3 citations · 3 across the 2 of their papers we have counts for
4 papers
Domain Aligned CLIP for Few-shot Classification
Muhammad Waleed Gondal, Jochen Gast, Inigo Alonso Ruiz +4
Large vision-language representation learning models like CLIP have demonstrated impressive performance for zero-shot transfer to downstream tasks while largely benefiting from int…
Deep Video Deblurring: The Devil is in the Details
Jochen Gast, Stefan Roth
Video deblurring for hand-held cameras is a challenging task, since the underlying blur is caused by both camera shake and object motion. State-of-the-art deep networks exploit tem…
Lightweight Probabilistic Deep Networks
Jochen Gast, Stefan Roth
Even though probabilistic treatments of neural networks have a long history, they have not found widespread use in practice. Sampling approaches are often too slow already for simp…
Parametric Object Motion from Blur
Jochen Gast, Anita Sellent, Stefan Roth
Motion blur can adversely affect a number of vision tasks, hence it is generally considered a nuisance. We instead treat motion blur as a useful signal that allows to compute the m…