{"id":"https://openalex.org/W4401414239","doi":"https://doi.org/10.1109/icra57147.2024.10611647","title":"CLIPUNetr: Assisting Human-robot Interface for Uncalibrated Visual Servoing Control with CLIP-driven Referring Expression Segmentation","display_name":"CLIPUNetr: Assisting Human-robot Interface for Uncalibrated Visual Servoing Control with CLIP-driven Referring Expression Segmentation","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401414239","doi":"https://doi.org/10.1109/icra57147.2024.10611647"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611647","pdf_url":null,"source":null,"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"},"type":"conference-paper","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/A5009754134","display_name":"Chen Jiang","orcid":"https://orcid.org/0000-0002-9740-9499"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Chen Jiang","raw_affiliation_strings":["University of Alberta,Department of Computing Science,Edmonton AB,Canada,T6G 2E8"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta,Department of Computing Science,Edmonton AB,Canada,T6G 2E8","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101455740","display_name":"Yuchen Yang","orcid":"https://orcid.org/0009-0000-3805-2293"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yuchen Yang","raw_affiliation_strings":["University of Alberta,Department of Computing Science,Edmonton AB,Canada,T6G 2E8"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta,Department of Computing Science,Edmonton AB,Canada,T6G 2E8","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030948380","display_name":"Martin J\u00e4gersand","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Martin Jagersand","raw_affiliation_strings":["University of Alberta,Department of Computing Science,Edmonton AB,Canada,T6G 2E8"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta,Department of Computing Science,Edmonton AB,Canada,T6G 2E8","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6620","last_page":"6626"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9993000030517578,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9993000030517578,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9979000091552734,"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/T10691","display_name":"Retinal Development and Disorders","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/visual-servoing","display_name":"Visual servoing","score":0.9280100464820862},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6891043782234192},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6858658194541931},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6528591513633728},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6321998834609985},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6051338315010071},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.551083505153656},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5491703152656555},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.43275386095046997},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.4326794445514679}],"concepts":[{"id":"https://openalex.org/C10912380","wikidata":"https://www.wikidata.org/wiki/Q527952","display_name":"Visual servoing","level":3,"score":0.9280100464820862},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6891043782234192},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6858658194541931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6528591513633728},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6321998834609985},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6051338315010071},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.551083505153656},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5491703152656555},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.43275386095046997},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.4326794445514679},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10611647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611647","pdf_url":null,"source":null,"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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1524405667","https://openalex.org/W2124904960","https://openalex.org/W2414119096","https://openalex.org/W2879390606","https://openalex.org/W2925241625","https://openalex.org/W2955368974","https://openalex.org/W2961348656","https://openalex.org/W2962984928","https://openalex.org/W2963860638","https://openalex.org/W2963868681","https://openalex.org/W3004383953","https://openalex.org/W3009185927","https://openalex.org/W3025800305","https://openalex.org/W3034764937","https://openalex.org/W3094502228","https://openalex.org/W3134664367","https://openalex.org/W3135359526","https://openalex.org/W3216551675","https://openalex.org/W4212875960","https://openalex.org/W4226452378","https://openalex.org/W4288108707","https://openalex.org/W4306177171","https://openalex.org/W4312420092","https://openalex.org/W4312964941","https://openalex.org/W4323767275","https://openalex.org/W4385062417","https://openalex.org/W6765456200","https://openalex.org/W6782847789","https://openalex.org/W6784333009","https://openalex.org/W6791353385","https://openalex.org/W6801810553","https://openalex.org/W6811433417","https://openalex.org/W6843759960","https://openalex.org/W6846529796"],"related_works":["https://openalex.org/W2126852585","https://openalex.org/W2367086100","https://openalex.org/W2352270872","https://openalex.org/W1520171478","https://openalex.org/W2386520554","https://openalex.org/W4317830657","https://openalex.org/W2127866683","https://openalex.org/W3024380338","https://openalex.org/W2065095941","https://openalex.org/W1522196789"],"abstract_inverted_index":{"The":[0],"classical":[1],"human-robot":[2],"interface":[3],"in":[4,33,130,154],"uncalibrated":[5],"image-based":[6],"visual":[7],"servoing":[8],"(UIBVS)":[9],"relies":[10],"on":[11],"either":[12],"human":[13,27],"annotations":[14],"or":[15],"semantic":[16],"segmentation":[17,70,84],"with":[18,107],"categorical":[19],"labels.":[20],"Both":[21],"methods":[22],"fail":[23],"to":[24,59,92,104,119,127],"match":[25],"natural":[26,39],"communication":[28],"and":[29,110,124,139,147],"convey":[30],"rich":[31],"semantics":[32],"manipulation":[34,157],"tasks":[35],"as":[36,38],"effectively":[37],"language":[40],"expressions.":[41],"In":[42,133],"this":[43,47],"paper,":[44],"we":[45,75,114],"tackle":[46],"problem":[48],"by":[49,142],"using":[50],"referring":[51,73,82,96],"expression":[52,83],"segmentation,":[53],"which":[54],"is":[55],"a":[56,79,116],"prompt-based":[57],"approach,":[58],"provide":[60],"more":[61],"in-depth":[62],"information":[63],"for":[64],"robot":[65],"perception.":[66],"To":[67],"generate":[68,105],"high-quality":[69],"predictions":[71,106],"from":[72,95],"expressions,":[74,97],"propose":[76,115],"CLIPUNetr":[77,86,121],"-":[78],"new":[80,117],"CLIP-driven":[81],"network.":[85],"leverages":[87],"CLIP\u2019s":[88],"strong":[89],"vision-language":[90],"representations":[91],"segment":[93],"regions":[94],"while":[98],"utilizing":[99],"its":[100],"\"U-shaped\"":[101],"encoder-decoder":[102],"architecture":[103],"sharper":[108],"boundaries":[109],"finer":[111],"structures.":[112],"Furthermore,":[113],"pipeline":[118],"integrate":[120],"into":[122],"UIBVS":[123,152],"apply":[125],"it":[126],"control":[128,153],"robots":[129],"real-world":[131,151],"environments.":[132],"experiments,":[134],"our":[135],"method":[136],"improves":[137],"boundary":[138],"structure":[140],"measurements":[141],"an":[143,155],"average":[144],"of":[145],"120%":[146],"can":[148],"successfully":[149],"assist":[150],"unstructured":[156],"environment.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}