The ability to construct CAD or other object models from edge and range data has a fundamental meaning in building a recognition and positioning system. While the problem of model...
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...
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...
Abstract--In this work, we study how continuous video monitoring and intelligent video processing can be used in eldercare to assist the independent living of elders and to improve...
Zhongna Zhou, Xi Chen, Yu-Chia Chung, Zhihai He, T...
Developing better systems for document image analysis requires understanding errors, their sources, and their effects. The interactions between various processing steps are comple...