Selective sampling, a form of active learning, reduces the cost of labeling training data by asking only for the labels of the most informative unlabeled examples. We introduce a ...
Information Extraction (IE) is the task of extracting knowledge from unstructured text. We present a novel unsupervised approach for information extraction based on graph mutual r...
We present an active learning framework to simultaneously learn appearance and contextual models for scene understanding tasks (multi-class classification). Existing multi-class a...
The primary goal of image steganography techniques has been to maximize embedding rate while minimizing the detectability of the resulting stego images against steganalysis techni...
This paper proposes a learnt data-driven approach for accurate, real-time tracking of facial features using only intensity information. Constraints such as a-priori shape models o...
Eng-Jon Ong, Yuxuan Lan, Barry Theobald, Richard H...