956/42918","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38956/42918","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yiyun Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiyun Zhou","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mingjing Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I39586589","display_name":"Swansea University","ror":"https://ror.org/053fq8t95","country_code":"GB","type":"education","lineage":["https://openalex.org/I39586589"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mingjing Xu","raw_affiliation_strings":["Swansea University"],"affiliations":[{"raw_affiliation_string":"Swansea University","institution_ids":["https://openalex.org/I39586589"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jingwei Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingwei Shi","raw_affiliation_strings":["Shanghai University of Finance and Economics"],"affiliations":[{"raw_affiliation_string":"Shanghai University of Finance and Economics","institution_ids":["https://openalex.org/I181679659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Quanjiang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quanjiang Li","raw_affiliation_strings":["National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jingyuan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyuan Chen","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39130435,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"22","first_page":"18864","last_page":"18872"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10338","display_name":"Advanced Sensor and Energy Harvesting Materials","score":0.6596999764442444,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10338","display_name":"Advanced Sensor and Energy Harvesting Materials","score":0.6596999764442444,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10653","display_name":"Robot Manipulation and Learning","score":0.0892999991774559,"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/T10914","display_name":"Tactile and Sensory Interactions","score":0.06019999831914902,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6051999926567078},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6025999784469604},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5846999883651733},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5343000292778015},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4657999873161316},{"id":"https://openalex.org/keywords/rss","display_name":"RSS","score":0.4519999921321869},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.3801000118255615},{"id":"https://openalex.org/keywords/tactile-sensor","display_name":"Tactile sensor","score":0.358599990606308}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7332000136375427},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6051999926567078},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6025999784469604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5938000082969666},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5846999883651733},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5846999883651733},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5343000292778015},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4657999873161316},{"id":"https://openalex.org/C2385561","wikidata":"https://www.wikidata.org/wiki/Q45432","display_name":"RSS","level":2,"score":0.4519999921321869},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3801000118255615},{"id":"https://openalex.org/C46722567","wikidata":"https://www.wikidata.org/wiki/Q7674139","display_name":"Tactile sensor","level":3,"score":0.358599990606308},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.351500004529953},{"id":"https://openalex.org/C152086174","wikidata":"https://www.wikidata.org/wiki/Q3030571","display_name":"Haptic technology","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34220001101493835},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.30090001225471497},{"id":"https://openalex.org/C2779688209","wikidata":"https://www.wikidata.org/wiki/Q131250","display_name":"Mantis","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26840001344680786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i22.38956","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38956","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38956/42918","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i22.38956","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38956","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38956/42918","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4016536772251129,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137832818.pdf","grobid_xml":"https://content.openalex.org/works/W7137832818.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Tactile":[0],"sensing":[1],"offers":[2],"rich":[3],"and":[4,9,45,73,118,133],"complementary":[5],"information":[6],"to":[7,13,25,36,66,78,90],"vision":[8,46],"language,":[10,44],"enabling":[11],"robots":[12],"perceive":[14],"fine-grained":[15],"object":[16],"properties.":[17],"However,":[18],"existing":[19,33],"tactile":[20,68,81,105,142],"sensors":[21,72],"lack":[22],"standardization,":[23],"leading":[24],"redundant":[26],"features":[27,69],"that":[28,126],"hinder":[29],"cross-sensor":[30],"generalization.":[31],"Moreover,":[32],"methods":[34],"fail":[35],"fully":[37],"integrate":[38],"the":[39,95,102,110],"intermediate":[40],"communication":[41],"among":[42],"tactile,":[43],"modalities.":[47],"To":[48,99],"address":[49],"this,":[50],"we":[51,107],"propose":[52,109],"TLV-CoRe,":[53],"a":[54,63,84,137],"CLIP-based":[55],"Tactile-Language-Vision":[56],"Collaborative":[57],"Representation":[58],"learning":[59,77,132],"method.":[60],"TLV-CoRe":[61,127],"introduces":[62],"Sensor-Aware":[64],"Modulator":[65],"unify":[67],"across":[70,120],"different":[71,121],"employs":[74],"tactile-irrelevant":[75],"decoupled":[76],"disentangle":[79],"irrelevant":[80],"features.":[82],"Additionally,":[83],"Unified":[85],"Bridging":[86],"Adapter":[87],"is":[88],"introduced":[89],"enhance":[91],"tri-modal":[92],"interaction":[93],"within":[94],"shared":[96],"representation":[97,131],"space.":[98],"fairly":[100],"evaluate":[101],"effectiveness":[103],"of":[104],"models,":[106],"further":[108],"RSS":[111],"evaluation":[112],"framework,":[113],"focusing":[114],"on":[115],"Robustness,":[116],"Synergy,":[117],"Stability":[119],"methods.":[122],"Experimental":[123],"results":[124],"demonstrate":[125],"significantly":[128],"improves":[129],"sensor-agnostic":[130],"cross-modal":[134],"alignment,":[135],"offering":[136],"new":[138],"direction":[139],"for":[140],"multimodal":[141],"representation.":[143]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-02-06T00:00:00"}