A new part segmentation approach is presented which works on real images. These images contain 3D objects with textures and shadows on a complex background. The proposed approach relies on the outline of the object to guide the grouping of lines using symmetry and colinearity principles. This grouping of lines leads to simple shapes which can be modeled by 3D primitives such as geons or general...

Inconsistency in a database, when viewed purely logically, seem undesirable. Indeed the traditional approach to dealing with inconsistency in data is to employ means to restore consistency immediately. However, it is important to study the larger environment containing such databases, and the circumstances surrounding the inconsistency. We argue that within the larger environment, an inconsiste...

The cornerstone for the success of Service-Oriented Computing lies in its promise to allow fast and easy composition of services to create added-value applications. Compositions need to be described in terms of their desired functional properties, but the non-functional properties are of paramount importance as well. Inspired by the Web service challenge we propose a new model for describing th...

Exemplar SVMs (E-SVMs, Malisiewicz et al., ICCV 2011), where an SVM is trained with only a single positive sample, have found applications in the areas of object detection and content-based image retrieval (CBIR), amongst others. In this paper we introduce a method of part based transfer regularization that boosts the performance of E-SVMs, with a negligible additional cost. This enhanced E-SVM...

The hit-or-miss transform (HMT) is a fundamental operation on binary images, widely used since 40 years. As it is not increasing, its extension to grey-level images is not straightforward, and very few authors have considered it. Moreover, despite its potential usefulness, very few applications of the grey-level HMT have been proposed until now. Part I of this paper, developed hereafter, is dev...

Content based image retrieval (CBIR), the problem of searching digital images in large databases according to their visual content, is a well established research area in computer vision. In this work we are particularly interested in retrieving subwindows of images which are similar to the given query image, i.e. the goal is detection rather than image level classification. The notion of simil...

Distributed word representations have recently been proven to be an invaluable resource for NLP. These representations are normally learned using neural networks and capture syntactic and semantic information about words. Information about word morphology and shape is normally ignored when learning word representations. However, for tasks like part-of-speech tagging, intra-word information is e...

In an effort to establish a better understanding of multichannel level alignment, a correlation and regression analysis has been performed of objective metrics and subjective data collected and subsequently reported in parts I-III & V. This study considers subjective data acquired with 9 test signals with different set-ups considering loudspeaker placement, directivity, reproduction bandwidth a...