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
...
Sudheendra Vijayanarasimhan (University of Texas a...
Most modern computer vision systems for high-level
tasks, such as image classification, object recognition and
segmentation, are based on learning algorithms that are
able to se...
We propose a novel framework for contour based object
detection and recognition, which we formulate as a joint
contour fragment grouping and labeling problem. For a
given set of...
ChengEn Lu, Longin Jan Latecki, Nagesh Adluru, Hai...
Shape indexing is a way of making rapid associations between features detected in an image and object models that could have produced them. When model databases are large, the use...
Model Abstraction from Examples Yakov Keselman, Member, IEEE, and Sven Dickinson, Member, IEEE The recognition community has typically avoided bridging the representational gap bet...