Mario Lučić

9

Papers

254

Total Citations

Papers (9)

On Scaling Up a Multilingual Vision and Language Model

Which Model To Transfer? Finding the Needle in the Growing Haystack

Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations

RUST: Latent Neural Scene Representations From Unposed Imagery

ViViT: A Video Vision Transformer

Video OWL-ViT: Temporally-consistent Open-world Localization in Video

End-to-End Spatio-Temporal Action Localisation with Video Transformers

A Large-Scale Study on Regularization and Normalization in GANs

High-Fidelity Image Generation With Fewer Labels