Exploratory Data Analysis (EDA) is an essential yet tedious process for examining a new dataset. To facilitate it, Natural Language Interfaces (NLIs) can help people intuitively explore the dataset via data-oriented questions. However, existing NLIs primarily focus on providing accurate answers to questions, with few offering explanations or presentations of the data analysis pipeline used to uncover the answer. Such presentations are crucial for EDA as they enhance the interpretability and reliability of the answer, while also helping users understand the analysis process and derive insights. To fill this gap, we introduce Urania, a natural language interactive system that can visualize the data analysis pipelines used to resolve input questions. It integrates a NLI that allows users to explore data via questions, and a novel data-aware question decomposition algorithm that resolves each input question into a data analysis pipeline. This pipeline is visualized in the form of a datamation, with animated presentations of analysis operations and their corresponding data changes. Through two quantitative experiments and expert interviews, we demonstrated that our data-aware question decomposition algorithm shows competitive performance compared to existing techniques in terms of execution accuracy, and that Urania can help people explore datasets better. In the end, we discuss the observations from the studies and the potential future works.

Design spaces serve as a conceptual framework that enables designers to explore feasible solutions, yet their lack of computational formalization limits integration with AI-driven design automation. To address this, we introduce a structured design space model that formalizes design spaces with orthogonal dimensions and discrete elements, making them machine-interpretable and executable. Building on this model, we present IDEA, a fully automated design exploration framework to generate effective outcomes based on user requirements and design spaces. Specifically, IDEA leverages large language models (LLMs) for constraint generation, incorporates a constraint-guided Monte Carlo Tree Search (MCTS) algorithm to explore the space, and instantiates abstract decisions into domain-specific implementations. We evaluate IDEA in two design scenarios: data-driven article and standard visualization, supported by comparativeratings, expert interviews, and quantitative experiments. Results demonstrate the IDEA's adaptability across domains and its capability to produce high-quality designs.

Knowledge distillation (KD) techniques have been employed to tackle the issue of incomplete multi-modality data, aiming to enhance the performance of the student model (i.e., using unimodal data) as close as possible to the teacher model (i.e., using multimodal data) through information transfer between the two models. However, directly using the traditional KD model will lead to the problem of mismatched model capacities. The teacher model typically receives a greater amount of information compared to the student model. If the learned information from the teacher model is directly transferred, it will impact the performance of the student model. To this end, this paper proposes a novel fuzzy knowledge distillation (fuzzy-KD) model for brain network analysis of incomplete multi-modality data. Specifically, we design a fuzzy-KD module to reduce the information gap between the teacher and student models through two operations: fuzzy processing and feature selection. The fuzzy processing applies an affiliation function to each channel of the feature maps learned by the teacher model to improve the generalization of representations. The feature selection employs channel compression to compel the student model to focus on crucial information within the teacher model. Experiments on real epilepsy datasets show that our method outperforms several state-of-the-art methods in the field of epilepsy recognition.

Science has long been viewed as a key driver of economic growth and rising standards of living. Knowledge about how scientific advances support marketplace inventions is therefore essential for understanding the role of science in propelling real-world applications and technological progress. The increasing availability of large-scale datasets tracing scientific publications and patented inventions and the complex interactions among them offers us new opportunities to explore the evolving dual frontiers of science and technology at an unprecedented level of scale and detail. However, we lack suitable visual analytics approaches to analyze such complex interactions effectively. Here we introduce InnovationInsights, an interactive visual analysis system for researchers, research institutions, and policymakers to explore the complex linkages between science and technology, and to identify critical innovations, inventors, and potential partners. The system first identifies important associations between scientific papers and patented inventions through a set of statistical measures introduced by our experts from the field of the Science of Science. A series of visualization views are then used to present these associations in the data context. In particular, we introduce the Interplay Graph to visualize patterns and insights derived from the data, helping users effectively navigate citation relationships between papers and patents. This visualization thereby helps them identify the origins of technical inventions and the impact of scientific research. We evaluate the system through two case studies with experts followed by expert interviews. We further engage a premier research institution to test-run the system, helping its institution leaders to extract new insights for innovation. Through both the case studies and the engagement project, we find that our system not only meets our original goals of design, allowing users to better identify the sources of technical inventions and to understand the broad impact of scientific research; it also goes beyond these purposes to enable an array of new applications for researchers and research institutions, ranging from identifying untapped innovation potential within an institution to forging new collaboration opportunities between science and industry.

