We investigate the potential of combined features of aerial images and high-resolution interferometric SAR (InSAR) data for building detection in urban areas. It is shown that completeness and correctness may be increased if we integrate both InSAR double-bounce lines and 3D lines of stereo data in addition to building hints of a single optical orthophoto. In order to exploit context informatio...

Our “pyramid filtering” insight enables exact and extremely efficient per-voxel classification with minimal memory overhead. We will now demonstrate our improvement over existing techniques empirically and theoretically. For an empirical demonstration of efficiency, consider the following two alternatives to pyramid filtering: 1) the “sliding window” approach: iterate through every voxel in the...

A perceptual phenomenon is reported, whereby prior acoustic context has a large, rapid and long-lasting effect on a basic auditory judgement. Pairs of tones were devised to include ambiguous transitions between frequency components, such that listeners were equally likely to report an upward or downward 'pitch' shift between tones. We show that presenting context tones before the ambiguous pair...

In this paper, we introduce contextinformed features in a log-linear phrase-based SMT framework; these features enable us to exploit source similarity in addition to target similarity modeled by the language model. We present a memory-based classification framework that enables the estimation of these features while avoiding sparseness problems. We evaluate the performance of our approach on It...

Named entity classification is the recognition and identification of linguistics elements that can be cataloged in several categories as names of organizations, persons, locations, time expressions, among others [1]. This classification represents an important subtask of more complex information extraction and linguistic applications, given that named entities represents the main content of a d...

This paper examines the influence of features based on clusters of co-occurrences for supervised Word Sense Disambiguation and Lexical Substitution. Cooccurrence cluster features are derived from clustering the local neighborhood of a target word in a co-occurrence graph based on a corpus in a completely unsupervised fashion. Clusters can be assigned in context and are used as features in a sup...

Local spatio-temporal features have been shown to be efficient and robust to represent simple actions. However, for complicated human activities with long-range motion or multiple interactive body parts and persons, the limitation of low-level features blows up because of their local properties and the lack of context. This paper addresses the problem by suggesting a framework for both computin...

Local spatio-temporal features have been shown to be effective and robust in order to represent simple actions. However, for high level human activities with long-range motion or multiple interactive body parts and persons, the limitation of low-level features blows up because of their localness. This paper addresses the problem by suggesting a framework that computes mid-level features and tak...

This Coastal and Hydraulic Engineering Technical Note (CHETN) summarizes the state of understanding of the influence of grain size on surf zone sediment transport and is a companion to Smith et al. (2004). This CHETN discusses details of bed-load and suspended load transport, and the classical bed-load regime is shown to encompass two distinct modes of transport. Four LST models with varying le...