Considering that quincunx lattice is a more efficient spatial sampling scheme than square lattice, we investigate a new approach of image coding for quincunx sample arrangement. T...
The most expressive way humans display emotions is through facial expressions. Humans detect and interpret faces and facial expressions in a scene with little or no effort. Still, ...
This paper addresses action spotting, the spatiotemporal detection and localization of human actions in video. A novel compact local descriptor of video dynamics in the context of...
Konstantinos Derpanis, Mikhail Sizintsev, Kevin Ca...
—Human movement models often divide movements into parts. In walking the stride can be segmented into four different parts, and in golf and other sports, the swing is divided int...
Eric Guenterberg, Hassan Ghasemzadeh, Roozbeh Jafa...
In this paper we propose a novel framework for 3D object categorization. The object is modeled it in terms of its sub-parts as an histogram of 3D visual word occurrences. We introd...
Roberto Toldo, Umberto Castellani, Andrea Fusiello