Given a pair of images represented using bag-of-visual words and a label corresponding to whether the images are “related”(must-link constraint) or “unrelated” (must not li...
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...
This paper overviews a new gesture recognition framework
based on learning local motion signatures (LMSs) introduced
by [1]. After the generation of these LMSs computed
on one i...
This paper addresses the problem of recognizing shadows from monochromatic natural images. Without chromatic information, shadow classification is very challenging because the in...
While data privacy is a human right, it is challenging to enforce it. For example, if multiple retailers execute a single order at Amazon Marketplace, each retailer can use diffe...