As computer vision research considers more object categories and greater variation within object categories, it is clear that larger and more exhaustive datasets are necessary. How...
Brendan Collins, Jia Deng, Kai Li, Fei-Fei Li 0002
In this paper, a new selective sampling method for the active learning framework is presented. Initially, a small training set ? and a large unlabeled set ? are given. The goal is...
We present a new approach to large-scale graph mining based on so-called backbone refinement classes. The method efficiently mines tree-shaped subgraph descriptors under minimum f...
Human-nameable visual “attributes” can benefit various recognition tasks. However, existing techniques restrict these properties to categorical labels (for example, a person ...
The ability to normalize pose based on super-category landmarks can significantly improve models of individual categories when training data are limited. Previous methods have co...