{"id":"https://openalex.org/W7129759119","doi":"https://doi.org/10.1109/icipw68931.2025.11385873","title":"Can Local Vision-Language Models Improve Activity Recognition Over Vision Transformers? - Case Study On Newborn Resuscitation","display_name":"Can Local Vision-Language Models Improve Activity Recognition Over Vision Transformers? - Case Study On Newborn Resuscitation","publication_year":2025,"publication_date":"2025-09-14","ids":{"openalex":"https://openalex.org/W7129759119","doi":"https://doi.org/10.1109/icipw68931.2025.11385873"},"language":null,"primary_location":{"id":"doi:10.1109/icipw68931.2025.11385873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icipw68931.2025.11385873","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 Image Processing Workshops (ICIPW)","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/A5125917081","display_name":"Enrico Guerriero","orcid":null},"institutions":[{"id":"https://openalex.org/I92008406","display_name":"University of Stavanger","ror":"https://ror.org/02qte9q33","country_code":"NO","type":"education","lineage":["https://openalex.org/I92008406"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Enrico Guerriero","raw_affiliation_strings":["University of Stavanger,Dept. of electrical eng. and computer science,Stavanger,Norway"],"affiliations":[{"raw_affiliation_string":"University of Stavanger,Dept. of electrical eng. and computer science,Stavanger,Norway","institution_ids":["https://openalex.org/I92008406"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094624151","display_name":"Kjersti Engan","orcid":null},"institutions":[{"id":"https://openalex.org/I92008406","display_name":"University of Stavanger","ror":"https://ror.org/02qte9q33","country_code":"NO","type":"education","lineage":["https://openalex.org/I92008406"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Kjersti Engan","raw_affiliation_strings":["University of Stavanger,Dept. of electrical eng. and computer science,Stavanger,Norway"],"affiliations":[{"raw_affiliation_string":"University of Stavanger,Dept. of electrical eng. and computer science,Stavanger,Norway","institution_ids":["https://openalex.org/I92008406"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043479425","display_name":"\u00d8yvind Meinich-Bache","orcid":"https://orcid.org/0000-0002-9264-027X"},"institutions":[{"id":"https://openalex.org/I92008406","display_name":"University of Stavanger","ror":"https://ror.org/02qte9q33","country_code":"NO","type":"education","lineage":["https://openalex.org/I92008406"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"\u00d8yvind Meinich-Bache","raw_affiliation_strings":["University of Stavanger,Dept. of electrical eng. and computer science,Stavanger,Norway"],"affiliations":[{"raw_affiliation_string":"University of Stavanger,Dept. of electrical eng. and computer science,Stavanger,Norway","institution_ids":["https://openalex.org/I92008406"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5125917081"],"corresponding_institution_ids":["https://openalex.org/I92008406"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87808705,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"586","last_page":"591"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11060","display_name":"Infant Development and Preterm Care","score":0.43779999017715454,"subfield":{"id":"https://openalex.org/subfields/2735","display_name":"Pediatrics, Perinatology and Child Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11060","display_name":"Infant Development and Preterm Care","score":0.43779999017715454,"subfield":{"id":"https://openalex.org/subfields/2735","display_name":"Pediatrics, Perinatology and Child Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13248","display_name":"Healthcare Technology and Patient Monitoring","score":0.09669999778270721,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10549","display_name":"Neonatal Respiratory Health Research","score":0.08980000019073486,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/resuscitation","display_name":"Resuscitation","score":0.671999990940094},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.45339998602867126},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.3555999994277954},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3456000089645386},{"id":"https://openalex.org/keywords/neonatal-resuscitation","display_name":"Neonatal resuscitation","score":0.3336000144481659},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3269999921321869}],"concepts":[{"id":"https://openalex.org/C2778165595","wikidata":"https://www.wikidata.org/wiki/Q5491454","display_name":"Resuscitation","level":2,"score":0.671999990940094},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.6212999820709229},{"id":"https://openalex.org/C545542383","wikidata":"https://www.wikidata.org/wiki/Q2751242","display_name":"Medical emergency","level":1,"score":0.48590001463890076},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.45339998602867126},{"id":"https://openalex.org/C177713679","wikidata":"https://www.wikidata.org/wiki/Q679690","display_name":"Intensive care medicine","level":1,"score":0.4413999915122986},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33469998836517334},{"id":"https://openalex.org/C2780843067","wikidata":"https://www.wikidata.org/wiki/Q25091318","display_name":"Neonatal resuscitation","level":3,"score":0.3336000144481659},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.3208000063896179},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2944999933242798},{"id":"https://openalex.org/C2982818900","wikidata":"https://www.wikidata.org/wiki/Q20779747","display_name":"Artificial vision","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2721000015735626},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icipw68931.2025.11385873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icipw68931.2025.11385873","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 Image Processing Workshops (ICIPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W141442112","https://openalex.org/W2998624672","https://openalex.org/W3010432310","https://openalex.org/W3014440910","https://openalex.org/W3126721948","https://openalex.org/W3140547928","https://openalex.org/W4386071476","https://openalex.org/W4391136507","https://openalex.org/W4402727764","https://openalex.org/W4402916050","https://openalex.org/W4404509535","https://openalex.org/W4410344546"],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"documentation":[1],"of":[2,57,74,99,146],"newborn":[3,38,101],"resuscitation":[4,39,102],"is":[5],"essential":[6],"for":[7],"quality":[8],"improvement":[9],"and":[10,25,85,110],"adherence":[11],"to":[12,62,88],"clinical":[13],"guidelines,":[14],"yet":[15],"it":[16],"remains":[17],"underutilized":[18],"in":[19,33,47],"practice.":[20],"Previous":[21],"work":[22,53],"using":[23],"3D-CNNs":[24],"Vision":[26],"Transformers":[27],"(ViT)":[28],"has":[29,42],"shown":[30],"promising":[31],"results":[32,121,136,145],"detecting":[34],"key":[35],"activities":[36],"from":[37,66],"videos,":[40,103],"but":[41,130],"also":[43],"highlighted":[44],"the":[45,55,72,135,143],"challenges":[46],"recognizing":[48],"such":[49,67],"fine-grained":[50],"activities.":[51],"This":[52],"investigates":[54],"potential":[56],"generative":[58],"AI":[59],"(GenAI)":[60],"methods":[61],"improve":[63],"activity":[64],"recognition":[65],"videos.":[68],"Specifically,":[69],"we":[70,104],"explore":[71],"use":[73],"local":[75],"vision-language":[76],"models":[77,83],"(VLMs),":[78],"combined":[79],"with":[80,113,128,133],"large":[81],"language":[82],"(LLMs),":[84],"compare":[86],"them":[87],"a":[89,94],"supervised":[90],"TimeSFormer":[91],"baseline.":[92],"Using":[93],"dataset":[95],"comprising":[96],"13.26":[97],"hours":[98],"simulated":[100],"evaluate":[105],"several":[106],"zero-shot":[107],"VLM-based":[108],"strategies":[109],"fine-tuned":[111,132],"VLMs":[112,126],"classification":[114],"heads,":[115],"including":[116],"Low-Rank":[117],"Adaptation":[118],"(LoRA).":[119],"Our":[120],"suggest":[122],"that":[123],"small":[124],"(local)":[125],"struggle":[127],"hallucinations,":[129],"when":[131],"LoRA,":[134],"reach":[137],"F1":[138],"score":[139],"at":[140],"0.91,":[141],"surpassing":[142],"TimeSformer":[144],"0.70.":[147]},"counts_by_year":[],"updated_date":"2026-02-19T06:27:42.648592","created_date":"2026-02-16T00:00:00"}