Semantic scene classification is a useful, yet challenging problem in image understanding. Most existing systems are based on low-level features, such as color or texture, and suc...
Matthew R. Boutell, Anustup Choudhury, Jiebo Luo, ...
Text-based search using video speech transcripts is a popular approach for granular video retrieval at the shot or story level. However, misalignment of speech and visual tracks, ...
This paper presents a robust and efficient skeleton-based graph matching method for object recognition and recovery applications. The novel feature is to unify both object recogni...
This paper proposes a music signal synthesis scheme that is based on sinusoid modeling and sliding-window ESPRIT. Despite widely used audio coding standards, effectively synthesiz...
Given a time horizon parameter h and an object set O, predictive collision detection finds all the object pairs < oi, oj, ti > which will collide in the future time interva...