66 search results - page 5 / 14 » Unsupervised discovery of visual object class hierarchies |
CVPR
2009
IEEE
15 years 1 months ago
2009
IEEE
Autonomous systems which learn and utilize a limited
visual vocabulary have wide spread applications.
Enabling such systems to segment a set of cluttered scenes
into objects is ...
CVPR
2010
IEEE
14 years 3 months ago
2010
IEEE
How can knowing about some categories help us to discover new ones in unlabeled images? Unsupervised visual category discovery is useful to mine for recurring objects without huma...
ICCV
2007
IEEE
14 years 1 months ago
2007
IEEE
We consider clustering situations in which the pairwise affinity between data points depends on a latent ”context” variable. For example, when clustering features arising fro...
ICCV
2011
IEEE
12 years 7 months ago
2011
IEEE
In the real visual world, the number of categories a classifier needs to discriminate is on the order of hundreds or thousands. For example, the SUN dataset [24] contains 899 sce...
ACCV
2010
Springer
13 years 2 months ago
2010
Springer
Abstract. We propose a novel unsupervised transfer learning framework that utilises unlabelled auxiliary data to quantify and select the most relevant transferrable knowledge for r...