{"id":"https://openalex.org/W7128625153","doi":"https://doi.org/10.1109/icves65691.2025.11376443","title":"Label Anything, Train Nothing: 2D Zero-Shot Annotation via Generative VLMs, Zero-Shot Object Detectors and Foundation Models","display_name":"Label Anything, Train Nothing: 2D Zero-Shot Annotation via Generative VLMs, Zero-Shot Object Detectors and Foundation Models","publication_year":2025,"publication_date":"2025-10-27","ids":{"openalex":"https://openalex.org/W7128625153","doi":"https://doi.org/10.1109/icves65691.2025.11376443"},"language":null,"primary_location":{"id":"doi:10.1109/icves65691.2025.11376443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icves65691.2025.11376443","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 Vehicular Electronics and Safety (ICVES)","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/A5125673043","display_name":"Daniel Serrano Dominguez","orcid":null},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]},{"id":"https://openalex.org/I63634437","display_name":"Universidad Aut\u00f3noma de Madrid","ror":"https://ror.org/01cby8j38","country_code":"ES","type":"education","lineage":["https://openalex.org/I63634437"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Daniel Serrano Dominguez","raw_affiliation_strings":["Universidad Carlos III de Madrid,Autonomous Mobility and Perception Lab (AMPL),Departamento de Ingeniería de Sistemas y Automática,Madrid,Spain"],"affiliations":[{"raw_affiliation_string":"Universidad Carlos III de Madrid,Autonomous Mobility and Perception Lab (AMPL),Departamento de Ingeniería de Sistemas y Automática,Madrid,Spain","institution_ids":["https://openalex.org/I63634437","https://openalex.org/I50357001"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125651507","display_name":"Alejandro Salazar Gomez","orcid":null},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]},{"id":"https://openalex.org/I63634437","display_name":"Universidad Aut\u00f3noma de Madrid","ror":"https://ror.org/01cby8j38","country_code":"ES","type":"education","lineage":["https://openalex.org/I63634437"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alejandro Salazar Gomez","raw_affiliation_strings":["Universidad Carlos III de Madrid,Autonomous Mobility and Perception Lab (AMPL),Departamento de Ingeniería de Sistemas y Automática,Madrid,Spain"],"affiliations":[{"raw_affiliation_string":"Universidad Carlos III de Madrid,Autonomous Mobility and Perception Lab (AMPL),Departamento de Ingeniería de Sistemas y Automática,Madrid,Spain","institution_ids":["https://openalex.org/I63634437","https://openalex.org/I50357001"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050915847","display_name":"Alejandro Barrera","orcid":"https://orcid.org/0000-0001-5970-2961"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]},{"id":"https://openalex.org/I63634437","display_name":"Universidad Aut\u00f3noma de Madrid","ror":"https://ror.org/01cby8j38","country_code":"ES","type":"education","lineage":["https://openalex.org/I63634437"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alejandro Barrera","raw_affiliation_strings":["Universidad Carlos III de Madrid,Autonomous Mobility and Perception Lab (AMPL),Departamento de Ingeniería de Sistemas y Automática,Madrid,Spain"],"affiliations":[{"raw_affiliation_string":"Universidad Carlos III de Madrid,Autonomous Mobility and Perception Lab (AMPL),Departamento de Ingeniería de Sistemas y Automática,Madrid,Spain","institution_ids":["https://openalex.org/I63634437","https://openalex.org/I50357001"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084446725","display_name":"J. Godoy","orcid":"https://orcid.org/0009-0009-8435-4415"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]},{"id":"https://openalex.org/I63634437","display_name":"Universidad Aut\u00f3noma de Madrid","ror":"https://ror.org/01cby8j38","country_code":"ES","type":"education","lineage":["https://openalex.org/I63634437"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jaime Godoy","raw_affiliation_strings":["Universidad Carlos III de Madrid,Autonomous Mobility and Perception Lab (AMPL),Departamento de Ingeniería de Sistemas y Automática,Madrid,Spain"],"affiliations":[{"raw_affiliation_string":"Universidad Carlos III de Madrid,Autonomous Mobility and Perception Lab (AMPL),Departamento de Ingeniería de Sistemas y Automática,Madrid,Spain","institution_ids":["https://openalex.org/I63634437","https://openalex.org/I50357001"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101906705","display_name":"Fernando Garc\u00eda","orcid":"https://orcid.org/0000-0002-6156-4091"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]},{"id":"https://openalex.org/I63634437","display_name":"Universidad Aut\u00f3noma de Madrid","ror":"https://ror.org/01cby8j38","country_code":"ES","type":"education","lineage":["https://openalex.org/I63634437"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Fernando Garcia","raw_affiliation_strings":["Universidad Carlos III de Madrid,Autonomous Mobility and Perception Lab (AMPL),Departamento de Ingeniería de Sistemas y Automática,Madrid,Spain"],"affiliations":[{"raw_affiliation_string":"Universidad Carlos III de Madrid,Autonomous Mobility