Related papers: Characterizing Visualization Perception with Psych…

Visual reasoning, as a prominent research area, plays a crucial role in AI by facilitating concept formation and interaction with the world. However, current works are usually carried out separately on small datasets thus lacking…

Understanding your audience is foundational to creating high impact visualization designs. However, individual differences and cognitive abilities also influence interactions with information visualization. Differing user needs and…

In computer vision, a prevailing method for quantifying dataset bias is to train a model to distinguish between datasets. High classification accuracy is then interpreted as evidence of meaningful semantic differences. This approach assumes…

A precise understanding of why units in an artificial network respond to certain stimuli would constitute a big step towards explainable artificial intelligence. One widely used approach towards this goal is to visualize unit responses via…

Understanding how humans and AI systems interpret ambiguous visual stimuli offers critical insight into the nature of perception, reasoning, and decision-making. This paper examines image labeling performance across human participants and…

We address the problem of learning a single model for person re-identification, attribute classification, body part segmentation, and pose estimation. With predictions for these tasks we gain a more holistic understanding of persons, which…

Handling visual complexity is a challenging problem in visualization owing to the subjectiveness of its definition and the difficulty in devising generalizable quantitative metrics. In this paper we address this challenge by measuring the…

The ability of humans to quickly identify general concepts from a handful of images has proven difficult to emulate with robots. Recently, a computer architecture was developed that allows robots to mimic some aspects of this human ability…

The geometric shapes of the outside world objects hide an undisclosed emotional, psychological, artistic, aesthetic and shape-generating potential; they may attract or cause fear as well as a variety of other emotions. This suggests that…

Inspired by cartographic generalization principles, we present a generalization technique for rendering line charts at different sizes, preserving the important semantics of the data at that display size. The algorithm automatically…

The recent trend in action recognition is towards larger datasets, an increasing number of action classes and larger visual vocabularies. State-of-the-art human action classification in challenging video data is currently based on a…

This paper presents a new self-supervised system for learning to detect novel and previously unseen categories of objects in images. The proposed system receives as input several unlabeled videos of scenes containing various objects. The…

In multi-class classification tasks, like human activity recognition, it is often assumed that classes are separable. In real applications, this assumption becomes strong and generates inconsistencies. Besides, the most commonly used…

Learning abstractions directly from data is a core challenge in robotics. Humans naturally operate at an abstract level, reasoning over high-level subgoals while delegating execution to low-level motor skills -- an ability that enables…

When searching for an object in a scene, how does the brain decide where to look next? Theories of visual search suggest the existence of a global attentional map, computed by integrating bottom-up visual information with top-down,…

We propose a visual analytics system to help a user analyze and steer zero-shot learning models. Zero-shot learning has emerged as a viable scenario for categorizing data that consists of no labeled examples, and thus a promising approach…

Obtaining large annotated datasets is critical for training successful machine learning models and it is often a bottleneck in practice. Weak supervision offers a promising alternative for producing labeled datasets without ground truth…

In deep learning, visualization techniques extract the salient patterns exploited by deep networks for image classification, focusing on single images; no effort has been spent in investigating whether these patterns are systematically…

Scatterplots are among the most widely used visualization techniques. Compelling scatterplot visualizations improve understanding of data by leveraging visual perception to boost awareness when performing specific visual analytic tasks.…

Real world learning scenarios involve a nonstationary distribution of classes with sequential dependencies among the samples, in contrast to the standard machine learning formulation of drawing samples independently from a fixed, typically…