134 search results - page 1 / 27 » Learning Predictable and Discriminative Attributes for Visua... |
ICCV
2011
IEEE
12 years 4 months ago
2011
IEEE
We present an active learning approach to choose image annotation requests among both object category labels and the objects’ attribute labels. The goal is to solicit those labe...
JMLR
2010
12 years 11 months ago
2010
We introduce a simple order-based greedy heuristic for learning discriminative structure within generative Bayesian network classifiers. We propose two methods for establishing an...
AAAI
2012
11 years 7 months ago
2012
We propose to model relative attributes1 that capture the relationships between images and objects in terms of human-nameable visual properties. For example, the models can captur...
CVPR
2009
IEEE
14 years 12 months ago
2009
IEEE
We propose to shift the goal of recognition from naming
to describing. Doing so allows us not only to name familiar
objects, but also: to report unusual aspects of a familiar
ob...
CVPR
2011
IEEE
13 years 27 days ago
2011
IEEE
Visual attributes expose human-defined semantics to object recognition models, but existing work largely restricts their influence to mid-level cues during classifier training....