928 search results - page 102 / 186 » Unsupervised Segmentation of Objects using Efficient Learnin... |
123
click to vote
ICIP
2002
IEEE
16 years 3 months ago
2002
IEEE
In this paper a fully automatic system for embedding visually recognizable watermark patterns to video objects is proposed. The architecture consists of 3 main modules. During the...
141
click to vote
PAMI
2011
14 years 8 months ago
2011
—In solving complex visual learning tasks, adopting multiple descriptors to more precisely characterize the data has been a feasible way for improving performance. The resulting ...
102
click to vote
CVPR
2010
IEEE
15 years 10 months ago
2010
IEEE
Current uses of tagged images typically exploit only the most explicit information: the link between the nouns named and the objects present somewhere in the image. We propose to ...
121
click to vote
PAMI
2010
15 years 9 days ago
2010
—Shortest paths have been used to segment object boundaries with both continuous and discrete image models. Although these techniques are well defined in 2D, the character of the...
124
click to vote
JMLR
2012
13 years 4 months ago
2012
Unsupervised discovery of latent representations, in addition to being useful for density modeling, visualisation and exploratory data analysis, is also increasingly important for...