Related papers: Cicero: A Declarative Grammar for Responsive Visua…
Draco introduced a constraint-based framework to model visualization design in an extensible and testable form. It provides a way to abstract design guidelines from theoretical and empirical studies and applies the knowledge in automated…
In the face of complex decisions, people often engage in a three-stage process that spans from (1) exploring and analyzing pertinent information (intelligence); (2) generating and exploring alternative options (design); and ultimately…
Text-to-image multimodal tasks, generating/retrieving an image from a given text description, are extremely challenging tasks since raw text descriptions cover quite limited information in order to fully describe visually realistic images.…
Attention-based neural encoder-decoder frameworks have been widely adopted for image captioning. Most methods force visual attention to be active for every generated word. However, the decoder likely requires little to no visual information…
Design study is an established approach of conducting problem-driven visualization research. The academic visualizationcommunity has produced a large body of work for reporting on design studies, informed by a handful of theoretical…
Designing adaptive documents that are visually appealing across various devices and for diverse viewers is a challenging task. This is due to the wide variety of devices and different viewer requirements and preferences. Alterations to a…
Vision-language models (VLMs) have shown promise in graph structure understanding, but remain limited by input-token constraints, facing scalability bottlenecks and lacking effective mechanisms to coordinate textual and visual modalities.…
We propose OmniCaptioner, a versatile visual captioning framework for generating fine-grained textual descriptions across a wide variety of visual domains. Unlike prior methods limited to specific image types (e.g., natural images or…
Given an image and a reference caption, the image caption editing task aims to correct the misalignment errors and generate a refined caption. However, all existing caption editing works are implicit models, ie, they directly produce the…
Automated visualization design navigates a tension between symbolic systems and generative models. Constraint solvers enforce structural and perceptual validity, but the rules they require are difficult to author and too rigid to capture…
With most modern visualization tools, authors need to transform their data into tidy formats to create visualizations they want. Because this requires experience with programming or separate data processing tools, data transformation…
Expressing design intent using natural language prompts requires designers to verbalize the ambiguous visual details concisely, which can be challenging or even impossible. To address this, we introduce Brickify, a visual-centric…
Understanding visually situated language requires interpreting complex layouts of textual and visual elements. Pre-processing tools, such as optical character recognition (OCR), can map document image inputs to textual tokens, then large…
Machine translation models have discrete vocabularies and commonly use subword segmentation techniques to achieve an 'open vocabulary.' This approach relies on consistent and correct underlying unicode sequences, and makes models…
Customized generation aims to incorporate a novel concept into a pre-trained text-to-image model, enabling new generations of the concept in novel contexts guided by textual prompts. However, customized generation suffers from an inherent…
Generating images from semantic visual knowledge is a challenging task, that can be useful to condition the synthesis process in complex, subtle, and unambiguous ways, compared to alternatives such as class labels or text descriptions.…
Contextualized Image Captioning (CIC) evolves traditional image captioning into a more complex domain, necessitating the ability for multimodal reasoning. It aims to generate image captions given specific contextual information. This paper…
Constraint Handling Rules (CHR) has matured into a general purpose language over the past two decades. Any general purpose language requires its own development tools. Visualization tools, in particular, facilitate many tasks for…
Picasso is a free open-source (Eclipse Public License) web application written in Python for rendering standard visualizations useful for analyzing convolutional neural networks. Picasso ships with occlusion maps and saliency maps, two…
Atomic physics experiments often require a complex sequence of precisely timed computer controlled events. A distributed GUI-based control system designed with such experiments in mind, The Cicero Word Generator, is described. The system…