629 search results - page 61 / 126 » Learning and Forgetting with Local Information of New Object... |
CVPR
2008
IEEE
14 years 10 months ago
2008
IEEE
This paper proposes a new concept in hierarchical representations that exploits features of different granularity and specificity coming from all layers of the hierarchy. The conc...
CIKM
2010
Springer
13 years 6 months ago
2010
Springer
We consider the problem of learning to rank relevant and novel documents so as to directly maximize a performance metric called Expected Global Utility (EGU), which has several de...
ECCV
2010
Springer
2010
Springer
Backprojection Revisited: Scalable Multi-view Object Detection and Similarity Metrics for Detections
14 years 1 months ago
Hough transform based object detectors learn a mapping from the image domain to a Hough voting space. Within this space, object hypotheses are formed by local maxima. The votes con...
NIPS
2007
13 years 9 months ago
2007
We investigate a new, convex relaxation of an expectation-maximization (EM) variant that approximates a standard objective while eliminating local minima. First, a cautionary resu...
CVPR
2009
IEEE
15 years 3 months ago
2009
IEEE
Most modern computer vision systems for high-level
tasks, such as image classification, object recognition and
segmentation, are based on learning algorithms that are
able to se...