We consider the problem of estimating global motion in an image stream containing outlier motion, and propose a novel framework to address the stated problem. Rather than following the conventional approach of analyzing pairs of images, we propose an accumulative framework that utilizes all available information to compute the desired alignment of an incoming image. This approach simultaneously...

This article reviews the rationale for using accumulative one-step-ahead prediction error (APE) as a data-driven method for model selection. Theoretically, APE is closely related to Bayesian model selection and the method of minimum description length (MDL). The sole requirement for using APE is that the models under consideration are capable of generating a prediction for the next, unseen data...

Planning as satisfiability (SAT-Plan) is one of the best approaches to optimal planning, which has been shown effective on problems in many different domains. However, the potential of the SAT-Plan strategy has not been fully exploited. Following the SAT-Plan paradigm, in this paper we formulate a STRIPS planning problem as a maximum SAT (max-SAT) and develop a general two-phase algorithm for p...

Acquiring knowledge about library routines is necessary for a programmer to effectively use most programming languages. Support for this learning activity is rare while the learning effort required is huge. This paper proposes a conceptual framework of a new documentation system that supports programmers to incrementally learn the use of library routines. The system draws on active information ...

Video based person re-identification plays a central role in realistic security and video surveillance. In this paper we propose a novel Accumulative Motion Context (AMOC) network for addressing this important problem, which effectively exploits the long-range motion context for robustly identifying the same person under challenging conditions. Given a video sequence of the same or different pe...

The open source environment R isf the most widely used software to statistically explore biological data sets including sequence alignments. BAM is the de facto standard file format for sequence alignment. With rbamtools, we provide now a full spectrum of accessibility to BAM for R users such as reading, writing, extraction of subsets and plotting of alignment depth where the script syntax clos...

In this paper we introduce new, bacterial evolutionary algorithm (BEA) based methods for routing unicast and multicast demands in grooming capable multi-layer optical wavelength division multiplexing (WDM) networks. The methods introduced are compared with both well known heuristic methods, accumulative shortest path heuristic (ASP) and minimum path heuristic (MPH), and as well as with ILP. We ...