Optical communication is an integral part of the modern economy, having all but replaced electronic systems. Future growth in bandwidth appears to be on horizon using structured light, encoding information into spatial modes and transmitting them down fibre free-space, latter crucial for addressing last mile digitally disconnected communities. Unfortunately, patterns light are easily distorted,...

We present a standoff annotation framework for the integration of NLP components, currently implemented in the context of the DELPH-IN tools1. This provides a flexible standoff pointer scheme suitable for various types of data, a lattice encodes structural ambiguity, intraannotation relationships are encoded, and annotations are decorated with structured content. We provide an XML serialization...

Photocatalysis appears as an interesting approach for different applications, with the possibility of using sunlight a sustainable and renewable source energy [...]

We propose a category-independent method to produce a bag of regions and rank them, such that top-ranked regions are likely to be good segmentations of different objects. Our key objectives are completeness and diversity: every object should have at least one good proposed region, and a diverse set should be top-ranked. Our approach is to generate a set of segmentations by performing graph cuts...

Railway tunnel 3D clearance inspection is critical to guaranteeing railway operation safety. However, it is a challenge to inspect railway tunnel 3D clearance using a vision system, because both the spatial range and field of view (FOV) of such measurements are quite large. This paper summarizes our work on dynamic railway tunnel 3D clearance inspection based on a multi-camera and structured-li...

Training structured prediction models is time-consuming. However, most existing approaches only use a single machine, thus, the advantage of computing power and the capacity for larger data sets of multiple machines have not been exploited. In this work, we propose an efficient algorithm for distributedly training structured support vector machines based on a distributed block-coordinate descen...

Structured rational matrices such as symmetric, skew-symmetric, Hamiltonian, skew-Hamiltonian, Hermitian, and para-Hermitian arise in many applications. Linearizations of rational...