[hal-02160704] Volumes of Blurred-Invariant Gaussians for Dynamic Texture Classification
An effective model, which jointly captures shape and motion cues, for dynamic texture (DT) description is introduced by taking into account advantages of volumes of blurred-invariant features in three main following stages. First, a 3-dimensional Gaussian kernel is used to form smoothed sequences that allow to deal with well-known limitations of local encoding such as near uniform regions and sensitivity to noise. [...]
Image of the month
Framework of the INFERNO architecture for audio primitive retrieving.
NEURO Team (see the paper).
News from the lab