Unsupervised discovery of latent representations, in addition to being useful for density modeling, visualisation and exploratory data analysis, is also increasingly important for...
Jasper Snoek, Ryan Prescott Adams, Hugo Larochelle
Abstract. Text detection in urban scenes is a hard task due to the high variability of text appearance: different text fonts, changes in the point of view, or partial occlusion are...
We present a new metaphor for learning anatomy - the 3d puzzle. With this metaphor students learn anatomic relations by assembling a geometric model themselves. For this purpose, a...
We present a two-layer hierarchical formulation to exploit different levels of contextual information in images for robust classification. Each layer is modeled as a conditional f...
Current uses of tagged images typically exploit only the most explicit information: the link between the nouns named and the objects present somewhere in the image. We propose to ...
Sung Ju Hwang, University of Texas, Kristen Grauma...