IEEE VIS Publication Dataset

The one-to-one strategy of mapping each single data item into a graphical marker adopted in many visualization techniques has limited usefulness when the number of records and/or the dimensionality of the data set are very high. In this situation, the strong overlapping of graphical markers severely hampers the user's ability to identify patterns in the data from its visual representation. We tackle this problem here with a strategy that computes frequency or density information from the data set, and uses such information in parallel coordinates visualizations to filter out the information to be presented to the user, thus reducing visual clutter and allowing the analyst to observe relevant patterns in the data. The algorithms to construct such visualizations, and the interaction mechanisms supported, inspired by traditional image processing techniques such as grayscale manipulation and thresholding are also presented. We also illustrate how such algorithms can assist users to effectively identify clusters in very noisy large data sets

We present PaperLens, a visualization that reveals connections, trends, and activity throughout the InfoVis conference community for the last 8 years. It tightly couples views across papers, authors, and references. This paper describes how we analyzed the data, the strengths and weaknesses of PaperLens, and interesting patterns and relationships we have discovered using PaperLens.

This paper describes a comparative experiment with five well-known tree visualization systems, and Windows Explorer as a baseline system. Subjects performed tasks relating to the structure of a directory hierarchy, and to attributes of files and directories. Task completion times, correctness and user satisfaction were measured, and video recordings of subjects' interaction with the systems were made. Significant system and task type effects and an interaction between system and task type were found. Qualitative analyses of the video recordings were thereupon conducted to determine reasons for the observed differences, resulting in several findings and design recommendations as well as implications for future experiments with tree visualization systems

Traditional multidimensional visualization techniques, such as glyphs, parallel coordinates and scatterplot matrices, suffer from clutter at the display level and difficult user navigation among dimensions when visualizing high dimensional datasets. In this paper, we propose a new multidimensional visualization technique named a value and relation (VaR) display, together with a rich set of navigation and selection tools, for interactive exploration of datasets with up to hundreds of dimensions. By explicitly conveying the relationships among the dimensions of a high dimensional dataset, the VaR display helps users grasp the associations among dimensions. By using pixel-oriented techniques to present values of the data items in a condensed manner, the VaR display reveals data patterns in the dataset using as little screen space as possible. The navigation and selection tools enable users to interactively reduce clutter, navigate within the dimension space, and examine data value details within context effectively and efficiently. The VaR display scales well to datasets with large numbers of data items by employing sampling and texture mapping. A case study on a real dataset, as well as the VaR displays of multiple real datasets throughout the paper, reveals how our proposed approach helps users interactively explore high dimensional datasets with large numbers of data items

Intelligence analysts receive thousands of facts from a variety of sources. In addition to the bare details of the fact ÔÇö a particular person, for example ÔÇö each fact may have provenance, reliability, weight, and other attributes. Each fact may also be associated with other facts, e.g. that one person met another at a particular location. The analyst┬Æs task is to examine a huge collection of such loosely-structured facts, and try to "connect the dots" to perceive the underlying and unknown causes ÔÇö and their possible future courses. We have designed and implemented a Java platform called VIM to support intelligence analysts in their work.

Data repositories around the world hold many thousands of data sets. Finding information from these data sets is greatly facilitated by being able to quickly and efficiently browse remote data sets. In this note, we introduce the Iconic Remote Visual Data Exploration tool(IRVDX), which is a visual data mining tool used for exploring the features of remote and distributed data without the necessity of downloading the entire data set. IRVDX employs three kinds of visualizations: one provides a reduced representation of the data sets, which we call Dataset Icons. These icons show the important statistical characteristics of data sets and help to identify relevant data sets from distributed repositories. Another one is called the Remote Dataset Visual Browser that provides visualizations to browse remote data without downloading the complete data set to identify its content. The final one provides visualizations to show the degree of similarity between two data sets and to visually determine whether a join of two remote data sets will be meaningful.

This work focuses on visualizing highly cyclic hierarchical data. A user interface is discussed and its interaction is illustrated using a recipe database example. This example showcases a database with multiple categories for each recipe (database entry).

We introduce a semantically zoomable interface that displays emails as interactive objects rather than files containing lines of text, as in traditional e-mail interfaces. In this system, e-mails are displayed as node objects called e-mail nodes within a 2.5-dimensional world. The e-mail nodes are semantically zoomable and each may be rearranged to different locations within the plane to organize threads, topics, or projects. The prototype for this system was built using the Piccolo toolkit, the successor of Pad++ and Jazz [2, 3].

A standard method of visualizing high-dimensional data is reducing its dimensionality to two or three using some algorithm, and then creating a scatterplot with data represented by labelled and/or colored dots. Two problems with this approach are (1) dots do not represent data well, (2) reducing to just three dimensions does not make full use of several dimensionality-reduction algorithms. We demonstrate how Partiview can be used to solve these problems, in the context of handwriting recognition and image retrieval.

Our visualisation of the IEEE InfoVis citation network is based on 3D graph visualisation techniques. To make effective use of the third dimension we use a layered approach, constraining nodes to lie on parallel planes depending on parameters such as year of publication or link degree. Within the parallel planes nodes are arranged using a fast force-directed layout method. A number of clusters representing different research areas were identified using a self organising map approach.

