{"dcterms:modified":"2024-04-14","dcterms:creator":"Harvard Dataverse","@type":"ore:ResourceMap","schema:additionalType":"Dataverse OREMap Format v1.0.0","dvcore:generatedBy":{"@type":"schema:SoftwareApplication","schema:name":"Dataverse","schema:version":"6.1 build iqss-prod-patch","schema:url":"https://github.com/iqss/dataverse"},"@id":"https://dataverse.harvard.edu/api/datasets/export?exporter=OAI_ORE&persistentId=https://doi.org/10.7910/DVN/PRHQMK","ore:describes":{"citation:keyword":[{"citation:keywordValue":"Open-Vocabulary Object Detection with Vision Transformers (OWL-ViT)"},{"citation:keywordValue":"Object Detection"},{"citation:keywordValue":"Vision Transformers"},{"citation:keywordValue":"End-to-End Training"},{"citation:keywordValue":"Generalized Intersection over Union (gIoU) Loss"}],"publication":{"publicationIDNumber":"10.5281/zenodo.10938342"},"citation:dsDescription":{"citation:dsDescriptionValue":"Computer vision has been receiving increasing attention with the recent complex Generative AI models released by tech industry giants, such as OpenAI and Google. However, there is a specific subfield that we wanted to focus on, that is, Image-Guided Object Detection. A detailed literature survey directed us towards a successful study called Simple Open-Vocabulary Object Detection with Vision Transformers (OWL-ViT) [1], which is a multifunctional complex model that can also perform image-guided object detection as a side function. In this study, some experiments have been conducted utilizing OWL-ViT architecture as the base model and manipulated the necessary parts to achieve a better one-shot performance. Code and models are available on GitHub.","citation:dsDescriptionDate":"2024-04-15"},"citation:datasetContact":{"citation:datasetContactName":"Melih Serin","citation:datasetContactAffiliation":"Boğaziçi University","citation:datasetContactEmail":"melihsrnn@gmail.com"},"author":{"citation:authorName":"Melih Serin","citation:authorAffiliation":"Boğaziçi University"},"title":"Image-Guided Object Detection using OWL-ViTand Enhanced Query Embedding Extraction","subject":"Engineering","citation:depositor":"KUUJE","dateOfDeposit":"2024-04-14","@id":"https://doi.org/10.7910/DVN/PRHQMK","@type":["ore:Aggregation","schema:Dataset"],"schema:version":"1.0","schema:name":"Image-Guided Object Detection using OWL-ViTand Enhanced Query Embedding Extraction","schema:dateModified":"2024-04-14 18:49:15.591","schema:datePublished":"2024-04-14","schema:creativeWorkStatus":"RELEASED","schema:license":"http://creativecommons.org/publicdomain/zero/1.0","dvcore:fileTermsOfAccess":{"dvcore:fileRequestAccess":true},"schema:includedInDataCatalog":"Harvard Dataverse","schema:isPartOf":{"schema:name":"Harvard Dataverse","@id":"https://dataverse.harvard.edu/dataverse/harvard","schema:description":"<span><span><span><h3>Share, archive, and get credit for your data. Find and cite data across all research fields.</h3></span></span></span>"},"ore:aggregates":[{"schema:name":"ImageGuidedObjectDetection.pdf","dvcore:restricted":false,"schema:version":1,"dvcore:datasetVersionId":415335,"@id":"https://dataverse.harvard.edu/file.xhtml?fileId=10117853","schema:sameAs":"https://dataverse.harvard.edu/api/access/datafile/10117853","@type":"ore:AggregatedResource","schema:fileFormat":"application/pdf","dvcore:filesize":4173342,"dvcore:storageIdentifier":"s3://dvn-cloud:18edeccb62a-f3945d289a53","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"3d43488c06f591c6c2a832dc82181d05"}}],"schema:hasPart":["https://dataverse.harvard.edu/file.xhtml?fileId=10117853"]},"@context":{"author":"http://purl.org/dc/terms/creator","citation":"https://dataverse.org/schema/citation/","dateOfDeposit":"http://purl.org/dc/terms/dateSubmitted","dcterms":"http://purl.org/dc/terms/","dvcore":"https://dataverse.org/schema/core#","ore":"http://www.openarchives.org/ore/terms/","publication":"http://purl.org/dc/terms/isReferencedBy","publicationIDNumber":"http://purl.org/spar/datacite/ResourceIdentifier","schema":"http://schema.org/","subject":"http://purl.org/dc/terms/subject","title":"http://purl.org/dc/terms/title"}}