{"id":"https://openalex.org/W7137949845","doi":"https://doi.org/10.1609/aaai.v40i22.38915","title":"TouchFormer: A Robust Transformer-based Framework for Multimodal Material Perception","display_name":"TouchFormer: A Robust Transformer-based Framework for Multimodal Material Perception","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137949845","doi":"https://doi.org/10.1609/aaai.v40i22.38915"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i22.38915","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38915","pdf_url":null,"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://doi.org/10.1609/aaai.v40i22.38915","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110962115","display_name":"Kailin Lyu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kailin Lyu","raw_affiliation_strings":["Institute of automation, Chinese academy of science\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of automation, Chinese academy of science\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129717725","display_name":"Long Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Xiao","raw_affiliation_strings":["Institute of automation, Chinese academy of science\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of automation, Chinese academy of science\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055726090","display_name":"Jiaqi Zeng","orcid":"https://orcid.org/0000-0002-6967-5394"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianing Zeng","raw_affiliation_strings":["Institute of automation, Chinese academy of science\nSchool of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of automation, Chinese academy of science\nSchool of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129749593","display_name":"Junhao Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Junhao Dong","raw_affiliation_strings":["Nanyang Technological University"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089553750","display_name":"Xuexin Liu","orcid":"https://orcid.org/0000-0003-2997-5680"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuexin Liu","raw_affiliation_strings":["Institute of automation, Chinese academy of science"],"affiliations":[{"raw_affiliation_string":"Institute of automation, Chinese academy of science","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020284959","display_name":"Zhuojun Zou","orcid":"https://orcid.org/0000-0002-6582-0902"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuojun Zou","raw_affiliation_strings":["Institute of automation, Chinese academy of science"],"affiliations":[{"raw_affiliation_string":"Institute of automation, Chinese academy of science","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101861986","display_name":"Hang Yang","orcid":"https://orcid.org/0000-0002-4231-1419"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyue Yang","raw_affiliation_strings":["Institute of automation, Chinese academy of science"],"affiliations":[{"raw_affiliation_string":"Institute of automation, Chinese academy of science","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129700640","display_name":"Lin Shu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Shu","raw_affiliation_strings":["Institute of automation, Chinese academy of science"],"affiliations":[{"raw_affiliation_string":"Institute of automation, Chinese academy of science","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129723803","display_name":"Jie Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Hao","raw_affiliation_strings":["Institute of automation, Chinese academy of science"],"affiliations":[{"raw_affiliation_string":"Institute of automation, Chinese academy of science","institution_ids":["https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5110962115"],"corresponding_institution_ids":["https://openalex.org/I4210112150"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20223881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"22","first_page":"18496","last_page":"18504"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.3749000132083893,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.3749000132083893,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.13259999454021454,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.05700000002980232,"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/benchmark","display_name":"Benchmark (surveying)","score":0.5755000114440918},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5727999806404114},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.569100022315979},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5117999911308289},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.506600022315979},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4950999915599823},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4823000133037567},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.3939000070095062}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6822999715805054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6819000244140625},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5755000114440918},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5727999806404114},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.569100022315979},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5317999720573425},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5117999911308289},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.506600022315979},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4950999915599823},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4823000133037567},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3253999948501587},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.3221000134944916},{"id":"https://openalex.org/C2780617661","wikidata":"https://www.wikidata.org/wiki/Q541563","display_name":"Subcategory","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.28760001063346863},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.27239999175071716},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i22.38915","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38915","pdf_url":null,"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.v40i22.38915","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38915","pdf_url":null,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Traditional":[0],"vision-based":[1],"material":[2,21,118],"perception":[3],"methods":[4],"often":[5],"experience":[6],"substantial":[7],"performance":[8,64],"degradation":[9],"under":[10],"visually":[11],"impaired":[12],"conditions,":[13],"thereby":[14],"motivating":[15],"the":[16,48,57,130,166],"shift":[17],"toward":[18],"non-visual":[19,128],"multimodal":[20,32,76],"perception.":[22],"Despite":[23],"this,":[24],"existing":[25,127],"approaches":[26],"frequently":[27],"perform":[28],"naive":[29],"fusion":[30,77],"of":[31,52,138],"inputs,":[33],"overlooking":[34],"key":[35],"challenges":[36],"such":[37,174],"as":[38,175],"modality-specific":[39],"noise,":[40],"missing":[41],"modalities":[42],"common":[43],"in":[44,115,155,171],"real-world":[45,149],"scenarios,":[46],"and":[47,88,90,140,144,161,178],"dynamically":[49],"varying":[50],"importance":[51],"each":[53],"modality":[54],"depending":[55],"on":[56,142],"task.":[58],"These":[59],"limitations":[60],"lead":[61],"to":[62,94,126,158],"suboptimal":[63],"across":[65],"several":[66],"benchmark":[67],"tasks.":[68,120],"In":[69],"this":[70],"paper,":[71],"we":[72,81,103],"propose":[73],"a":[74,83,105],"robust":[75],"framework,":[78],"TouchFormer.":[79],"Specifically,":[80],"employ":[82],"Modality-Adaptive":[84],"Gating":[85],"(MAG)":[86],"mechanism":[87],"intra-":[89],"inter-modality":[91],"attention":[92],"mechanisms":[93],"adaptively":[95],"integrate":[96],"cross-modal":[97],"features,":[98],"enhancing":[99],"model":[100],"robustness.":[101],"Additionally,":[102],"introduce":[104],"Cross-Instance":[106],"Embedding":[107],"Regularization(CER)":[108],"strategy,":[109],"which":[110],"significantly":[111],"improves":[112],"classification":[113,135],"accuracy":[114,136],"fine-grained":[116],"subcategory":[117],"recognition":[119],"Experimental":[121],"results":[122],"demonstrate":[123],"that,":[124],"compared":[125],"methods,":[129],"proposed":[131],"TouchFormer":[132],"framework":[133],"achieves":[134],"improvements":[137],"2.48%":[139],"6.83%":[141],"SSMC":[143],"USMC":[145],"tasks,":[146],"respectively.":[147],"Furthermore,":[148],"robotic":[150],"experiments":[151],"validate":[152],"TouchFormer's":[153],"effectiveness":[154],"enabling":[156],"robots":[157],"better":[159],"perceive":[160],"interpret":[162],"their":[163],"environment,":[164],"paving":[165],"way":[167],"for":[168],"its":[169],"deployment":[170],"safety-critical":[172],"applications":[173],"emergency":[176],"response":[177],"industrial":[179],"automation.":[180]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}