2 papers in the Atlas registry, 2020–2025. 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
Contribution to the Atlas
primary sourcecited as a reference
Representation learning7 pages
Depth1 page
Detection1 page
Segmentation1 page
Papers · 2
2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense FeaturesTschannen, Gritsenko et al. · arXiv preprint
No page yetnot yet cited2020An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleDosovitskiy, Beyer et al. · ICLR 2021 (arXiv 2020)
ViT
in 10 Atlas pages