State of the art methods for image and object re-
trieval exploit both appearance (via visual words) and
local geometry (spatial extent, relative pose). In large
scale problems,...
Michal Perdoch (Czech Technical University), Ondre...
Actions are spatio-temporal patterns which can be characterized
by collections of spatio-temporal invariant features.
Detection of actions is to find the re-occurrences
(e.g. th...
We propose a method based on sparse representation
(SR) to cluster data drawn from multiple low-dimensional
linear or affine subspaces embedded in a high-dimensional
space. Our ...
Similarity metrics that are learned from labeled training
data can be advantageous in terms of performance
and/or efficiency. These learned metrics can then be used
in conjuncti...
Fast retrieval methods are critical for large-scale and
data-driven vision applications. Recent work has explored
ways to embed high-dimensional features or complex distance
fun...