In traditional text clustering methods, documents are represented as "bags of words" without considering the semantic information of each document. For instance, if two ...
Xiaohua Hu, Xiaodan Zhang, Caimei Lu, E. K. Park, ...
In the quest for an elegant formulation of the notion of "polycategory" we develop a more symmetric counterpart to Burroni's notion of "T-category", where ...
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 paper addresses real-time automatic visual tracking,
labeling and classification of a variable number of
objects such as pedestrians or/and vehicles, under timevarying
illu...
Current methods for learning visual categories work well when a large amount of labeled data is available, but can run into severe difficulties when the number of labeled examples...