Related papers: Beyond Heuristics: Learning Visualization Design

Current concerns over reforming engineering education have focused attention on helping students develop skills and an adaptive expertise. Phenomenological guidelines for instruction along these lines can be understood as arising out of an…

Synthetic images rendered by graphics engines are a promising source for training deep networks. However, it is challenging to ensure that they can help train a network to perform well on real images, because a graphics-based generation…

Recent advances in visual analytics have enabled us to learn from user interactions and uncover analytic goals. These innovations set the foundation for actively guiding users during data exploration. Providing such guidance will become…

With the growth of data sizes, visualizing them becomes more complex. Desktop displays are insufficient for presenting and collaborating on complex data visualizations. Large displays could provide the necessary space to demo or present…

Optimal viewpoint prediction is an essential task in many computer graphics applications. Unfortunately, common viewpoint qualities suffer from two major drawbacks: dependency on clean surface meshes, which are not always available, and the…

Building an AI agent that can design on its own has been a goal since the 1980s. Recently, deep learning has shown the ability to learn from large-scale data, enabling significant advances in data-driven design. However, learning over prior…

The exponential growth of data has outpaced human ability to process information, necessitating innovative approaches for effective human-data interaction. To transform raw data into meaningful insights, storytelling, and visualization have…

Deep neural networks have become the default choice for many applications like image and video recognition, segmentation and other image and video related tasks.However, a critical challenge with these models is the lack of…

In recent years, deep generative models have been shown to 'imagine' convincing high-dimensional observations such as images, audio, and even video, learning directly from raw data. In this work, we ask how to imagine goal-directed visual…

Graphical models can represent a multivariate distribution in a convenient and accessible form as a graph. Causal models can be viewed as a special class of graphical models that not only represent the distribution of the observed system…

Findings from graphical perception can guide visualization recommendation algorithms in identifying effective visualization designs. However, existing algorithms use knowledge from, at best, a few studies, limiting our understanding of how…

Reweighting a distribution to minimize a distance to a target distribution is a powerful and flexible strategy for estimating a wide range of causal effects, but can be challenging in practice because optimal weights typically depend on…

For deep learning practitioners, hyperparameter tuning for optimizing model performance can be a computationally expensive task. Though visualization can help practitioners relate hyperparameter settings to overall model performance,…

Materials design often relies on human-generated hypotheses, a process inherently limited by cognitive constraints such as knowledge gaps and limited ability to integrate and extract knowledge implications, particularly when…

Building models of the world from observation, i.e., induction, is one of the major challenges in machine learning. In order to be useful, models need to maintain accuracy when used in novel situations, i.e., generalize. In addition, they…

Learning Games (LGs) are promising pedagogical tools but their design still remains experimental. Inspired by design-pattern based methods, recommended in educational domains, we propose a methodology and a model to analyze the scenario of…

Graphs are fundamental data structures which concisely capture the relational structure in many important real-world domains, such as knowledge graphs, physical and social interactions, language, and chemistry. Here we introduce a powerful…

As online news increasingly include data journalism, there is a corresponding increase in the incorporation of visualization in article thumbnail images. However, little research exists on the design rationale for visualization thumbnails,…

Learning to see through data is central to contemporary forms of algorithmic knowledge production. While often represented as a mechanical application of rules, making algorithms work with data requires a great deal of situated work. This…

Graphic design often involves exploring different stylistic directions, which can be time-consuming for non-experts. We address this problem of stylistically improving designs based on natural language instructions. While VLMs have shown…