{"id":"https://openalex.org/W4416055831","doi":"https://doi.org/10.1109/wacv61042.2026.00559","title":"BlendCLIP: Bridging Synthetic and Real Domains for Zero-Shot 3D Object Classification with Multimodal Pretraining","display_name":"BlendCLIP: Bridging Synthetic and Real Domains for Zero-Shot 3D Object Classification with Multimodal Pretraining","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4416055831","doi":"https://doi.org/10.1109/wacv61042.2026.00559"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.18244","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015757522","display_name":"Ajinkya Khoche","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Ajinkya Khoche","raw_affiliation_strings":["KTH Royal Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gerg\u0151 L\u00e1szl\u00f3 Nagy","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Gerg\u0151 L\u00e1szl\u00f3 Nagy","raw_affiliation_strings":["KTH Royal Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030926823","display_name":"Maciej K. Wozniak","orcid":"https://orcid.org/0000-0002-3432-6151"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Maciej Wozniak","raw_affiliation_strings":["KTH Royal Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034423781","display_name":"Thomas Gustafsson","orcid":"https://orcid.org/0000-0002-0079-9049"},"institutions":[{"id":"https://openalex.org/I1294350288","display_name":"Scania (Sweden)","ror":"https://ror.org/03g4sde39","country_code":"SE","type":"company","lineage":["https://openalex.org/I1294350288"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Thomas Gustafsson","raw_affiliation_strings":["Scania CV AB"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scania CV AB","institution_ids":["https://openalex.org/I1294350288"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028082686","display_name":"Patric Jensfelt","orcid":"https://orcid.org/0000-0002-1170-7162"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Patric Jensfelt","raw_affiliation_strings":["KTH Royal Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"5766","last_page":"5775"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.34940001368522644,"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":0.34940001368522644,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.1876000016927719,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.1185000017285347,"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/bridging","display_name":"Bridging (networking)","score":0.8152999877929688},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.6686999797821045},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6013000011444092},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.583899974822998},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5260999798774719},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.504800021648407},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4810999929904938},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.47909998893737793},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4171000123023987},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.39899998903274536}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8152999877929688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8051999807357788},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.6686999797821045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6384999752044678},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6013000011444092},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.583899974822998},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5260999798774719},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.504800021648407},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4810999929904938},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47909998893737793},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4293000102043152},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.39899998903274536},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.38929998874664307},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.37529999017715454},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3215999901294708},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.31529998779296875},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26499998569488525},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/wacv61042.2026.00559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.18244","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.18244","pdf_url":"https://arxiv.org/pdf/2510.18244","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:DiVA.org:kth-378741","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-378741","pdf_url":null,"source":{"id":"https://openalex.org/S4306400653","display_name":"Diva portal (Dalarna University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2510.18244","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.18244","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.18244","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.18244","pdf_url":"https://arxiv.org/pdf/2510.18244","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0],"3D":[1,118,232],"object":[2],"classification":[3],"is":[4,14,123,158,225],"crucial":[5],"for":[6,27],"real-world":[7,112,150,166,223],"applications":[8],"like":[9,192],"autonomous":[10],"driving,":[11],"however":[12],"it":[13,144],"often":[15],"hindered":[16],"by":[17,81,179,202],"a":[18,72,92,96,103,124],"significant":[19],"domain":[20,219],"gap":[21,80],"between":[22],"the":[23,30,37,60,84,132,135,146,176,198,226],"synthetic":[24,44,138,212],"data":[25,45,58,114,126,140],"used":[26],"training":[28,171],"and":[29,107,115,194,236],"sparse,":[31],"noisy":[32],"LiDAR":[33],"scans":[34],"encountered":[35],"in":[36,134],"real-world.":[38],"Current":[39],"methods":[40],"trained":[41,54],"solely":[42],"on":[43,56,175,188,204,210,243],"fail":[46],"to":[47,49,63,94,145,228],"generalize":[48],"outdoor":[50,190],"scenes,":[51],"while":[52,206],"those":[53],"only":[55],"real":[57],"lack":[59],"semantic":[61],"diversity":[62],"recognize":[64],"rare":[65],"or":[66],"unseen":[67],"objects.":[68],"We":[69,89],"introduce":[70],"BlendCLIP,":[71],"multimodal":[73],"pretraining":[74],"framework":[75],"that":[76,129,155,217],"bridges":[77],"this":[78],"synthetic-to-real":[79],"strategically":[82],"combining":[83],"strengths":[85],"of":[86,99,102,149],"both":[87],"domains.":[88],"first":[90,130],"propose":[91],"pipeline":[93],"generate":[95],"large-scale":[97],"dataset":[98,237],"object-level":[100],"triplets\u2014consisting":[101],"point":[104],"cloud,":[105],"image,":[106],"text":[108],"description\u2014mined":[109],"directly":[110],"from":[111],"driving":[113],"human":[116],"annotated":[117],"boxes.":[119],"Our":[120,152,214,234],"core":[121],"contribution":[122],"curriculum-based":[125],"mixing":[127],"strategy":[128],"grounds":[131],"model":[133,184],"semantically":[136],"rich":[137],"CAD":[139],"before":[141],"progressively":[142],"adapting":[143],"specific":[147],"characteristics":[148],"scans.":[151],"experiments":[153],"show":[154],"our":[156,182],"approach":[157],"highly":[159],"label-efficient:":[160],"introducing":[161],"as":[162,164],"few":[163],"1.5%":[165],"samples":[167],"per":[168],"batch":[169],"into":[170],"boosts":[172],"zero-shot":[173],"accuracy":[174],"nuScenes":[177,193],"benchmark":[178],"27%.":[180],"Consequently,":[181],"final":[183],"achieves":[185],"state-of-the-art":[186],"performance":[187],"challenging":[189],"datasets":[191],"TruckScenes,":[195],"improving":[196],"over":[197],"best":[199],"prior":[200],"method":[201],"19.3%":[203],"nuScenes,":[205],"maintaining":[207],"strong":[208],"generalization":[209],"diverse":[211],"benchmarks.":[213],"findings":[215],"demonstrate":[216],"effective":[218],"adaptation,":[220],"not":[221],"full-scale":[222],"annotation,":[224],"key":[227],"unlocking":[229],"robust":[230],"open-vocabulary":[231],"perception.":[233],"code":[235],"will":[238],"be":[239],"released":[240],"upon":[241],"acceptance":[242],"https://github.com/kesu1/BlendCLIP.":[244]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-24T00:00:00"}