{"id":"https://openalex.org/W7140627202","doi":"https://doi.org/10.1109/ieeeconf67917.2025.11443843","title":"FABLE: Florence-2\u2013Assisted Behavioral Learning and Embedding for Multilabel Action Recognition","display_name":"FABLE: Florence-2\u2013Assisted Behavioral Learning and Embedding for Multilabel Action Recognition","publication_year":2025,"publication_date":"2025-10-26","ids":{"openalex":"https://openalex.org/W7140627202","doi":"https://doi.org/10.1109/ieeeconf67917.2025.11443843"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf67917.2025.11443843","doi":"https://doi.org/10.1109/ieeeconf67917.2025.11443843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf67917.2025.11443843","pdf_url":null,"source":{"id":"https://openalex.org/S4363608623","display_name":"Asilomar Conference on Signals, Systems and Computers (ACSSC)","issn_l":"1058-6393","issn":["1058-6393","2576-2303"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 59th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5138471652","display_name":"Jonathan McGee","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan McGee","raw_affiliation_strings":["University of Virginia,Department of ECE,Charlottesville,VA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia,Department of ECE,Charlottesville,VA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080729988","display_name":"Soumee Guha","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soumee Guha","raw_affiliation_strings":["University of Virginia,Department of ECE,Charlottesville,VA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia,Department of ECE,Charlottesville,VA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106638185","display_name":"Lisa S. Berlizova","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lisa S. Berlizova","raw_affiliation_strings":["University of Virginia,Department of ECE,Charlottesville,VA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia,Department of ECE,Charlottesville,VA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081562360","display_name":"Peter A. Youngs","orcid":"https://orcid.org/0000-0002-1711-1749","observed_orcids":["https://orcid.org/0000-0002-1711-1749"]},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Youngs","raw_affiliation_strings":["University of Virginia,Department of CISE,Charlottesville,VA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia,Department of CISE,Charlottesville,VA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034452294","display_name":"Scott T. Acton","orcid":"https://orcid.org/0000-0003-3288-1255","observed_orcids":["https://orcid.org/0000-0003-3288-1255"]},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott T. Acton","raw_affiliation_strings":["University of Virginia,Department of ECE,Charlottesville,VA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia,Department of ECE,Charlottesville,VA","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"377","last_page":"381"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9735999703407288,"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":0.9735999703407288,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.02280000038444996,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.0013000000035390258,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/florence-2","display_name":"Florence-2","score":0.8119999766349792},{"id":"https://openalex.org/keywords/visual-grounding","display_name":"visual grounding","score":0.7620000243186951},{"id":"https://openalex.org/keywords/teacher-student-relationship","display_name":"teacher-student relationship","score":0.6940000057220459},{"id":"https://openalex.org/keywords/text-embeddings","display_name":"text embeddings","score":0.48899999260902405},{"id":"https://openalex.org/keywords/fine-tuning-pre-trained-models","display_name":"pre-trained model fine-tuning","score":0.6119999885559082}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5825999975204468},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5378000140190125},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5220000147819519},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5157999992370605},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2962999939918518},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28029999136924744},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.26030001044273376}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf67917.2025.11443843","doi":"https://doi.org/10.1109/ieeeconf67917.2025.11443843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf67917.2025.11443843","pdf_url":null,"source":{"id":"https://openalex.org/S4363608623","display_name":"Asilomar