{"id":"https://openalex.org/W4395443572","doi":"https://doi.org/10.1145/3640471.3680244","title":"Vision Beyond Boundaries: An Initial Design Space of Domain-specific Large Vision Models in Human-robot Interaction","display_name":"Vision Beyond Boundaries: An Initial Design Space of Domain-specific Large Vision Models in Human-robot Interaction","publication_year":2024,"publication_date":"2024-09-21","ids":{"openalex":"https://openalex.org/W4395443572","doi":"https://doi.org/10.1145/3640471.3680244"},"language":"en","primary_location":{"id":"doi:10.1145/3640471.3680244","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3640471.3680244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"26th International Conference on Mobile Human-Computer Interaction","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2404.14965","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070382887","display_name":"Yuchong Zhang","orcid":"https://orcid.org/0000-0003-1804-6296"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Yuchong Zhang","raw_affiliation_strings":["Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-1804-6296","affiliations":[{"raw_affiliation_string":"Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yong Ma","orcid":"https://orcid.org/0000-0002-8398-4118"},"institutions":[{"id":"https://openalex.org/I4432739","display_name":"University of Bergen","ror":"https://ror.org/03zga2b32","country_code":"NO","type":"education","lineage":["https://openalex.org/I4432739"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Yong Ma","raw_affiliation_strings":["University of Bergen, Norway"],"raw_orcid":"https://orcid.org/0000-0002-8398-4118","affiliations":[{"raw_affiliation_string":"University of Bergen, Norway","institution_ids":["https://openalex.org/I4432739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023792180","display_name":"Danica Kragi\u0107","orcid":"https://orcid.org/0000-0003-2965-2953"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Danica Kragic","raw_affiliation_strings":["KTH Royal Institute of Techonology, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-2965-2953","affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Techonology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070382887"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":12.2949,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.97901142,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.6115999817848206,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.6115999817848206,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.5947999954223633,"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/T11159","display_name":"Manufacturing Process and Optimization","score":0.5914000272750854,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.654698371887207},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.6543244123458862},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6183335185050964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5760250091552734},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5583806037902832},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4927995502948761},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4514637291431427},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.4314470887184143},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.4256996512413025},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22367286682128906},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.12561562657356262}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.654698371887207},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.6543244123458862},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6183335185050964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5760250091552734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5583806037902832},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4927995502948761},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4514637291431427},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.4314470887184143},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.4256996512413025},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22367286682128906},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.12561562657356262},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3640471.3680244","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3640471.3680244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"26th International Conference on Mobile Human-Computer Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2404.14965","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.14965","pdf_url":"https://arxiv.org/pdf/2404.14965","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2404.14965","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.14965","pdf_url":"https://arxiv.org/pdf/2404.14965","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7104010596","display_name":null,"funder_award_id":"FUS21-0067","funder_id":"https://openalex.org/F4320320940","funder_display_name":"Stiftelsen f\u00f6r\u00a0Strategisk Forskning"}],"funders":[{"id":"https://openalex.org/F4320320940","display_name":"Stiftelsen f\u00f6r\u00a0Strategisk Forskning","ror":"https://ror.org/044wr7g58"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4395443572.pdf","grobid_xml":"https://content.openalex.org/works/W4395443572.