This work proposes to learn visual encodings of attention patterns that enables sequential attention for object detection in real world environments. The system embeds a saccadic d...
Abstract. We present a possibly great improvement while performing semisupervised learning tasks from training data sets when only a small fraction of the data pairs is labeled. In...
Abstract. We present a purely vision-based scheme for learning a topological representation of an open environment. The system represents selected places by local views of the surr...
Epistemic games are designed to help players develop domain-specific expertise that characterizes how professionals in a particular domain reason, communicate, and act [1, 11]. To ...
Rare category detection is an open challenge for active learning, especially in the de-novo case (no labeled examples), but of significant practical importance for data mining - ...