Conference on Signals, Systems and Computers (ACSSC)","issn_l":"1058-6393","issn":["1058-6393","2576-2303"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 59th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.6164000034332275}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W55768394","https://openalex.org/W1567302070","https://openalex.org/W1999954155","https://openalex.org/W2119466907","https://openalex.org/W2156935079","https://openalex.org/W2549365021","https://openalex.org/W2604675517","https://openalex.org/W2904572180","https://openalex.org/W2913978442","https://openalex.org/W2932399282","https://openalex.org/W2982112268","https://openalex.org/W2998420437","https://openalex.org/W3035591000","https://openalex.org/W3152893301","https://openalex.org/W3160190143","https://openalex.org/W4312881242","https://openalex.org/W4392827338","https://openalex.org/W4393148669","https://openalex.org/W4402660140","https://openalex.org/W4403905772","https://openalex.org/W4404604719","https://openalex.org/W4407692915","https://openalex.org/W4408861326","https://openalex.org/W4409536933"],"related_works":["https://openalex.org/W7131085021","https://openalex.org/W6979290342","https://openalex.org/W4415901493","https://openalex.org/W4408323594","https://openalex.org/W4390872452","https://openalex.org/W7123345998","https://openalex.org/W7135026191","https://openalex.org/W4388854793","https://openalex.org/W3200114289","https://openalex.org/W4408032607"],"abstract_inverted_index":{"Understanding":[0],"complex":[1],"activities":[2,75],"in":[3],"a":[4,13,21,31,46,86,96,122,132,170,196],"scene":[5],"requires":[6],"capturing":[7],"subtle":[8],"actor\u2013actor":[9],"and":[10,52,73,92,127,141,186,192],"actor\u2013object":[11],"interactions,":[12],"problem":[14],"made":[15],"significantly":[16],"harder":[17],"when":[18],"restricted":[19],"to":[20,34,68,82,89,153],"single":[22],"video":[23],"frame.":[24,107],"Generative":[25],"Visual":[26],"Language":[27],"Models":[28],"(VLMs)":[29],"have":[30],"salient":[32],"ability":[33],"construct":[35],"coherent":[36,133],"captions,":[37],"identify":[38,43,154],"object":[39],"regions,":[40],"or":[41],"even":[42],"objects":[44],"from":[45,118],"given":[47],"phrase.":[48],"Florence2\u2013Assisted":[49],"Behavioral":[50],"Learning":[51],"Embedding":[53],"(FABLE)":[54],"for":[55,163],"Multilabel":[56],"Action":[57],"Recognition":[58],"combines":[59],"Florence-2\u2019s":[60,111],"regionbased":[61],"visual":[62,91,126],"grounding":[63],"with":[64,114],"discriminative":[65],"text-embedding":[66],"cues":[67],"understand":[69],"the":[70,101,155],"teacher-student":[71],"interactions":[72],"individual":[74,200],"within":[76,105],"an":[77],"elementary":[78,147],"classroom":[79,148,164],"environment.":[80],"Analogous":[81],"CLIP,":[83],"FABLE":[84,109,150],"employs":[85],"cross-similarity":[87],"mechanism":[88],"align":[90],"textual":[93],"representations,":[94],"generating":[95],"logit":[97],"distribution":[98],"that":[99,130,159],"identifies":[100],"most":[102,161],"probable":[103],"actions":[104],"each":[106],"However,":[108],"incorporates":[110],"image\u2013prompt":[112],"embeddings":[113,116],"text":[115],"derived":[117],"label":[119],"definitions,":[120],"learning":[121],"one-to-one":[123],"alignment":[124],"between":[125],"semantic":[128],"spaces":[129],"yields":[131],"multilabel":[134],"probability":[135],"distribution.":[136],"Across":[137],"23,000":[138],"training":[139],"frames":[140,144],"5,000":[142],"test":[143],"of":[145,174,179,184,190],"labeled":[146],"data,":[149],"was":[151],"used":[152],"Florence-2":[156],"pretrained":[157],"tasks":[158],"fine-tune":[160],"effectively":[162],"action":[165],"recognition.":[166],"The":[167],"model":[168],"achieved":[169],"micro":[171,176],"F1":[172,182],"score":[173,178,183,189],"0.74,":[175,180],"mAP":[177,188],"macro":[181,187],"0.77,":[185],"0.65,":[191],"we":[193],"further":[194],"report":[195],"detailed":[197],"performance":[198],"across":[199],"classes.":[201]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-03-27T00:00:00"}