The paper is devoted to the problem of estimating the number of people visible in a camera. It uses as features a portion of foreground pixels in each cell of a rectangular grid. ...
The selection of weak classifiers is critical to the success of boosting techniques. Poor weak classifiers do not perform better than random guess, thus cannot help decrease the t...
We present a novel surface reconstruction algorithm that can recover high-quality surfaces from noisy and defective data sets without any normal or orientation information. A set ...
Abstract. Feature selection refers to the problem of selecting those input features that are most predictive of a given outcome; a problem encountered in many areas such as machine...
The ability to determine what day-to-day activity (such as cooking pasta, taking a pill, or watching a video) a person is performing is of interest in many application domains. A ...
Mike Perkowitz, Matthai Philipose, Kenneth P. Fish...