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W1928181285","https://openalex.org/W1997714027","https://openalex.org/W2008225641","https://openalex.org/W2013923424","https://openalex.org/W2016041204","https://openalex.org/W2033998449","https://openalex.org/W2054953903","https://openalex.org/W2074558871","https://openalex.org/W2077396358","https://openalex.org/W2100020399","https://openalex.org/W2100723321","https://openalex.org/W2109206308","https://openalex.org/W2131998556","https://openalex.org/W2134489096","https://openalex.org/W2144484988","https://openalex.org/W2144957697","https://openalex.org/W2146685071","https://openalex.org/W2162261715","https://openalex.org/W2482333547","https://openalex.org/W2578959729","https://openalex.org/W2594093535","https://openalex.org/W2751719237","https://openalex.org/W2758436592","https://openalex.org/W2773030754","https://openalex.org/W2790547736","https://openalex.org/W2792044747","https://openalex.org/W2792617863","https://openalex.org/W2796191958","https://openalex.org/W2804850956","https://openalex.org/W2902601871","https://openalex.org/W2914157382","https://openalex.org/W2963037989","https://openalex.org/W2967857025","https://openalex.org/W2991065157","https://openalex.org/W3005858535","https://openalex.org/W3035860379","https://openalex.org/W3044348268","https://openalex.org/W3099632052","https://openalex.org/W3112959725","https://openalex.org/W3135367836","https://openalex.org/W3138516171","https://openalex.org/W3177833223","https://openalex.org/W3202169296","https://openalex.org/W3202617036","https://openalex.org/W3205255557","https://openalex.org/W3217412301","https://openalex.org/W4206654130","https://openalex.org/W4211151538","https://openalex.org/W4214609028","https://openalex.org/W4282588426","https://openalex.org/W4319323596","https://openalex.org/W4319457507","https://openalex.org/W4381435362","https://openalex.org/W4383176435","https://openalex.org/W4386128543","https://openalex.org/W4388182168","https://openalex.org/W4389665984","https://openalex.org/W4392169153","https://openalex.org/W6750378353"],"related_works":["https://openalex.org/W2978665606","https://openalex.org/W4287179229","https://openalex.org/W3205513966","https://openalex.org/W3120459843","https://openalex.org/W4366547574","https://openalex.org/W3200191727","https://openalex.org/W189465620","https://openalex.org/W4366818884","https://openalex.org/W2248308732","https://openalex.org/W4392651289"],"abstract_inverted_index":{"The":[0,91],"emergence":[1],"of":[2,12,16,44,115],"large":[3],"vision":[4,45],"models":[5,46],"(LVMs)":[6],"is":[7],"following":[8,22],"in":[9,21,29,47,107],"the":[10,13,42,55,104,113],"footsteps":[11],"recent":[14],"prosperity":[15],"Large":[17],"Language":[18],"Models":[19],"(LLMs)":[20],"years.":[23],"However,":[24],"there\u2019s":[25],"a":[26,126],"noticeable":[27],"gap":[28],"structured":[30],"research":[31],"applying":[32],"LVMs":[33],"to":[34],"human-robot":[35],"interaction":[36],"(HRI),":[37],"despite":[38],"extensive":[39],"evidence":[40],"supporting":[41],"efficacy":[43,106],"enhancing":[48],"interactions":[49],"between":[50],"humans":[51],"and":[52,57,88,117,138],"robots.":[53],"Recognizing":[54],"vast":[56],"anticipated":[58],"potential,":[59],"we":[60],"introduce":[61],"an":[62],"initial":[63],"design":[64,123],"space":[65,124],"that":[66],"incorporates":[67],"domain-specific":[68],"LVMs,":[69],"chosen":[70],"for":[71,129],"their":[72],"superior":[73],"performance":[74],"over":[75],"normal":[76],"models.":[77],"We":[78,111],"delve":[79],"into":[80],"three":[81],"primary":[82,105],"dimensions:":[83],"HRI":[84,131],"contexts,":[85],"vision-based":[86],"tasks,":[87],"specific":[89],"domains.":[90],"empirical":[92],"evaluation":[93],"was":[94],"implemented":[95],"among":[96],"15":[97],"experts":[98],"across":[99],"five":[100],"evaluated":[101],"metrics,":[102],"showcasing":[103],"relevant":[108],"decision-making":[109],"scenarios.":[110],"explore":[112],"process":[114],"ideation":[116],"potential":[118],"application":[119],"scenarios,":[120],"envisioning":[121],"this":[122],"as":[125],"foundational":[127],"guideline":[128],"future":[130],"system":[132],"design,":[133],"emphasizing":[134],"accurate":[135],"domain":[136],"alignment":[137],"model":[139],"selection.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}