Related papers: The Effect of Visual Design in Image Classificatio…

We consider the problem of visually explaining similarity models, i.e., explaining why a model predicts two images to be similar in addition to producing a scalar score. While much recent work in visual model interpretability has focused on…

Contrastive learning has revolutionized the field of computer vision, learning rich representations from unlabeled data, which generalize well to diverse vision tasks. Consequently, it has become increasingly important to explain these…

People's visual experiences of the world are easy to carve up and examine along natural language boundaries, e.g., by category labels, attribute labels, etc. However, it is more difficult to elicit detailed visuospatial information about…

Visual statistical inference is a way to determine significance of patterns found while exploring data. It is dependent on the evaluation of a lineup, of a data plot among a sample of null plots, by human observers. Each individual is…

Multi-modal word semantics aims to enhance embeddings with perceptual input, assuming that human meaning representation is grounded in sensory experience. Most research focuses on evaluation involving direct visual input, however, visual…

Humans have come to rely on machines for reducing excessive information to manageable representations. But this reliance can be abused -- strategic machines might craft representations that manipulate their users. How can a user make good…

Set visualization facilitates the exploration and analysis of set-type data. However, how sets should be visualized when the data is uncertain is still an open research challenge. To address the problem of depicting uncertainty in set…

Policy decisions relevant to the environment rely on tools like dashboards, risk models, and prediction models to provide information and data visualizations that enable decision-makers to make trade-offs. The conventional paradigm of data…

Data visualizations are increasingly seen as socially constructed, with several recent studies positing that perceptions and interpretations of visualization artifacts are shaped through complex sets of interactions between members of a…

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,…

Understanding how people perceive visualizations is crucial for designing effective visual data representations; however, many heuristic design guidelines are derived from specific tasks or visualization types, without considering the…

Uncertainty visualizations often emphasize point estimates to support magnitude estimates or decisions through visual comparison. However, when design choices emphasize means, users may overlook uncertainty information and misinterpret…

The communication of uncertainty estimates, predictions and insights based on spatio-temporal models is important for decision-making as it impacts the utilisation and interpretation of information. Bivariate mapping is commonly used for…

Nowadays, financial data analysis is becoming increasingly important in the business market. As companies collect more and more data from daily operations, they expect to extract useful knowledge from existing collected data to help make…

Although an object may appear in numerous contexts, we often describe it in a limited number of ways. Language allows us to abstract away visual variation to represent and communicate concepts. Building on this intuition, we propose an…

Designers often create visualizations to achieve specific high-level analytical or communication goals. These goals require people to naturally extract complex, contextualized, and interconnected patterns in data. While limited prior work…

Large-scale recommender systems often face severe latency and storage constraints at prediction time. These are particularly acute when the number of items that could be recommended is large, and calculating predictions for the full set is…

This article studies the benefits of using spatially randomized experimental designs which partition the experimental area into distinct, non-overlapping units with treatments assigned randomly. Such designs offer improved policy evaluation…

Data visualizations typically show retrospective views of an existing dataset with little or no focus on repeatability. However, consumers of these tools often use insights gleaned from retrospective visualizations as the basis for…

Modern recommender systems model people and items by discovering or `teasing apart' the underlying dimensions that encode the properties of items and users' preferences toward them. Critically, such dimensions are uncovered based on user…