{"id":"https://openalex.org/W4413925854","doi":"https://doi.org/10.1109/icra55743.2025.11127829","title":"Robotic-CLIP: Fine-Tuning CLIP on Action Data for Robotic Applications","display_name":"Robotic-CLIP: Fine-Tuning CLIP on Action Data for Robotic Applications","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413925854","doi":"https://doi.org/10.1109/icra55743.2025.11127829"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127829","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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/A5102846683","display_name":"Nghia T. Nguyen","orcid":"https://orcid.org/0000-0002-6263-7563"},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Nghia Nguyen","raw_affiliation_strings":["FPT Software AI Center,Vietnam"],"affiliations":[{"raw_affiliation_string":"FPT Software AI Center,Vietnam","institution_ids":["https://openalex.org/I109689652"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063231826","display_name":"Minh N. Vu","orcid":"https://orcid.org/0000-0001-8727-0350"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Minh N. Vu","raw_affiliation_strings":["Automation & Control Institute (ACIN), TU Wien,Vienna,Austria"],"affiliations":[{"raw_affiliation_string":"Automation & Control Institute (ACIN), TU Wien,Vienna,Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079787626","display_name":"Tung D. Ta","orcid":"https://orcid.org/0000-0002-2342-1364"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tung D. Ta","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045614046","display_name":"Baoru Huang","orcid":"https://orcid.org/0000-0002-4421-652X"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Baoru Huang","raw_affiliation_strings":["University of Liverpool,Department of Computer Science,UK"],"affiliations":[{"raw_affiliation_string":"University of Liverpool,Department of Computer Science,UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043429366","display_name":"Thieu Vo","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Thieu Vo","raw_affiliation_strings":["National University of Singapore,Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023725893","display_name":"Ngan Le","orcid":"https://orcid.org/0000-0003-2571-0511"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ngan Le","raw_affiliation_strings":["University of Arkansas,USA"],"affiliations":[{"raw_affiliation_string":"University of Arkansas,USA","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100693035","display_name":"Anh Nguyen","orcid":"https://orcid.org/0000-0003-0742-5653"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anh Nguyen","raw_affiliation_strings":["University of Liverpool,Department of Computer Science,UK"],"affiliations":[{"raw_affiliation_string":"University of Liverpool,Department of Computer Science,UK","institution_ids":["https://openalex.org/I146655781"]}]}],"institutions":[],"countries_distinct_count":6,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5102846683"],"corresponding_institution_ids":["https://openalex.org/I109689652"],"apc_list":null,"apc_paid":null,"fwci":1.1715,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8248798,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5930","last_page":"5936"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9092000126838684,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9092000126838684,"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/computer-science","display_name":"Computer science","score":0.700242817401886},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5485358238220215},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.47882822155952454},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4169735312461853},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3610866069793701},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3217639923095703},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.061975687742233276}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.700242817401886},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5485358238220215},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.47882822155952454},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4169735312461853},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3610866069793701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3217639923095703},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.061975687742233276},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127829","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2963033241","https://openalex.org/W3009201938","https://openalex.org/W3130885760","https://openalex.org/W3176445421","https://openalex.org/W3186077919","https://openalex.org/W3203711169","https://openalex.org/W4312288659","https://openalex.org/W4312818263","https://openalex.org/W4327545837","https://openalex.org/W4383097445","https://openalex.org/W4383108296","https://openalex.org/W4383108836","https://openalex.org/W4385431288","https://openalex.org/W4386065752","https://openalex.org/W4386075580","https://openalex.org/W4386075819","https://openalex.org/W4386075997","https://openalex.org/W4386790226","https://openalex.org/W4389665991","https://openalex.org/W4390190404","https://openalex.org/W4390874575","https://openalex.org/W4390889814","https://openalex.org/W4401413802","https://openalex.org/W4401415888","https://openalex.org/W4401416041","https://openalex.org/W4401416788","https://openalex.org/W4401417288","https://openalex.org/W4402702930","https://openalex.org/W4402716288","https://openalex.org/W4402753899","https://openalex.org/W4404612908","https://openalex.org/W4405786915"],"related_works":["https://openalex.org/W8302103","https://openalex.org/W3171631314","https://openalex.org/W2674584172","https://openalex.org/W2967743314","https://openalex.org/W2606825221","https://openalex.org/W2184085865","https://openalex.org/W2064245428","https://openalex.org/W2170721890","https://openalex.org/W2122871747","https://openalex.org/W1990892711"],"abstract_inverted_index":{"Vision":[0],"language":[1,34],"models":[2,130],"have":[3],"played":[4],"a":[5],"key":[6],"role":[7],"in":[8,25,118,144],"extracting":[9],"meaningful":[10],"features":[11],"for":[12,55],"various":[13,132],"robotic":[14,26,56,69,119,134],"applications.":[15,147],"Among":[16],"these,":[17],"Contrastive":[18],"Language-Image":[19],"Pretraining":[20],"(CLIP)":[21],"is":[22],"widely":[23],"used":[24],"tasks":[27,57],"that":[28,124],"require":[29],"both":[30],"vision":[31],"and":[32,48,75,80],"natural":[33],"understanding.":[35],"However,":[36],"CLIP":[37,87],"was":[38],"trained":[39],"solely":[40],"on":[41,88],"static":[42],"images":[43],"paired":[44],"with":[45],"text":[46],"prompts":[47],"has":[49],"not":[50],"yet":[51],"been":[52],"fully":[53],"adapted":[54],"involving":[58],"dynamic":[59],"actions.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64,137],"introduce":[65],"Robotic-CLIP":[66,84,105,126,143],"to":[67,115],"enhance":[68],"perception":[70],"capabilities.":[71],"We":[72],"first":[73],"gather":[74],"label":[76],"large-scale":[77],"action":[78,96,103],"data,":[79,104],"then":[81],"build":[82],"our":[83,125],"by":[85],"fine-tuning":[86],"309,433":[89],"videos":[90],"(\u2248":[91],"7.4":[92],"million":[93],"frames)":[94],"of":[95,142],"data":[97],"using":[98],"contrastive":[99],"learning.":[100],"By":[101],"leveraging":[102],"inherits":[106],"CLIP's":[107],"strong":[108],"image":[109],"performance":[110],"while":[111],"gaining":[112],"the":[113,139],"ability":[114],"understand":[116],"actions":[117],"contexts.":[120],"Intensive":[121],"experiments":[122],"show":[123],"outperforms":[127],"other":[128],"CLIP-based":[129],"across":[131],"language-driven":[133],"tasks.":[135],"Additionally,":[136],"demonstrate":[138],"practical":[140],"effectiveness":[141],"real-world":[145],"grasping":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}