We propose to model relative attributes1 that capture the relationships between images and objects in terms of human-nameable visual properties. For example, the models can captur...
We present a trainable sequential-inference technique for processes with large state and observation spaces and relational structure. Our method assumes "reliable observation...
We present an algorithmic framework for learning multiple related tasks. Our framework exploits a form of prior knowledge that relates the output spaces of these tasks. We present...
Currently, there is no standard instrument for evaluating learning effectiveness. While final examinations and end-of-semester course evaluation surveys can be used to do this, th...
This paper presents a new approach to improving relation extraction based on minimally supervised learning. By adding some limited closed-world knowledge for confidence estimation...
Feiyu Xu, Hans Uszkoreit, Sebastian Krause, Hong L...