{"id":"https://openalex.org/W4408112786","doi":"https://doi.org/10.1145/3721291","title":"Video Fire Recognition Using Zero-Shot Vision-Language Models Guided by a Task-Aware Object Detector","display_name":"Video Fire Recognition Using Zero-Shot Vision-Language Models Guided by a Task-Aware Object Detector","publication_year":2025,"publication_date":"2025-03-03","ids":{"openalex":"https://openalex.org/W4408112786","doi":"https://doi.org/10.1145/3721291"},"language":"en","primary_location":{"id":"doi:10.1145/3721291","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721291","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3721291","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3721291","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038476909","display_name":"Diego Gragnaniello","orcid":"https://orcid.org/0000-0003-4271-8160"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Diego Gragnaniello","raw_affiliation_strings":["Department of Information Engineering, Electrical Engineering and Applied Mathematics, University of Salerno, Fisciano, Italy","Department of Information and Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, Italy"],"raw_orcid":"https://orcid.org/0000-0003-4271-8160","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Electrical Engineering and Applied Mathematics, University of Salerno, Fisciano, Italy","institution_ids":["https://openalex.org/I131729948"]},{"raw_affiliation_string":"Department of Information and Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, Italy","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071216669","display_name":"Antonio Greco","orcid":"https://orcid.org/0000-0002-5495-2432"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Antonio Greco","raw_affiliation_strings":["Department of Information Engineering, Electrical Engineering and Applied Mathematics, University of Salerno, Fisciano, Italy","Department of Information and Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, Italy"],"raw_orcid":"https://orcid.org/0000-0002-5495-2432","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Electrical Engineering and Applied Mathematics, University of Salerno, Fisciano, Italy","institution_ids":["https://openalex.org/I131729948"]},{"raw_affiliation_string":"Department of Information and Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, Italy","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090709130","display_name":"Carlo Sansone","orcid":"https://orcid.org/0000-0002-8176-6950"},"institutions":[{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Carlo Sansone","raw_affiliation_strings":["Department of Electrical Engineering and Information Technology, University of Napoli Federico II, Napoli, Italy","Department of Electrical Engineering and Information Technology (DIETI), University of Napoli Federico II, Italy"],"raw_orcid":"https://orcid.org/0000-0002-8176-6950","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Technology, University of Napoli Federico II, Napoli, Italy","institution_ids":["https://openalex.org/I71267560"]},{"raw_affiliation_string":"Department of Electrical Engineering and Information Technology (DIETI), University of Napoli Federico II, Italy","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092302658","display_name":"Bruno Vento","orcid":"https://orcid.org/0009-0006-7687-4929"},"institutions":[{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Bruno Vento","raw_affiliation_strings":["Department of Electrical Engineering and Information Technology, University of Napoli Federico II, Napoli, Italy","Department of Electrical Engineering and Information Technology (DIETI), University of Napoli Federico II, Italy"],"raw_orcid":"https://orcid.org/0009-0006-7687-4929","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Technology, University of Napoli Federico II, Napoli, Italy","institution_ids":["https://openalex.org/I71267560"]},{"raw_affiliation_string":"Department of Electrical Engineering and Information Technology (DIETI), University of Napoli Federico II, Italy","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.167,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.93013075,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"21","issue":"10","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12597","display_name":"Fire Detection and Safety Systems","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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/T12597","display_name":"Fire Detection and Safety Systems","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9907000064849854,"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/T11500","display_name":"Evacuation and Crowd Dynamics","score":0.9688000082969666,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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-science","display_name":"Computer science","score":0.8983712196350098},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.7046827673912048},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6952667236328125},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.6518939137458801},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.620774507522583},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5468761920928955},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5285605192184448},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.46007758378982544},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4062980115413666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8983712196350098},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7046827673912048},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6952667236328125},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.6518939137458801},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.620774507522583},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5468761920928955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5285605192184448},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.46007758378982544},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4062980115413666},