1112 search results - page 103 / 223 » Novel image feature alphabets for object recognition |
MM
2006
ACM
15 years 3 months ago
2006
ACM
Labeling objects in images is an essential prerequisite for many visual learning and recognition applications that depend on training data, such as image retrieval, object detecti...
108
click to vote
CVPR
2011
IEEE
14 years 6 months ago
2011
IEEE
The most popular way to use probabilistic models in vision is first to extract some descriptors of small image patches or object parts using well-engineered features, and then to...
IROS
2006
IEEE
15 years 4 months ago
2006
IEEE
- Robot companions need to be able to constantly acquire knowledge about new objects for instance in order to detect them in the environment. This ability is necessary since it is ...
CVPR
2004
IEEE
15 years 12 months ago
2004
IEEE
Object classification in far-field video sequences is a challenging problem because of low resolution imagery and projective image distortion. Most existing far-field classificati...
ICCV
2005
IEEE
15 years 3 months ago
2005
IEEE
We address the problem of learning object class models and object segmentations from unannotated images. We introduce LOCUS (Learning Object Classes with Unsupervised Segmentation...