{"id":"https://openalex.org/W4401414358","doi":"https://doi.org/10.1109/icra57147.2024.10610228","title":"Multimodal Visual-Tactile Representation Learning through Self-Supervised Contrastive Pre-Training","display_name":"Multimodal Visual-Tactile Representation Learning through Self-Supervised Contrastive Pre-Training","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401414358","doi":"https://doi.org/10.1109/icra57147.2024.10610228"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610228","doi":"https://doi.org/10.1109/icra57147.2024.10610228","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610228","pdf_url":null,"source":{"id":"https://openalex.org/S4210217939","display_name":"Proceedings - IEEE International Conference on Robotics and Automation/Proceedings","issn_l":"1050-4729","issn":["1050-4729","2577-087X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2401.12024","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041880381","display_name":"Vedant Dave","orcid":"https://orcid.org/0009-0009-9992-3713","observed_orcids":["https://orcid.org/0009-0009-9992-3713"]},"institutions":[{"id":"https://openalex.org/I182712176","display_name":"Montanuniversit\u00e4t Leoben","ror":"https://ror.org/02fhfw393","country_code":"AT","type":"education","lineage":["https://openalex.org/I182712176"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Vedant Dave","raw_affiliation_strings":["Montanuniversität Leoben,Cyber-Physical-Systems Lab,Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Montanuniversität Leoben,Cyber-Physical-Systems Lab,Austria","institution_ids":["https://openalex.org/I182712176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064630658","display_name":"Fotios Lygerakis","orcid":"https://orcid.org/0000-0001-8044-3511","observed_orcids":["https://orcid.org/0000-0001-8044-3511"]},"institutions":[{"id":"https://openalex.org/I182712176","display_name":"Montanuniversit\u00e4t Leoben","ror":"https://ror.org/02fhfw393","country_code":"AT","type":"education","lineage":["https://openalex.org/I182712176"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Fotios Lygerakis","raw_affiliation_strings":["Montanuniversität Leoben,Cyber-Physical-Systems Lab,Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Montanuniversität Leoben,Cyber-Physical-Systems Lab,Austria","institution_ids":["https://openalex.org/I182712176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037230603","display_name":"Elmar Rueckert","orcid":"https://orcid.org/0000-0003-1221-8253","observed_orcids":["https://orcid.org/0000-0003-1221-8253"]},"institutions":[{"id":"https://openalex.org/I182712176","display_name":"Montanuniversit\u00e4t Leoben","ror":"https://ror.org/02fhfw393","country_code":"AT","type":"education","lineage":["https://openalex.org/I182712176"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Elmar Rueckert","raw_affiliation_strings":["Montanuniversität Leoben,Cyber-Physical-Systems Lab,Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Montanuniversität Leoben,Cyber-Physical-Systems Lab,Austria","institution_ids":["https://openalex.org/I182712176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I182712176"],"apc_list":null,"apc_paid":null,"fwci":24.8122,"has_fulltext":true,"cited_by_count":47,"citation_normalized_percentile":{"value":0.99723668,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8013","last_page":"8020"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9199000000953674,"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":0.9199000000953674,"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":0.05480000004172325,"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/T12032","display_name":"Multisensory perception and integration","score":0.009999999776482582,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/visual-tactile-fusion","display_name":"visual-tactile fusion","score":0.8529999852180481},{"id":"https://openalex.org/keywords/multimodal-representation-learning","display_name":"multimodal representation learning","score":0.9430000185966492},{"id":"https://openalex.org/keywords/self-supervised-contrastive-learning","display_name":"self-supervised contrastive learning","score":0.8970000147819519},{"id":"https://openalex.org/keywords/tactile-sensing","display_name":"tactile sensing","score":0.6029999852180481},{"id":"https://openalex.org/keywords/robotic-manipulation","display_name":"robotic manipulation","score":0.48899999260902405},{"id":"https://openalex.org/keywords/linear-probing","display_name":"linear probing","score":0.5849999785423279}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7610095739364624},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5507704019546509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5397857427597046},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5356497168540955},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43793898820877075},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3757205903530121},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37482914328575134},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36987924575805664},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3201724886894226},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icra57147.2024.10610228","doi":"https://doi.org/10.1109/icra57147.2024.10610228","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610228","pdf_url":null,"source":{"id":"https://openalex.org/S4210217939","display_name":"Proceedings - IEEE International Conference on Robotics and Automation/Proceedings","issn_l":"1050-4729","issn":["1050-4729","2577-087X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2401.12024","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.12024","pdf_url":"https://arxiv.org/pdf/2401.12024","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2401.12024","doi":"https://doi.org/10.48550/arxiv.2401.12024","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2401.12024","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2401.12024","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.12024","pdf_url":"https://arxiv.org/pdf/2401.12024","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401414358.pdf","grobid_xml":"https://content.openalex.org/works/W4401414358.