There is an abundant literature on face detection due to its important role in many vision applications. Since Viola and Jones proposed the first real-time AdaBoost based face detector, Haar-like features have been adopted as the method of choice for frontal face detection. In this work, we show that simple features other than Haar-like features can also be applied for training an effective fac...

Slicing-Fitting-Linking (SFL) is a fast triangulation technique that guarantees building a closed mesh with consistent normals. The proposed technique can be used with diierent surface reconstruction cues such as laser scanner, stereo, SFS, and CT/MRI. The output of SFL can be in the form of STL les that are suitable for most rapid prototyping machines. The technique has three tasks. The rst ta...

We present a generic authorship verification scheme for the PAN-2015 identification task. Our scheme uses a two-step training phase on the training corpora. The first phase learns individual feature category parameters as well as decision thresholds based on equal error rates. The second phase builds feature category ensembles which are used for majority vote decisions because ensembles can out...

A semi-empirical model for surf zone wave height decay is adapted to the parabolic equation method in order to include the effect of depth-limited wave breaking in combined refraction/diffraction calculations. Several examples for plane beaches are presented in order to show correspondence between the empirical model, its numerical formulation, and previous laboratory data. The model is then ap...

An experiment tested whether people orient to and encode pictures selected from a Web site differently, depending on whether the pictures were selected by searching or surfing. Participants in the search condition spent more time selecting pictures than the participants in the surf condition spent. The pictures chosen in the search condition elicited cardiac orienting, while pictures chosen in ...

Presented here is an analysis of the effects of soil-foundation-structure interaction (SFSI) on seismic response of highway bridges. Of particular importance is the issue of input motions, their scaling and application to the SFS models. The analysis presented in this paper addresses the influence of inelastic behavior of both the soil and the structural components during seismic response evalu...

This paper presents methods for tracking moving objects in an outdoor environment. A robust tracking is achieved using feature fusion and multiple cameras. The proposed method integrates spatial position, shape and color information to track object blobs. The trajectories obtained from individual cameras are incorporated by an extended Kalman filter (EKF) to resolve object occlusion. Our result...

This paper presents a framework for soccer event detection through collaborative analysis of the textual, visual and aural modalities. The basic notion is to decompose a match video into smaller segments until ultimately the desired eventful segment is identified. Simple features are considered namely the minute-by-minute reports from sports websites (i.e., text), the semantic shot classes of f...

s of the 44th National Symposium of the American Vacuum Society, San Jose, CA, 20–24 Oct. 1997, p. 215. S.-J. Wang, I.-S. Jin, and H.-H. Park, Surf. Coat. Technol. 100–101, 59 ~1998!. M. Schaepkens, N. R. Rueger, J. J. Beulens, X. Li, T. E. F. M. Standaert, P. J. Matsuo, and G. S. Oehrlein, J. Vac. Sci. Technol. A 17, 3272 ~1999!. H.-H. Park, M.-H. Jo, H.-R. Kim, and S.-H. Hyon, J. Mater. Sci. ...

In this paper we describe a framework of analyzing programs belonging to different TV program genres using Hidden Markov Models and pseudo-semantic features derived from video shots. Clustering using Gaussian mixture models is used to determine the order of the models. Results for initial genre classification experiments using two simple features derived from video shots are given.