Natural images are typically a composition of cartoon and texture structures. One common task is to separate such an image into two single images, one containing the cartoon part and the other containing the texture part. Recently, a powerful class of algorithms using sparse approximation and l1 minimization has been introduced to resolve this problem, and numerous inspiring empirical results h...

The objective of this paper is to examine statistical approaches to the classification of textured materials from a single image obtained under unknown viewpoint and illumination. The approaches investigated here are based on the joint probability distribution of filter responses. We review previous work based on this formulation and make two observations. First, we show that there is a corresp...

Viewpoint selection has become a very active area of research during the last decade. Computation of good viewpoints is important in graph drawing, scene understanding, etc. A good viewpoint can give us rich information about a scene. In this study, we present a novel Kinematics Significance based Skeleton Map (KSSM) during iterative Laplacian contraction. Inspired by salient viewpoint selectio...

Action recognition is a popular and important research topic in computer vision. However, it is challenging when facing viewpoint variance. So far, most researches in action recognition remain rooted in view-dependent representations. Some view invariance approaches have been proposed, but most of them suffer from some weaknesses, such as lack of abundant information for recognition, dependency...

In this paper, we propose a new method for synthesizing player viewpoint images from multiple view videos in tennis. Our method is divided into two key techniques: virtual-view synthesis and player’s viewpoint estimation. In the former, we divide the object tennis scene into sub regions, which are background, tennis court ground, players, and ball. For each sub region, a virtual viewpoint image...

Experiencing a body part as one's own, i.e., body ownership, depends on the integration of multisensory bodily signals (including visual, tactile, and proprioceptive information) with the visual top-down signals from peripersonal space. Although it has been shown that the visuo-spatial viewpoint from where the body is seen is an important visual top-down factor for body ownership, different stu...

Object viewpoint classification aims at predicting an approximate 3D pose of objects in a scene and is receiving increasing attention. State-of-the-art approaches to viewpoint classification use generative models to capture relations between object parts. In this work we propose to use a mixture of holistic templates (e.g. HOG) and discriminative learning for joint viewpoint classification and ...

11 This paper presents the 4DPlates, an application designed to display high resolution data and reconstruct their positions in the geologic past. 4DPlates makes use of level of detail (LoD) grids with a 4-8 tree structure to store the data so only the require resolution for a particular viewpoint is used. This facility means that the user can interact with large data sets on the fly, achieving...

This position statement briefly outlines a perspective on the the idea of “socio-cognitive grids” from the viewpoint of research completed by the EU FET ALFEBIITE project.