Most recent class-level object recognition systems work with visual words, i.e., vector quantized local descriptors. In this paper we examine the feasibility of a dataindependent ...
What type of algorithms and statistical techniques support learning from very large datasets over long stretches of time? We address this question through a memory bounded version...
The process ofvoting for a candidate involves selecting an individual who best matches a personal system of values and beliefs. Typically, voters must select a candidate whom they...
This paper proposes a method for key-frame selection of captured motion data. In many cases, it is desirable to obtain a compact representation of the human motion. Key-framing is...
Abstract. In this paper an object learning system for image understanding is proposed. The knowledge acquisition system is designed as a supervised learning task, which emphasises ...