We propose an approach to find and describe objects within broad domains. We introduce a new dataset that provides annotation for sharing models of appearance and correlation acr...
This paper describes the use of a convolutional neural network to perform address block location on machine-printed mail pieces. Locating the address block is a dicult object rec...
In this paper we propose an automatic updating system for urban vector maps that is able to detect changes between the old dataset (consisting of both vector and raster maps) and t...
S. Ceresola, Andrea Fusiello, Manuele Bicego, Albe...
We develop sub-Nyquist sampling systems for analog signals comprised of several, possibly overlapping, finite duration pulses with unknown shapes and time positions. Efficient sam...
—We present a discriminative part-based approach for human action recognition from video sequences using motion features. Our model is based on the recently proposed hidden condi...