and Perception Lab (AMPL),Departamento de Ingeniería de Sistemas y Automática,Madrid,Spain","institution_ids":["https://openalex.org/I63634437","https://openalex.org/I50357001"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5125673043"],"corresponding_institution_ids":["https://openalex.org/I50357001","https://openalex.org/I63634437"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73773049,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.41620001196861267,"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":0.41620001196861267,"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":0.2547000050544739,"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":0.09049999713897705,"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/pascal","display_name":"Pascal (unit)","score":0.7455000281333923},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6651999950408936},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5942999720573425},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5572999715805054},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5486000180244446},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5371000170707703},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5059999823570251},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4918000102043152}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8514999747276306},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.7455000281333923},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6651999950408936},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5942999720573425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5572999715805054},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5572999715805054},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5486000180244446},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5371000170707703},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5059999823570251},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4918000102043152},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.41600000858306885},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.38499999046325684},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36629998683929443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3614000082015991},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.3018999993801117},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icves65691.2025.11376443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icves65691.2025.11376443","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 Vehicular Electronics and Safety (ICVES)","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":10,"referenced_works":["https://openalex.org/W2011953904","https://openalex.org/W2110764733","https://openalex.org/W2300469113","https://openalex.org/W2746791238","https://openalex.org/W2962919973","https://openalex.org/W4200597436","https://openalex.org/W4312420092","https://openalex.org/W4312563428","https://openalex.org/W4390874575","https://openalex.org/W4404612908"],"related_works":[],"abstract_inverted_index":{"Supervised":[0],"2D":[1,36],"detection":[2,103],"methods":[3],"rely":[4],"heavily":[5],"on":[6,122],"large":[7],"amounts":[8],"of":[9,43,78],"labeled":[10],"data":[11],"to":[12,82,90],"enable":[13],"robust":[14],"model":[15],"generalization.":[16],"However,":[17],"manually":[18],"annotating":[19],"such":[20],"datasets":[21],"is":[22,75],"inherently":[23],"unscalable":[24],"and":[25,63,128,133],"prohibitively":[26],"expensive.":[27],"We":[28,118],"propose":[29],"a":[30,50,85,108,143],"fully":[31],"automated,":[32],"training-free":[33],"approach":[34,48],"for":[35,54,59,69],"object":[37,61,95],"annotation,":[38],"built":[39],"upon":[40],"the":[41,64,76,79,93],"capabilities":[42,135],"pre-trained":[44],"zero-shot":[45,60],"models.":[46],"Our":[47,140],"integrates":[49],"Vision-Language":[51],"Model":[52,67],"(VLM)":[53],"class":[55,87],"extraction,":[56],"Grounding":[57],"DINO":[58],"detection,":[62],"Segment":[65],"Anything":[66],"(SAM)":[68],"mask":[70],"generation.":[71],"A":[72],"key":[73],"contribution":[74],"use":[77],"VLM":[80],"not":[81],"query":[83],"against":[84],"full":[86],"list,":[88],"but":[89],"first":[91],"identify":[92],"specific":[94],"categories":[96],"present":[97],"in":[98],"an":[99],"image,":[100],"drastically":[101],"improving":[102],"quality.":[104],"Furthermore,":[105],"we":[106],"introduce":[107],"refinement":[109],"step":[110],"using":[111],"Non-Maximum":[112],"Suppression":[113],"(NMS),":[114],"eliminating":[115],"duplicate":[116],"predictions.":[117],"evaluate":[119],"our":[120],"pipeline":[121],"diverse":[123],"benchmarks,":[124],"including":[125],"PASCAL":[126],"VOC":[127],"COCO,":[129],"demonstrating":[130],"its":[131],"effectiveness":[132],"generalization":[134],"without":[136],"any":[137],"task-specific":[138],"training.":[139],"method":[141],"offers":[142],"practical":[144],"path":[145],"towards":[146],"accelerating":[147],"dataset":[148],"creation":[149],"with":[150],"minimal":[151],"human":[152],"supervision.":[153]},"counts_by_year":[],"updated_date":"2026-02-12T06:17:30.163165","created_date":"2026-02-12T00:00:00"}