We show quite good face clustering is possible for a dataset of inaccurately and ambiguously labelled face images. Our dataset is 44,773 face images, obtained by applying a face f...
Tamara L. Berg, Alexander C. Berg, Jaety Edwards, ...
To learn a new visual category from few examples, prior knowledge from unlabeled data as well as previous related categories may be useful. We develop a new method for transfer le...
Many real-world applications call for learning predictive relationships from multi-modal data. In particular, in multi-media and web applications, given a dataset of images and th...
— We present a topological navigation system that is able to visually recognize the different rooms of an apartment and guide a robot between them. Specifically tailored for sma...