Shadow detection is a fundamental and challenging task, since it requires an understanding of global image semantics and there are various backgrounds around shadows. This paper presents a novel network for shadow detection by analyzing image context in a direction-aware manner. To achieve this, we first formulate the direction-aware attention mechanism in a spatial recurrent neural network (RN...

We describe our approach of introducing context-awareness into everyday applications to make them more easy-to-use. The approach aims in shortening both the learning curve when introducing new technology to endusers and prototype development time, as well as results in more reliable prototypes. Moreover, we expect that the approach yields better quality user test results. To demonstrate the app...

This study describes integration of an articulatory factor into the exemplar-based Context Sequence Model of speech production, CSM [10], which builds on the concept of a speech perceptionproduction loop. It has been demonstrated that selection of new exemplars for speech production is based on about 0.5 s of preceding acoustic context and following linguistic match of the exemplars. This inves...

In this paper, we present a method for integrating possible prior knowledge (such as phonetic and lexical knowledge), as well as acoustic context (e.g., the whole utterance) in the phone posterior estimation, and we propose to use the obtained posteriors as complementary posterior features in Tandem ASR configuration. These posteriors are estimated based on HMM state posterior probability defin...

Trophic cascades triggered by fishing have profound implications for marine ecosystems and the socioeconomic systems that depend on them. With the number of reported cases quickly growing, key features and commonalities have emerged. Fishery-induced trophic cascades often display differential response times and nonlinear trajectories among trophic levels and can be accompanied by shifts in alte...

In 4 experiments, we investigated the effects of object affordance in reach-to-grasp actions. Participants indicated whether a depicted small or large object was natural or manmade by means of different object-grasping responses (i.e., with a power or a precision grip). We observed that the size of the depicted object affected the grasping kinematics (grip aperture) and the reach-onset times of...

This paper addresses two fundamental research problems in the domain of context aware autonomic systems: the development of a generic context model that can be used to represent general purpose contexts in a system interpretable way and the autonomic context model management. The proposed context model uses two equivalent and synchronized ways of representing the context: a set based representa...

We demonstrate the use of context features, namely, names of places, and unlabelled data for the detection of personal name language of origin. While some early work used either rule-based methods or n-gram statistical models to determine the name language of origin, we use the discriminative classification maximum entropy model and view the task as a classification task. We perform bootstrappi...

Applications using automatically indexed clinical conditions must account for contextual features such as whether a condition is negated, historical or hypothetical, or experienced by someone other than the patient. We developed and evaluated an algorithm called ConText, an extension of the NegEx negation algorithm, which relies on trigger terms, pseudo-trigger terms, and termination terms for ...

In this paper, we review five heuristic strategies for handling context-sensitive features in supervised machine learning from examples. We discuss two methods for recovering lost (implicit) contextual information. We mention some evidence that hybrid strategies can have a synergetic effect. We then show how the work of several machine learning researchers fits into this framework. While we do ...