Related papers: Potential Pitfalls in Visual Models of Tipping Poi…

Neural network based models are a very powerful tool for creating word embeddings, the objective of these models is to group similar words together. These embeddings have been used as features to improve results in various applications such…

Visual grounding is a ubiquitous building block in many vision-language tasks and yet remains challenging due to large variations in visual and linguistic features of grounding entities, strong context effect and the resulting semantic…

With the growing adoption of Text-to-Image (TTI) systems, the social biases of these models have come under increased scrutiny. Herein we conduct a systematic investigation of one such source of bias for diffusion models: embedding spaces.…

Cross-view spatial reasoning remains a weak spot for vision-language models (VLMs): they often reason in language and lose the fine-grained geometry needed for the task. Thinking with images aims to address this by generating an…

A large variety of complex systems in ecology, climate science, biomedicine and engineering have been observed to exhibit tipping points, where the internal dynamical state of the system abruptly changes. For example, such critical…

Visual prompt tuning offers significant advantages for adapting pre-trained visual foundation models to specific tasks. However, current research provides limited insight into the interpretability of this approach, which is essential for…

While deep learning has led to huge progress in complex image classification tasks like ImageNet, unexpected failure modes, e.g. via spurious features, call into question how reliably these classifiers work in the wild. Furthermore, for…

Visual Storytelling is a challenging multimodal task between Vision & Language, where the purpose is to generate a story for a stream of images. Its difficulty lies on the fact that the story should be both grounded to the image sequence…

The biases exhibited by Text-to-Image (TTI) models are often treated as if they are independent, but in reality, they may be deeply interrelated. Addressing bias along one dimension, such as ethnicity or age, can inadvertently influence…

Prior work on perceptual effectiveness has decomposed visualizations into smaller common units (e.g., channels such as angle, position, and length) to establish rankings. While useful, these decompositions lack the computational structure…

Model-free and data-driven prediction of tipping point transitions in nonlinear dynamical systems is a challenging and outstanding task in complex systems science. We propose a novel, fully data-driven machine learning algorithm based on…

Modeling and parameter estimation for neuronal dynamics are often challenging because many parameters can range over orders of magnitude and are difficult to measure experimentally. Moreover, selecting a suitable model complexity requires a…

Data visualizations are widely used to communicate messages about urgent topics such as climate change and public health. However, we still know little about how these visualizations are produced and interpreted in popular science contexts.…

Neuro-symbolic representations have proved effective in learning structure information in vision and language. In this paper, we propose a new model architecture for learning multi-modal neuro-symbolic representations for video captioning.…

This article is addressing a recurrent problem in biology: mining newly built large scale networks. Our approach consists in comparing these new networks to well known ones. The visual backbone of this comparative analysis is provided by a…

Decision-making is a central yet under-defined goal in visualization research. While existing task models address decision processes, they often neglect the conditions framing a decision. To better support decision-making tasks, we propose…

Analysts often make visual causal inferences about possible data-generating models. However, visual analytics (VA) software tends to leave these models implicit in the mind of the analyst, which casts doubt on the statistical validity of…

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…

Visual error metrics play a fundamental role in the quantification of perceived image similarity. Most recently, use cases for them in real-time applications have emerged, such as content-adaptive shading and shading reuse to increase…

Time series forecasting is essential for agents to make decisions. Traditional approaches rely on statistical methods to forecast given past numeric values. In practice, end-users often rely on visualizations such as charts and plots to…