We propose PASTE, the first differentially private aggregation algorithms for distributed time-series data that offer good practical utility without any trusted server. PASTE add...
We present a novel geometric model for robot mapping based on shape. Shape similarity measure and matching techniques originating from computer vision are specially redesigned for ...
In this paper, we propose two ways of improving image classification based on bag-of-words representation [25]. Two shortcomings of this representation are the loss of the spatial...
Abstract—Location privacy has been a serious concern for mobile users who use location-based services provided by the thirdparty provider via mobile networks. Recently, there hav...
Yu Wang 0003, Dingbang Xu, Xiao He, Chao Zhang, Fa...
We develop a framework for learning generic, expressive image priors that capture the statistics of natural scenes and can be used for a variety of machine vision tasks. The appro...