Learning based super-resolution can recover high resolution image with high quality. However, building an interactive learning based super-resolution system for general images is e...
Communicating the subtleties of a craft technique, like putting a zipper into a garment or throwing a clay pot, can be challenging even when working side by side. Yet HowTo conten...
Cristen Torrey, Elizabeth F. Churchill, David W. M...
We propose a new method for automated large scale gathering of Web images relevant to specified concepts. Our main goal is to build a knowledge base associated with as many conce...
We present an active learning framework to simultaneously learn appearance and contextual models for scene understanding tasks (multi-class classification). Existing multi-class a...
We study in this paper the problem of bridging the semantic gap between low-level image features and high-level semantic concepts, which is the key hindrance in content-based imag...