Thomas Unterthiner | VitaVision

Thomas Unterthiner

ORCIDOpenAlex

1 paper in the Atlas registry, 2020. Their work underpins 10 Atlas pages across 4 domains, is the primary source of 1, and runs through 6 narratives.

Papers over time

primary source of a pagecited by a pageno Atlas page yet
’20ViT

Contribution to the Atlas

primary sourcecited as a reference
Representation learning7 pages
ViTCLIPDeiTDINOv2MAEPositional EncodingTransformer
Depth1 page
DPT (Dense Prediction Transformer)
Detection1 page
RF-DETR
Segmentation1 page
SegFormer

Papers · 1

2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
ViT

Co-authors · 11

BeyerDehghaniDosovitskiyGellyHeigoldHoulsbyKolesnikovMindererUszkoreitWeissenbornZhaiUnterthiner
Open in the people network
Lucas Beyer1 shared paper
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 2020
Mostafa Dehghani1 shared paper
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 2020
Alexey Dosovitskiy1 shared paper
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 2020
Sylvain Gelly1 shared paper
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 2020
Georg Heigold1 shared paper
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 2020
Neil Houlsby1 shared paper
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 2020
Alexander Kolesnikov1 shared paper
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 2020
Matthias Minderer1 shared paper
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 2020