We introduce an efficient method for synthesizing acceleration noise – sound produced when an object experiences abrupt rigidbody acceleration due to collisions or other contac...
467 views172 votes15 years 11 months ago ICPR 2010»
Shadow detection and removal is an important step employed after foreground detection, in order to improve the segmentation of objects for tracking. Methods reported in the litera...
Current work on automatic opinion mining has ignored opinion targets expressed by anaphorical pronouns, thereby missing a significant number of opinion targets. In this paper we e...
149 views168 votes16 years 8 months ago ICCV 2003»
One significant challenge in the construction of visual detection systems is the acquisition of sufficient labeled data. This paper describes a new technique for training visual d...
639 views154 votes16 years 1 months ago CVPR 2010»
The integral image is typically used for fast integrating a function over a rectangular region in an image. We propose a method that extends the integral image to do fast integrat...
: Networked systems that gather sensor data in order to react to phenomena in their surroundings are faced with a growing need for adaptive behavior to operate in dynamically chang...
795 views146 votes16 years 2 months ago CVPR 2010»
Learning models for recognizing objects with few or no training examples is important, due to the intrinsic longtailed distribution of objects in the real world. In this paper, we...
In this paper we describe a hybrid approach to improving semantic extraction from news video. Experiments show the value of careful parameter tuning, exploiting multiple feature s...
117 views139 votes15 years 11 months ago ICCS 2004»
Shadow Hybrid Monte Carlo (SHMC) is a new method for sampling the phase space of large biological molecules. It improves sampling by allowing larger time steps and system sizes in ...
90 views173 votes15 years 11 months ago PPSN 2004»
This paper introduces a new evaluation function, called δ, for the Bandwidth Minimization Problem for Graphs (BMPG). Compared with the classical β evaluation function used, our ...