Over the years, several spatio-temporal interest point detectors have been proposed. While some detectors can only extract a sparse set of scaleinvariant features, others allow for...
Kernel methods are effective approaches to the modeling of structured objects in learning algorithms. Their major drawback is the typically high computational complexity of kernel ...
Fabio Aiolli, Giovanni Da San Martino, Alessandro ...
This paper discusses the potential benefits of applicationspecific power management through remote task execution. Power management is crucial for mobile devices that have to re...
A number of protocols have been proposed to date to defend against wormhole attacks in wireless networks by adopting synchronized clocks, positioning devices, or directional antenn...
In order for recognition systems to scale to a larger number of object categories building visual class taxonomies is important to achieve running times logarithmic in the number o...