Multimedia objects are often described by high-dimensional feature vectors which can be used for retrieval and clustering tasks. We have built an interactive retrieval system for 3D model databases that implements a variety of different feature transforms. Recently, we have enhanced the functionality of our system by integrating a SOM-based visualization module. In this poster demo, we show how 2D maps can be used to improve the effectiveness of retrieval, clustering, and over-viewing tasks in a 3D multimedia system.

Feature detection in flow fields is a well-researched area, but practical application is often difficult due to the numerical complexity of the algorithms preventing interactive use and due to noise in experimental or high-resolution simulation data sets. We present an integrated system that provides interactive denoising, vortex detection, and visualisation of vector data on Cartesian grids. All three major phases are implemented in such a way that the system runs completely on a modern GPU once the vector field is downloaded into graphics memory. The application aspect of our paper is twofold. First, we show how recently presented, prototypical GPU-based algorithms for filtering, numerical computation, and volume rendering can be combined into one productive system by handling all idiosyncrasies of a chosen graphics card. Second, we demonstrate that the significant speedup achieved compared to an optimized software implementation now allows interactive exploration of characteristic structures in turbulent flow fields.

We address the texture level-of-detail problem for extremely large surfaces such as terrain during realtime, view-dependent rendering. A novel texture hierarchy is introduced based on 4-8 refinements of raster tiles, in which the texture grids in effect rotate 45 degrees for each level of refinement. This hierarchy provides twice as many levels of detail as conventional quadtree-style refinement schemes such as mipmaps, and thus provides per-pixel view-dependent filtering that is twice as close to the ideal cutoff frequency for an average pixel. Because of this more gradual change in low-pass filtering, and due to the more precise emulation of the ideal cutoff frequency, we find in practice that the transitions between texture levels of detail are not perceptible. This allows rendering systems to avoid the complexity and performance costs of per-pixel blending between texture levels of detail. The 4-8 texturing scheme is integrated into a variant of the real-time optimally adapting meshes (ROAM) algorithm for view-dependent multiresolution mesh generation. Improvements to ROAM included here are: the diamond data structure as a streamlined replacement for the triangle bintree elements, the use of low-pass-filtered geometry patches in place of individual triangles, integration of 4-8 textures, and a simple out-of-core data access mechanism for texture and geometry tiles.

Many large scale physics-based simulations which take place on PC clusters or supercomputers produce huge amounts of data including vector fields. While these vector data such as electromagnetic fields, fluid flow fields, or particle paths can be represented by lines, the sheer number of the lines overwhelms the memory and computation capability of a high-end PC used for visualization. Further, very dense or intertwined lines, rendered with traditional visualization techniques, can produce unintelligible results with unclear depth relationships between the lines and no sense of global structure. Our approach is to apply a lighting model to the lines and sample them into an anisotropic voxel representation based on spherical harmonics as a preprocessing step. Then we evaluate and render these voxels for a given view using traditional volume rendering. For extremely large line based datasets, conversion to anisotropic voxels reduces the overall storage and rendering for O(n) lines to O(1) with a large constant that is still small enough to allow meaningful visualization of the entire dataset at nearly interactive rates on a single commodity PC.

The evolving technology of computer auto-fabrication ("3D printing") now makes it possible to produce physical models for complex biological molecules and assemblies. We report on an application that demonstrates the use of auto-fabricated tangible models and augmented reality for research and education in molecular biology, and for enhancing the scientific environment for collaboration and exploration. We have adapted an augmented reality system to allow virtual 3D representations (generated by the Python Molecular Viewer) to be overlaid onto a tangible molecular model. Users can easily change the overlaid information, switching between different representations of the molecule, displays of molecular properties such as electrostatics, or dynamic information. The physical model provides a powerful, intuitive interface for manipulating the computer models, streamlining the interface between human intent, the physical model, and the computational activity.

Recent activity within the UK National e-Science Programme has identified a need to establish an ontology for visualization. Motivation for this includes defining web and grid services for visualization (the ‘semantic grid’), supporting collaborative work, curation, and underpinning visualization research and education. At a preliminary meeting, members of the UK visualization community identified a skeleton for the ontology. We have started to build on this by identifying how existing work might be related and utilized. We believe that the greatest challenge is reaching a consensus within the visualization community itself. This poster is intended as one step in this process, setting out the perceived needs for the ontology, and sketching initial directions. It is hoped that this will lead to debate, feedback and involvement across the community.

A new method for the simplification and the visualization of vector fields is presented based on the notion of centroidal Voronoi tessellations (CVT's). A CVT is a special Voronoi tessellation for which the generators of the Voronoi regions in the tessellation are also the centers of mass (or means) with respect to a prescribed density. A distance function in both the spatial and vector spaces is introduced to measure the similarity of the spatially distributed vector fields. Based on such a distance, vector fields are naturally clustered and their simplified representations are obtained. Our method combines simple geometric intuitions with the rigorously established optimality properties of the CVTs. It is simple to describe, easy to understand and implement. Numerical examples are also provided to illustrate the effectiveness and competitiveness of the CVT-based vector simplification and visualization methodology.