{"id":"https://openalex.org/W7130536856","doi":"https://doi.org/10.1109/ictc66702.2025.11388520","title":"Top-Down Data Generation Using Vision\u2013Language Models for Object Detection in Constrained Battlefield Environments","display_name":"Top-Down Data Generation Using Vision\u2013Language Models for Object Detection in Constrained Battlefield Environments","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W7130536856","doi":"https://doi.org/10.1109/ictc66702.2025.11388520"},"language":null,"primary_location":{"id":"doi:10.1109/ictc66702.2025.11388520","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11388520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5126370552","display_name":"Yerin Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yerin Kim","raw_affiliation_strings":["ETRI,Digital Convergence Research Laboratory,Daejeon,Korea,34129"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETRI,Digital Convergence Research Laboratory,Daejeon,Korea,34129","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126393814","display_name":"Jaeuk Baek","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaeuk Baek","raw_affiliation_strings":["ETRI,Digital Convergence Research Laboratory,Daejeon,Korea,34129"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETRI,Digital Convergence Research Laboratory,Daejeon,Korea,34129","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028187951","display_name":"Donggyu Choi","orcid":"https://orcid.org/0000-0002-9721-2856"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Donggyu Choi","raw_affiliation_strings":["ETRI,Digital Convergence Research Laboratory,Daejeon,Korea,34129"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETRI,Digital Convergence Research Laboratory,Daejeon,Korea,34129","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080108695","display_name":"Chang-Eun Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chang-Eun Lee","raw_affiliation_strings":["ETRI,Digital Convergence Research Laboratory,Daejeon,Korea,34129"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETRI,Digital Convergence Research Laboratory,Daejeon,Korea,34129","institution_ids":["https://openalex.org/I142401562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I142401562"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"28","last_page":"32"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.6014999747276306,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.6014999747276306,"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":0.13740000128746033,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.03920000046491623,"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/object-detection","display_name":"Object detection","score":0.7771999835968018},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6819999814033508},{"id":"https://openalex.org/keywords/battlefield","display_name":"Battlefield","score":0.6398000121116638},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5687000155448914},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.527400016784668},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.5149000287055969},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.49399998784065247},{"id":"https://openalex.org/keywords/viola\u2013jones-object-detection-framework","display_name":"Viola\u2013Jones object detection framework","score":0.46630001068115234}],"concepts":[{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7771999835968018},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7002999782562256},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6819999814033508},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6802999973297119},{"id":"https://openalex.org/C2779669469","wikidata":"https://www.wikidata.org/wiki/Q4895508","display_name":"Battlefield","level":2,"score":0.6398000121116638},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6172999739646912},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5687000155448914},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.527400016784668},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.5149000287055969},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.49399998784065247},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.46630001068115234},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4083000123500824},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3937000036239624},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.35420000553131104},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.34380000829696655},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3174999952316284},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2847999930381775},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.2581999897956848}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc66702.2025.11388520","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11388520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334874","display_name":"Defense Acquisition Program Administration","ror":"https://ror.org/04bjg9m96"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2005245503","https://openalex.org/W2133665775","https://openalex.org/W2889985731","https://openalex.org/W4386076215","https://openalex.org/W4404612908","https://openalex.org/W4413146305"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,51],"paper,":[2],"we":[3,91,114],"propose":[4],"a":[5,97,110],"novel":[6],"object":[7,23,84,89,99,155],"detection":[8,85,156],"framework":[9,16,144],"based":[10],"on":[11],"Vision\u2013Language":[12],"Models":[13],"(VLMs).":[14],"The":[15,71],"integrates":[17],"synthetic":[18,31,55,148],"top-down":[19,56,79,149],"image":[20,69,121],"generation,":[21],"automatic":[22],"labeling,":[24,90],"and":[25,30,45,62,101,127,152],"efficient":[26],"composition":[27],"of":[28,112,118,141],"real":[29,78],"data":[32,39,52,103,151],"for":[33],"robust":[34],"model":[35],"training.":[36],"Specifically,":[37],"ground-view":[38],"are":[40,47,74],"collected":[41],"using":[42],"mobile":[43],"robots,":[44],"VLMs":[46,66],"employed":[48],"to":[49,67,81,106],"transform":[50],"into":[53],"high-quality":[54,147],"images.":[57],"We":[58],"optimize":[59],"both":[60],"positive":[61],"negative":[63],"prompts":[64],"in":[65,123,145,153,158],"maximize":[68],"quality.":[70],"generated":[72],"outputs":[73],"then":[75],"combined":[76],"with":[77],"images":[80],"train":[82],"the":[83,93,116,124,129,139,142],"model.":[86],"To":[87],"automate":[88],"utilize":[92],"Grounding":[94],"DINO":[95],"model,":[96],"vision\u2013language":[98],"detector,":[100],"apply":[102],"augmentation":[104],"techniques":[105],"improve":[107],"generalization.":[108],"Through":[109],"series":[111],"experiments,":[113],"investigate":[115],"impact":[117],"different":[119],"synthetic-to-real":[120],"ratios":[122],"training":[125],"set":[126],"identify":[128],"optimal":[130],"combination":[131],"through":[132],"quantitative":[133],"performance":[134,157],"analysis.":[135],"Experimental":[136],"results":[137],"demonstrate":[138],"effectiveness":[140],"proposed":[143],"generating":[146],"view":[150],"enhancing":[154],"constrained":[159],"battlefield":[160],"environments.":[161]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-20T00:00:00"}