593 search results - page 71 / 119 » Unsupervised Learning of Invariant Features Using Video |
CVPR
2009
IEEE
14 years 23 days ago
2009
IEEE
We investigate the problem of automatically labelling faces of characters in TV or movie material with their names, using only weak supervision from automaticallyaligned subtitle ...
BMVC
2010
13 years 7 months ago
2010
This paper presents a learning-based method for combining the shape and appearance feature types for 3D human pose estimation from single-view images. Our method is based on clust...
CVPR
2012
IEEE
11 years 11 months ago
2012
IEEE
In this paper, we deal with the estimation of body and head poses (i.e orientations) in surveillance videos, and we make three main contributions. First, we address this issue as ...
MM
2010
ACM
13 years 9 months ago
2010
ACM
The major scientific problem for content-based video retrieval is the semantic gap. Generally speaking, there are two appropriate ways to bridge the semantic gap: the first one is...
CRV
2009
IEEE
14 years 3 months ago
2009
IEEE
In this paper we argue that gestures based on nonaccidental motion features can be reliably detected amongst unconstrained background motion. Specifically, we demonstrate that hu...