{"id":"https://openalex.org/W7147749479","doi":"https://doi.org/10.1016/j.cviu.2026.104749","title":"ProfVLM: A lightweight video-language model for multi-view proficiency estimation","display_name":"ProfVLM: A lightweight video-language model for multi-view proficiency estimation","publication_year":2026,"publication_date":"2026-04-01","ids":{"openalex":"https://openalex.org/W7147749479","doi":"https://doi.org/10.1016/j.cviu.2026.104749"},"language":"en","primary_location":{"id":"doi:10.1016/j.cviu.2026.104749","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.cviu.2026.104749","pdf_url":null,"source":{"id":"https://openalex.org/S185008460","display_name":"Computer Vision and Image Understanding","issn_l":"1077-3142","issn":["1077-3142","1090-235X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Vision and Image Understanding","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.cviu.2026.104749","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132731297","display_name":"Edoardo Bianchi","orcid":null},"institutions":[{"id":"https://openalex.org/I171543936","display_name":"Free University of Bozen-Bolzano","ror":"https://ror.org/012ajp527","country_code":"IT","type":"education","lineage":["https://openalex.org/I171543936"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Edoardo Bianchi","raw_affiliation_strings":["Free University of Bozen-Bolzano, Via Bruno Buozzi 1, Bozen-Bolzano, 39100, Italy"],"raw_orcid":"https://orcid.org/0000-0002-0963-9543","affiliations":[{"raw_affiliation_string":"Free University of Bozen-Bolzano, Via Bruno Buozzi 1, Bozen-Bolzano, 39100, Italy","institution_ids":["https://openalex.org/I171543936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082391569","display_name":"Jacopo Staiano","orcid":"https://orcid.org/0000-0002-1260-4640"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Jacopo Staiano","raw_affiliation_strings":["University of Trento, Via Inama 5, Trento, 38122, Italy"],"raw_orcid":"https://orcid.org/0000-0002-1260-4640","affiliations":[{"raw_affiliation_string":"University of Trento, Via Inama 5, Trento, 38122, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026941307","display_name":"Antonio Liotta","orcid":"https://orcid.org/0000-0002-2773-4421"},"institutions":[{"id":"https://openalex.org/I171543936","display_name":"Free University of Bozen-Bolzano","ror":"https://ror.org/012ajp527","country_code":"IT","type":"education","lineage":["https://openalex.org/I171543936"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Antonio Liotta","raw_affiliation_strings":["Free University of Bozen-Bolzano, Via Bruno Buozzi 1, Bozen-Bolzano, 39100, Italy"],"raw_orcid":"https://orcid.org/0000-0002-2773-4421","affiliations":[{"raw_affiliation_string":"Free University of Bozen-Bolzano, Via Bruno Buozzi 1, Bozen-Bolzano, 39100, Italy","institution_ids":["https://openalex.org/I171543936"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5132731297"],"corresponding_institution_ids":["https://openalex.org/I171543936"],"apc_list":{"value":2370,"currency":"USD","value_usd":2370},"apc_paid":{"value":2370,"currency":"USD","value_usd":2370},"fwci":7.365,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96675254,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"268","issue":null,"first_page":"104749","last_page":"104749"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.2660999894142151,"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":0.2660999894142151,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.10019999742507935,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.08910000324249268,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/estimation","display_name":"Estimation","score":0.48899999260902405},{"id":"https://openalex.org/keywords/estimation-theory","display_name":"Estimation theory","score":0.29679998755455017},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.27869999408721924},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.25529998540878296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.637499988079071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5252000093460083},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.48899999260902405},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39579999446868896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.311599999666214},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2874000072479248},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26109999418258667},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.251800000667572}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1016/j.cviu.2026.104749","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.cviu.2026.104749","pdf_url":null,"source":{"id":"https://openalex.org/S185008460","display_name":"Computer