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3721291","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721291","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3721291","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3721291","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721291","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3721291","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4408112786.pdf"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1971301114","https://openalex.org/W1996199746","https://openalex.org/W2002924977","https://openalex.org/W2011160765","https://openalex.org/W2103941746","https://openalex.org/W2128187493","https://openalex.org/W2146926380","https://openalex.org/W2171201674","https://openalex.org/W2746174042","https://openalex.org/W2751420734","https://openalex.org/W2780222614","https://openalex.org/W2790037986","https://openalex.org/W2810053451","https://openalex.org/W2896348597","https://openalex.org/W2919981789","https://openalex.org/W2945689790","https://openalex.org/W2963294168","https://openalex.org/W3013887673","https://openalex.org/W3015758410","https://openalex.org/W3015965768","https://openalex.org/W3034526883","https://openalex.org/W3048051277","https://openalex.org/W3100742769","https://openalex.org/W3110232229","https://openalex.org/W3129096368","https://openalex.org/W3136931902","https://openalex.org/W3164816468","https://openalex.org/W3199537137","https://openalex.org/W3209814133","https://openalex.org/W4205785826","https://openalex.org/W4212958975","https://openalex.org/W4213140935","https://openalex.org/W4220808058","https://openalex.org/W4223958543","https://openalex.org/W4229055310","https://openalex.org/W4236965008","https://openalex.org/W4283380979","https://openalex.org/W4283716939","https://openalex.org/W4285550832","https://openalex.org/W4303645011","https://openalex.org/W4306952468","https://openalex.org/W4311089311","https://openalex.org/W4318464214","https://openalex.org/W4319297957","https://openalex.org/W4319600119","https://openalex.org/W4322742119","https://openalex.org/W4362598372","https://openalex.org/W4365800072","https://openalex.org/W4385342336","https://openalex.org/W4388823657","https://openalex.org/W4390498446","https://openalex.org/W4392172801","https://openalex.org/W4403998060"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2732813147","https://openalex.org/W2143460112","https://openalex.org/W2042906257"],"abstract_inverted_index":{"Fire":[0,116],"detection":[1,137,264],"from":[2,74],"images":[3],"or":[4,85],"videos":[5],"has":[6],"gained":[7],"a":[8,65,123,189,227],"growing":[9],"interest":[10],"in":[11,49,71,78,130],"recent":[12,262],"years":[13],"due":[14,292],"to":[15,30,126,150,160,207,230,293],"the":[16,19,42,50,75,107,145,158,168,174,192,209,217,232,236,244,251,257,267,270,277,280,283],"criticality":[17],"of":[18,44,80,103,144,173,191,201,273,279],"application.":[20],"Both":[21],"reliable":[22],"real-time":[23,306,314],"detectors":[24,129],"and":[25,105,138,179,238,269,316],"efficient":[26],"retrieval":[27,252,318],"techniques,":[28],"able":[29,149],"process":[31],"large":[32,320],"databases":[33],"acquired":[34],"by":[35,92,167,221,243,256],"sensor":[36],"networks,":[37,224],"are":[38,55,164],"needed.":[39],"Even":[40],"if":[41],"reliability":[43],"artificial":[45],"vision":[46],"methods":[47,62],"improved":[48],"last":[51],"years,":[52],"some":[53],"issues":[54],"still":[56],"open":[57],"problems.":[58],"In":[59,110],"particular,":[60],"literature":[61],"often":[63],"reveal":[64],"low":[66],"generalization":[67,171,271],"capability":[68,143,172],"when":[69],"employed":[70],"scenarios":[72],"different":[73],"training":[76],"ones":[77],"terms":[79],"framing":[81],"distance,":[82],"surrounding":[83],"environment,":[84],"weather":[86],"conditions.":[87],"This":[88,308],"can":[89,177,249],"be":[90],"addressed":[91],"considering":[93],"contextual":[94],"information":[95,139,211,219,241,317],"and,":[96],"more":[97],"specifically,":[98],"using":[99,235],"vision-language":[100,133,233,284],"models":[101,134,234],"capable":[102],"interpreting":[104],"describing":[106],"framed":[108],"scene.":[109],"this":[111],"work,":[112],"we":[113,225],"propose":[114,226],"FIRE-TASTIC:":[115],"Recognition":[117],"with":[118,132,212],"Task-Aware":[119],"Spatio-Temporal":[120],"Image":[121],"Captioning,":[122],"novel":[124,228],"framework":[125,194],"use":[127],"object":[128,245],"conjunction":[131],"for":[135,289,305,312],"fire":[136,154,263],"retrieval.":[140],"The":[141,247],"localization":[142,240],"former":[146],"makes":[147,309],"it":[148],"detect":[151],"even":[152],"tiny":[153],"traces":[155],"but":[156],"expose":[157],"system":[159],"false":[161],"alarms.":[162],"These":[163],"strongly":[165],"reduced":[166],"impressive":[169],"zero-shot":[170],"latter,":[175],"which":[176,204,275,286],"recognize":[178],"describe":[180],"fire-like":[181],"objects":[182],"without":[183],"prior":[184],"fine-tuning.":[185],"We":[186],"also":[187],"present":[188],"variant":[190],"FIRE-TASTIC":[193,310],"based":[195],"on":[196,260,301,319],"visual":[197],"question":[198],"answering":[199],"instead":[200],"image":[202],"captioning,":[203],"allows":[205],"one":[206],"customize":[208],"retrieved":[210],"personalized":[213],"questions.":[214],"To":[215],"integrate":[216],"high-level":[218],"provided":[220,242],"both":[222,313],"neural":[223],"method":[229],"query":[231],"temporal":[237],"spatial":[239],"detector.":[246],"proposal":[248],"improve":[250],"performance,":[253],"as":[254],"evidenced":[255],"experiments":[258],"conducted":[259],"two":[261],"datasets,":[265],"showing":[266],"effectiveness":[268],"capabilities":[272],"FIRE-TASTIC,":[274],"surpasses":[276],"state":[278],"art.":[281],"Moreover,":[282],"model,":[285],"is":[287,298],"unsuitable":[288],"video":[290],"processing":[291,315],"its":[294],"high":[295],"computational":[296],"load,":[297],"executed":[299],"only":[300],"suspicious":[302],"frames,":[303],"allowing":[304],"processing.":[307],"suitable":[311],"datasets.":[321]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
