<?xml version="1.0" encoding="UTF-8"?><resource xmlns="http://datacite.org/schema/kernel-4"><identifier identifierType="URL">https://inrepscholar.com/projects/954</identifier><creators><creator><creatorName>Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby</creatorName></creator></creators><titles><title>an-image-is-worth-16x16-words-transformers-for-image-recognition-at-scale-2023-015</title></titles><publisher>UFTAN UNIVERSITY</publisher><publicationYear>2023</publicationYear><resourceType resourceTypeGeneral="Text">Masters Thesis</resourceType><descriptions><description descriptionType="Abstract">This record links to the Vision Transformer paper, which adapts transformer architectures to image classification through patch-based image representation. It is useful for validating computer vision categories and AI search relevance.</description></descriptions></resource>