Abstract Genomics data is essential in biological and medical domains, and bioinformatics analysts often manually create circos plots to analyze the data and extract valuable insights. However, creating circos plots is complex, as it requires careful design for multiple track attributes and positional relationships between them. Typically, analysts often seek inspiration from existing circos plots, and they have to iteratively adjust and refine the plot to achieve a satisfactory final design, making the process both tedious and time‐intensive. To address these challenges, we propose IntelliCircos, an AI‐powered interactive authoring tool that streamlines the process from initial visual design to the final implementation of circos plots. Specifically, we build a new dataset containing 4396 circos plots with corresponding annotations and configurations, which are extracted and labeled from published papers. With the dataset, we further identify track combination patterns, and utilize Large Language Model (LLM) to provide domain‐specific design recommendations and configuration references to navigate the design of circos plots. We conduct a user study with 8 bioinformatics analysts to evaluate IntelliCircos, and the results demonstrate its usability and effectiveness in authoring circos plots.

Weather forecast ensembles are commonly used to assess the uncertainty and confidence of weather predictions. Conventional methods in meteorology often employ ensemble mean and standard deviation plots, as well as spaghetti plots, to visualize ensemble data. However, these methods suffer from significant information loss and visual clutter. In this paper, we propose a new approach for uncertainty visualization of weather forecast ensembles, including isovalue selection based on information loss and hierarchical visualization that integrates visual abstraction and detail preservation. Our approach uses non-uniform downsampling to select key-isovalues and provides an interactive visualization method based on hierarchical clustering. Firstly, we sample key-isovalues by contour probability similarity and determine the optimal sampling number using an information loss curve. Then, the corresponding isocontours are presented to guide users in selecting key-isovalues. Once the isovalue is chosen, we perform agglomerative hierarchical clustering on the isocontours based on signed distance fields and generate visual abstractions for each isocontour cluster to avoid visual clutter. We link a bubble tree to the visual abstractions to explore the details of isocontour clusters at different levels. We demonstrate the utility of our approach through two case studies with meteorological experts on real-world data. We further validate its effectiveness by quantitatively assessing information loss and visual clutter. Additionally, we confirm its usability through expert evaluation.

Computational notebooks are widely utilized for exploration and analysis. However, creating slides to communicate analysis results from these notebooks is quite tedious and time-consuming. Researchers have proposed automatic systems for generating slides from notebooks, which, however, often do not consider the process of users conceiving and organizing their messages from massive code cells. Those systems ask users to go directly into the slide creation process, which causes potentially ill-structured slides and burdens in further refinement. Inspired by the common and widely recommended slide creation practice: drafting outlines first and then adding concrete content, we introduce OutlineSpark, an AI-powered slide creation tool that generates slides from a slide outline written by the user. The tool automatically retrieves relevant notebook cells based on the outlines and converts them into slide content. We evaluated OutlineSpark with 12 users. Both the quantitative and qualitative feedback from the participants verify its effectiveness and usability.

Constructing supervised machine learning models for real-world video analysis require substantial labeled data, which is costly to acquire due to scarce domain expertise and laborious manual inspection. While data programming shows promise in generating labeled data at scale with user-defined labeling functions, the high dimensional and complex temporal information in videos poses additional challenges for effectively composing and evaluating labeling functions. In this paper, we propose VideoPro, a visual analytics approach to support flexible and scalable video data programming for model steering with reduced human effort. We first extract human-understandable events from videos using computer vision techniques and treat them as atomic components of labeling functions. We further propose a two-stage template mining algorithm that characterizes the sequential patterns of these events to serve as labeling function templates for efficient data labeling. The visual interface of VideoPro facilitates multifaceted exploration, examination, and application of the labeling templates, allowing for effective programming of video data at scale. Moreover, users can monitor the impact of programming on model performance and make informed adjustments during the iterative programming process. We demonstrate the efficiency and effectiveness of our approach with two case studies and expert interviews.

Data scientists often have to use other presentation tools (e.g., Microsoft PowerPoint) to create slides to communicate their analysis obtained using computational notebooks. Much tedious and repetitive work is needed to transfer the routines of notebooks (e.g., code, plots) to the presentable contents on slides (e.g., bullet points, figures). We propose a human-AI collaborative approach and operationalize it within Slide4N, an interactive AI assistant for data scientists to create slides from computational notebooks. Slide4N leverages advanced natural language processing techniques to distill key information from user-selected notebook cells and then renders them in appropriate slide layouts. The tool also provides intuitive interactions that allow further refinement and customization of the generated slides. We evaluated Slide4N with a two-part user study, where participants appreciated this human-AI collaborative approach compared to fully-manual or fully-automatic methods. The results also indicate the usefulness and effectiveness of Slide4N in slide creation tasks from notebooks.

In this paper, we are interested in exploring the problem of full-resolution image segmentation, with the focus placed on learning full-resolution representations for biomedicine images. We divide the original resolution image into patches of different sizes in different stages and then extracte local features from large to small patches using efficient and flexible components in modern convolutional neural networks (CNN). Meanwhile, a multilayer perceptron (MLP) block intended for modeling long-range dependencies between patches is designed to compensate for the inherent inductive bias caused by convolution operations. In addition, we perform multi-scale fusion and receive representation information from parallel paths at each stage, resulting in a rich full-resolution representation. We evaluate the proposed method on different biomedical image segmentation tasks and it achieves a competitive performance compared to the latest deep learning segmentation methods. It is hoped that this method will serve as a useful alternative to biomedical image segmentation and provide an improved idea for the research based on full-resolution representation.