{"id":"https://openalex.org/W4414170187","doi":"https://doi.org/10.1109/avss65446.2025.11149918","title":"Zero-Shot Scene Understanding for Automatic Target Recognition Using Large Vision-Language Models","display_name":"Zero-Shot Scene Understanding for Automatic Target Recognition Using Large Vision-Language Models","publication_year":2025,"publication_date":"2025-08-11","ids":{"openalex":"https://openalex.org/W4414170187","doi":"https://doi.org/10.1109/avss65446.2025.11149918"},"language":"en","primary_location":{"id":"doi:10.1109/avss65446.2025.11149918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/avss65446.2025.11149918","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 Advanced Visual and Signal-Based Systems (AVSS)","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/A5011077674","display_name":"Yasiru Ranasinghe","orcid":"https://orcid.org/0000-0002-3678-3065"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yasiru Ranasinghe","raw_affiliation_strings":["Johns Hopkins University,Baltimore"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004330920","display_name":"Vibashan VS","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vibashan VS","raw_affiliation_strings":["Johns Hopkins University,Baltimore"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078301498","display_name":"James Uplinger","orcid":"https://orcid.org/0000-0002-0146-2130"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]},{"id":"https://openalex.org/I2802705668","display_name":"United States Army Combat Capabilities Development Command","ror":"https://ror.org/02rdkx920","country_code":"US","type":"other","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Uplinger","raw_affiliation_strings":["DEVCOM Army Research Laboratory,Adelphi"],"affiliations":[{"raw_affiliation_string":"DEVCOM Army Research Laboratory,Adelphi","institution_ids":["https://openalex.org/I166416128","https://openalex.org/I2802705668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048451016","display_name":"Celso P. de Melo","orcid":"https://orcid.org/0000-0002-2715-2448"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]},{"id":"https://openalex.org/I2802705668","display_name":"United States Army Combat Capabilities Development Command","ror":"https://ror.org/02rdkx920","country_code":"US","type":"other","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Celso De Melo","raw_affiliation_strings":["DEVCOM Army Research Laboratory,Adelphi"],"affiliations":[{"raw_affiliation_string":"DEVCOM Army Research Laboratory,Adelphi","institution_ids":["https://openalex.org/I166416128","https://openalex.org/I2802705668"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101429144","display_name":"Vishal M. Patel","orcid":"https://orcid.org/0000-0001-5083-7632"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vishal M. Patel","raw_affiliation_strings":["Johns Hopkins University,Baltimore"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5011077674"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12522684,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9993000030517578,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9983999729156494,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6759999990463257},{"id":"https://openalex.org/keywords/automatic-target-recognition","display_name":"Automatic target recognition","score":0.5637999773025513},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5364000201225281},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.5151000022888184},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.49559998512268066},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4020000100135803}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6759999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6557000279426575},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6331999897956848},{"id":"https://openalex.org/C117623542","wikidata":"https://www.wikidata.org/wiki/Q621974","display_name":"Automatic target recognition","level":3,"score":0.5637999773025513},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5364000201225281},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.5151000022888184},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.49559998512268066},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46959999203681946},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4020000100135803},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.272599995136261},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2712000012397766},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C14551309","wikidata":"https://www.wikidata.org/wiki/Q4636325","display_name":"3D single-object recognition","level":4,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/avss65446.2025.11149918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/avss65446.2025.11149918","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 Advanced Visual and Signal-Based Systems (AVSS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320316514","display_name":"Arm","ror":"https://ror.org/04mmhzs81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W1917989004","https://openalex.org/W2018818941","https://openalex.org/W2074935284","https://openalex.org/W2104636679","https://openalex.org/W2131815970","https://openalex.org/W2524910163","https://openalex.org/W2798836702","https://openalex.org/W3133259526","https://openalex.org/W3134329288","https://openalex.org/W3176709420","https://openalex.org/W3217535672","https://openalex.org/W4321448364","https://openalex.org/W4372267559","https://openalex.org/W4388878476","https://openalex.org/W4390874575","https://openalex.org/W4391801209","https://openalex.org/W4392172801","https://openalex.org/W4393990806","https://openalex.org/W4402039882","https://openalex.org/W4402716047"],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"target":[1],"recognition":[2,51,75],"(ATR)":[3],"is":[4],"crucial":[5],"for":[6,83,114],"safety-critical":[7],"tasks":[8],"such":[9,41,102],"as":[10,103],"navigation":[11],"and":[12,24,29,89,107],"surveillance,":[13],"particularly":[14],"in":[15,35,86,120],"demanding":[16],"military":[17,98],"scenarios":[18],"with":[19,58,73],"unfamiliar":[20],"terrains,":[21],"harsh":[22],"environments,":[23],"unseen":[25],"object":[26,31],"categories.":[27],"Conventional":[28],"open-world":[30,71],"detectors":[32,72],"often":[33],"fail":[34],"these":[36,63],"contexts,":[37],"lacking":[38],"exposure":[39],"to":[40],"novel":[42,87],"conditions.":[43],"Meanwhile,":[44],"Large":[45],"Vision-Language":[46],"Models":[47],"(LVLMs)":[48],"exhibit":[49],"zero-shot":[50,84],"capabilities":[52],"across":[53],"diverse":[54],"settings":[55],"yet":[56],"struggle":[57],"precise":[59],"localization.":[60],"We":[61],"address":[62],"limitations":[64],"by":[65],"combining":[66],"the":[67,74],"localization":[68],"strength":[69],"of":[70,77],"confidence":[76],"LVLMs,":[78],"creating":[79],"a":[80],"robust":[81],"pipeline":[82],"ATR":[85,118],"domains":[88],"classes.":[90],"Our":[91],"study":[92],"compares":[93],"several":[94],"LVLMs":[95],"on":[96],"underrepresented":[97],"vehicles,":[99],"examining":[100],"factors":[101],"distance":[104],"range,":[105],"modality,":[106],"prompting":[108],"strategies.":[109],"These":[110],"findings":[111],"provide":[112],"insights":[113],"developing":[115],"more":[116],"reliable":[117],"systems":[119],"uncharted":[121],"environments.":[122]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}