: Because of the semantic gap between low-level feature and high-level semantic feature of images, the results of the traditional color-based image retrieval can't meet users&...
We consider object recognition as the process of attaching meaningful labels to specific regions of an image, and propose a model that learns spatial relationships between objects....
Grouse is a feature-based approach to steerable exploration of a graph and an associated hierarchy. Steerability allows exploration to begin immediately, rather than requiring a c...
Markov logic networks (MLNs) combine first-order logic and Markov networks, allowing us to handle the complexity and uncertainty of real-world problems in a single consistent fram...
We present a framework for learning features for visual discrimination. The learning system is exposed to a sequence of training images. Whenever it fails to recognize a visual co...