We investigate the properties of a metric between two distributions, the Earth Mover's Distance (EMD), for content-based image retrieval. The EMD is based on the minimal cost ...
It is a challenging and important task to retrieve images from a large and highly varied image data set based on their visual contents. Problems like how to fill the semantic gap b...
This paper introduces a web image dataset created by NUS’s Lab for Media Search. The dataset includes: (1) 269,648 images and the associated tags from Flickr, with a total of 5,...
Spatial relations play important role in computer vision, scene analysis, geographic information systems (GIS) and content based image retrieval. Analyzing spatial relations by Fo...
We address the problem of finding deformation between two images for the purpose of recognizing objects. The challenge is that discriminative features are often transformation-va...