26 search results - page 1 / 6 » Learning Hybrid Models for Image Annotation with Partially L... |
NIPS
2008
13 years 5 months ago
2008
Extensive labeled data for image annotation systems, which learn to assign class labels to image regions, is difficult to obtain. We explore a hybrid model framework for utilizing...
CVPR
2009
IEEE
14 years 11 months ago
2009
IEEE
Active learning strategies can be useful when manual labeling
effort is scarce, as they select the most informative
examples to be annotated first. However, for visual category
...
IJCV
2011
12 years 11 months ago
2011
Abstract We present an active learning framework that predicts the tradeoff between the effort and information gain associated with a candidate image annotation, thereby ranking un...
SDM
2009
SIAM
14 years 1 months ago
2009
SIAM
Many real-world applications call for learning predictive relationships from multi-modal data. In particular, in multi-media and web applications, given a dataset of images and th...
CVPR
2009
IEEE
14 years 11 months ago
2009
IEEE
In this paper, we present a multi-label sparse coding
framework for feature extraction and classification within
the context of automatic image annotation. First, each image
is ...