Instead of clustering video shots into scenes using low level image features, in this paper, we propose a rule-based model to extract simple dialog or action scenes. Through analy...
This paper presents a general strategy for designing efficient visual operators. The approach is highly task oriented and what constitutes the relevant information is defined by...
Exploding amounts of multimedia data increasingly require automatic indexing and classification, e.g. training classifiers to produce high-level features, or semantic concepts, ch...
Wei Jiang, Eric Zavesky, Shih-Fu Chang, Alexander ...
In this paper, we present a set of texture features that are locally invariant to similarity or affinity. The proposed indexing scheme relies on the topographic map, a shape-based...
In the past, processor design trends were dominated by increasingly complex feature sets, higher clock speeds, growing thermal envelopes and increasing power dissipation. Recently...