We derive a probabilistic framework for robust, realtime, visual tracking of multiple previously unseen objects from a moving camera. This framework models the discrete depth orde...
The treemap is one of the most popular methods for visualizing hierarchical data. When a treemap contains a large number of items, inspecting or comparing a few selected items in a...
Many automated learning procedures lack interpretability, operating effectively as a black box: providing a prediction tool but no explanation of the underlying dynamics that driv...
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...
This study develops a procedure for automatic extraction and segmentation of a class-specific object (or region) by learning class-specific boundaries. We present and evaluate t...