419 search results - page 48 / 84 » cvpr 2010 |
CVPR
2010
IEEE
15 years 9 months ago
2010
IEEE
Active learning methods aim to select the most informative unlabeled instances to label first, and can help to focus image or video annotations on the examples that will most impr...
111
Voted
CVPR
2010
IEEE
15 years 8 months ago
2010
IEEE
In this paper, we present a new framework for non-rigid structure from motion (NRSFM) that simultaneously addresses three significant challenges: severe occlusion, perspective ca...
101
Voted
CVPR
2010
IEEE
15 years 8 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...
103
Voted
CVPR
2010
IEEE
15 years 8 months ago
2010
IEEE
We present a practical approach for surface reconstruction of smooth mirror-like objects using sparse reflection correspondences (RCs). Assuming finite object motion with a fix...
107
click to vote
CVPR
2010
IEEE
15 years 8 months ago
2010
IEEE
When classifying high-dimensional sequence data, traditional methods (e.g., HMMs, CRFs) may require large amounts of training data to avoid overfitting. In such cases dimensional...