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1583837637","https://openalex.org/W1606738297","https://openalex.org/W1665214252","https://openalex.org/W1978464142","https://openalex.org/W2070612690","https://openalex.org/W2108598243","https://openalex.org/W2171130677","https://openalex.org/W2194775991","https://openalex.org/W2316796490","https://openalex.org/W2344531169","https://openalex.org/W2560674852","https://openalex.org/W2765994785","https://openalex.org/W2775635818","https://openalex.org/W2790961751","https://openalex.org/W2798991696","https://openalex.org/W2804941773","https://openalex.org/W2897995899","https://openalex.org/W2952866402","https://openalex.org/W2955383310","https://openalex.org/W2962983231","https://openalex.org/W2979579363","https://openalex.org/W3005162594","https://openalex.org/W3005680577","https://openalex.org/W3006239966","https://openalex.org/W3008303301","https://openalex.org/W3011137165","https://openalex.org/W3035060554","https://openalex.org/W3035524453","https://openalex.org/W3036224891","https://openalex.org/W3041148233","https://openalex.org/W3108655343","https://openalex.org/W3112669067","https://openalex.org/W3145450063","https://openalex.org/W3176463841","https://openalex.org/W4235910938","https://openalex.org/W4285102554","https://openalex.org/W4285285863","https://openalex.org/W4286695273","https://openalex.org/W4292231110","https://openalex.org/W4297808394","https://openalex.org/W4302010444","https://openalex.org/W4310995851","https://openalex.org/W4311519435","https://openalex.org/W4312750307","https://openalex.org/W4313562940","https://openalex.org/W4353111822","https://openalex.org/W4362709236","https://openalex.org/W4384518965","https://openalex.org/W4385430681","https://openalex.org/W7133182857"],"related_works":["https://openalex.org/W4416749610","https://openalex.org/W7128769360","https://openalex.org/W7155094524","https://openalex.org/W3015417033","https://openalex.org/W7130676801","https://openalex.org/W7202366529","https://openalex.org/W2737661303","https://openalex.org/W4385430681","https://openalex.org/W7125948318","https://openalex.org/W4312924775"],"abstract_inverted_index":{"The":[0],"rapidly":[1],"evolving":[2],"field":[3],"of":[4,13,41,57,126,132,169],"robotics":[5],"necessitates":[6],"methods":[7,71],"that":[8,84,164],"can":[9],"facilitate":[10],"the":[11,38,42,58,130,167],"fusion":[12],"multiple":[14],"modalities.":[15],"Specifically,":[16],"when":[17],"it":[18],"comes":[19],"to":[20,34,52,88],"interacting":[21],"with":[22],"tangible":[23],"objects,":[24],"effectively":[25],"combining":[26],"visual":[27],"and":[28,36,49,91,106,118,135,142,157],"tactile":[29],"sensory":[30,65,101],"data":[31],"is":[32],"key":[33],"understanding":[35],"navigating":[37],"complex":[39],"dynamics":[40],"physical":[43],"world,":[44],"enabling":[45],"a":[46,81,95,124],"more":[47,119,174],"nuanced":[48],"adaptable":[50],"response":[51],"changing":[53],"environments.":[54],"Nevertheless,":[55],"much":[56],"earlier":[59],"work":[60],"in":[61,94,113],"merging":[62],"these":[63],"two":[64,152],"modalities":[66],"has":[67],"relied":[68],"on":[69,151],"supervised":[70,143],"utilizing":[72],"datasets":[73],"labeled":[74],"by":[75,179],"humans.":[76],"This":[77],"paper":[78],"introduces":[79],"MViTac,":[80],"novel":[82],"methodology":[83],"leverages":[85,104],"contrastive":[86],"learning":[87,110],"integrate":[89],"vision":[90],"touch":[92],"sensations":[93],"self-supervised":[96,141],"fashion.":[97],"By":[98],"availing":[99],"both":[100],"inputs,":[102],"MViTac":[103,165],"intra":[105],"inter-modality":[107],"losses":[108],"for":[109],"representations,":[111],"resulting":[112],"enhanced":[114],"material":[115,155],"property":[116],"classification":[117,156],"adept":[120],"grasping":[121,158],"prediction.":[122,160],"Through":[123],"series":[125],"experiments,":[127],"we":[128,149],"showcase":[129],"effectiveness":[131],"our":[133,147],"method":[134],"its":[136],"superiority":[137],"over":[138],"existing":[139],"state-of-the-art":[140],"techniques.":[144],"In":[145],"evaluating":[146],"methodology,":[148],"focus":[150],"distinct":[153],"tasks:":[154],"success":[159],"Our":[161],"results":[162],"indicate":[163],"facilitates":[166],"development":[168],"improved":[170],"modality":[171],"encoders,":[172],"yielding":[173],"robust":[175],"representations":[176],"as":[177],"evidenced":[178],"linear":[180],"probing":[181],"assessments.":[182],"https://sites.google.com/view/mvitac/home":[183]},"counts_by_year":[{"year":2026,"cited_by_count":18},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":8}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-08-09T00:00:00"}