This paper addresses the problem of learning similaritypreserving binary codes for efficient retrieval in large-scale image collections. We propose a simple and efficient altern...
This paper presents a novel shape recovery technique that combines photometric stereo with polarization information. First, a set of ambiguous surface normals are estimated from po...
This paper proposes a new approach for hot event detection and summarization of news videos. The approach is mainly based on two graph algorithms: optimal matching (OM) and normali...
In this paper we describe new methods to detect semantic concepts from digital video based on audible and visual content. Temporal Gradient Correlogram captures temporal correlatio...
We present a general method for evaluating and visualizing evolutionary dynamics of self-replicators using a graph-based representation for genealogy. Through a transformation from...