Vision and Image Understanding","issn_l":"1077-3142","issn":["1077-3142","1090-235X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Vision and Image Understanding","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2509.26278","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2509.26278","pdf_url":"https://arxiv.org/pdf/2509.26278","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:iris.unitn.it:11572/485070","is_oa":true,"landing_page_url":"https://www.sciencedirect.com/science/article/pii/S1077314226001165","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"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":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1016/j.cviu.2026.104749","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.cviu.2026.104749","pdf_url":null,"source":{"id":"https://openalex.org/S185008460","display_name":"Computer Vision and Image Understanding","issn_l":"1077-3142","issn":["1077-3142","1090-235X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Vision and Image Understanding","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6524865627288818}],"awards":[],"funders":[{"id":"https://openalex.org/F1100377486","display_name":"European High Performance Computing Joint Undertaking","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W3027170253","https://openalex.org/W4402727748","https://openalex.org/W4402727916","https://openalex.org/W4402858085","https://openalex.org/W4403511263","https://openalex.org/W4404515383","https://openalex.org/W4404853794","https://openalex.org/W4405634818","https://openalex.org/W4406188408","https://openalex.org/W4409917311","https://openalex.org/W4410979896","https://openalex.org/W4412893567","https://openalex.org/W4413094477","https://openalex.org/W4413156866"],"related_works":[],"abstract_inverted_index":{"Most":[0],"existing":[1,130],"approaches":[2],"formulate":[3],"action":[4,158],"quality":[5,159],"assessment":[6],"and":[7,50,83,87,120,152],"skill":[8],"proficiency":[9,48],"estimation":[10],"as":[11,35],"discriminative":[12],"prediction":[13],"tasks,":[14],"typically":[15],"producing":[16],"discrete":[17],"labels":[18],"or":[19],"scores":[20],"without":[21],"explicitly":[22],"modeling":[23,148],"the":[24,28,33],"reasoning":[25],"process":[26],"underlying":[27],"assessment.":[29,160],"We":[30],"instead":[31],"reformulate":[32],"problem":[34],"generative":[36,146],"vision-language":[37,43,147],"modeling,":[38],"introducing":[39],"ProfVLM,":[40],"a":[41,91,96,150],"parameter-efficient":[42],"model":[44,98],"that":[45,80,145],"jointly":[46],"predicts":[47],"levels":[49],"generates":[51],"expert-like":[52],"natural":[53,135],"language":[54,62,97,136],"feedback":[55,101],"from":[56,90],"multi-view":[57,85],"videos.":[58],"ProfVLM":[59,109],"leverages":[60],"conditional":[61],"generation":[63],"to":[64,74,116,126,129],"provide":[65],"actionable":[66],"insights":[67],"along":[68],"with":[69,106,139],"quantitative":[70],"evaluation":[71],"scores.":[72],"Central":[73],"our":[75],"method":[76],"is":[77],"an":[78],"AttentiveGatedProjector":[79],"dynamically":[81],"fuses":[82],"projects":[84],"egocentric":[86],"exocentric":[88],"features":[89],"frozen":[92],"TimeSformer":[93],"backbone":[94],"into":[95],"fine-tuned":[99],"for":[100,156],"generation.":[102],"Trained":[103],"on":[104],"EgoExo4D":[105],"expert":[107],"commentaries,":[108],"surpasses":[110],"state-of-the-art":[111],"methods":[112],"while":[113],"using":[114],"up":[115,125],"20x":[117],"fewer":[118],"parameters":[119],"reducing":[121],"training":[122],"time":[123],"by":[124],"60%":[127],"compared":[128],"classification-based":[131],"methods.":[132],"By":[133],"providing":[134],"critiques":[137],"aligned":[138],"performance":[140],"levels,":[141],"this":[142],"work":[143],"shows":[144],"offers":[149],"powerful":[151],"efficient":[153],"paradigm":[154],"shift":[155],"interpretable":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2026-04-02T00:00:00"}
