68 search results - page 2 / 14 » Actively Selecting Annotations Among Objects and Attributes |
CVPR
2011
IEEE
13 years 1 months ago
2011
IEEE
Human-nameable visual attributes offer many advantages when used as mid-level features for object recognition, but existing techniques to gather relevant attributes can be ineffici...
FUIN
2010
12 years 11 months ago
2010
Machine learning methods are often used to classify objects described by hundreds of attributes; in many applications of this kind a great fraction of attributes may be totally irr...
CVPR
2009
IEEE
15 years 1 hour 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
...
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
Many applications of spoken-language systems can benefit from having access to annotations of prosodic events. Unfortunately, obtaining human annotations of these events, even se...
IJCV
2011
12 years 12 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...