Skip to main content

2 Result(s)

within Thomas Dagès Remove this filter

and

  1. No Access

    Chapter and Conference Paper

    A Model is Worth Tens of Thousands of Examples

    Traditional signal processing methods relying on mathematical data generation models have been cast aside in favour of deep neural networks, which require vast amounts of data. Since the theoretical sample com...

    Thomas Dagès, Laurent D. Cohen… in Scale Space and Variational Methods in Com… (2023)

  2. No Access

    Chapter and Conference Paper

    Seeing Things in Random-Dot Videos

    The human visual system correctly groups features and can even interpret random-dot videos induced by imaging natural dynamic scenes. Remarkably, this happens even if perception completely fails when the same ...

    Thomas Dagès, Michael Lindenbaum, Alfred M. Bruckstein in Pattern Recognition (2020)