As a vital research subject in the field of intelligent transportation systems (ITSs), traffic flow prediction using deep learning methods has attracted much attention in recent years. However, numerous existing studies mainly focus on short-term traffic flow predictions and fail to consider the influence of external factors. Effective long-term traffic flow prediction has become a challenging issue. As a solution to these challenges, this paper proposes a deep learning approach based on a spatiotemporal graph convolutional network for long-term traffic flow prediction with multiple factors. In the proposed method, our innovative idea is to introduce an attribute feature unit (AF-unit) to fuse external factors into a spatiotemporal graph convolutional network. The proposed method consists of (1) constructing a weighted adjacency matrix using Gaussian similarity functions; (2) assembling a feature matrix to store time-series traffic flow; (3) building an external attribute matrix composed of external factors, including temperature, visibility, and weather conditions; and (4) building a spatiotemporal graph convolutional network based on a deep learning architecture (i.e., T-GCN). The experimental results indicate that (1) the performance of our method considering spatiotemporal dependence has better prediction capability than baseline models; (2) the fusion of meteorological factors can reduce the inaccuracy of traffic prediction; and (3) our method has high accuracy and stability in long-term traffic flow prediction.

Abstract The rapid increase in the number of community‐based question‐and‐answer services is attracting many users. Questions are posted and answered by community members. These users, who can help other users answer questions, can be considered experts. To facilitate finding a suitable expert and alleviate information overload, in this paper, expert yellow pages (EYP) for community question answering (CQA) are constructed. Considering the various lengths of texts, the biterm topic model (BTM) is used to model questions and fields of expertise. Then, two‐dimensional EYP (2DEYP), which are composed of expertise field dimensions and question dimensions, are constructed. The intersections represent the cluster of experts. The proposed 2DEYP can be expanded both laterally and vertically for a more in‐depth understanding and a more precise location. As the closer neurons represent similar topics, a novel labelling method is proposed to identify topic words for navigation. The method uses the distance between neurons as the differentiation capability. To further distinguish experts, a ranking mechanism is proposed. The experts can be ranked by integrating their expertise and activity levels. The expertise level is novel and characterized by both breadth and depth aspects. The proposed approach is evaluated via a real dataset, and the experimental results show that the proposed algorithm is feasible and performs well.

A storyboard is a sequence of images to illustrate a story containing multiple sentences, which has been a key process to create different story products. In this paper, we tackle a new multimedia task of automatic storyboard creation to facilitate this process and inspire human artists. Inspired by the fact that our understanding of languages is based on our past experience, we propose a novel inspire-and-create framework with a story-to-image retriever that selects relevant cinematic images for inspiration and a storyboard creator that further refines and renders images to improve the relevancy and visual consistency. The proposed retriever dynamically employs contextual information in the story with hierarchical attentions and applies dense visual-semantic matching to accurately retrieve and ground images. The creator then employs three rendering steps to increase the flexibility of retrieved images, which include erasing irrelevant regions, unifying styles of images and substituting consistent characters. We carry out extensive experiments on both in-domain and out-of-domain visual story datasets. The proposed model achieves better quantitative performance than the state-of-the-art baselines for storyboard creation. Qualitative visualizations and user studies further verify that our approach can create high-quality storyboards even for stories in the wild.

We propose a triplet-based network for audio feature learning for version identification. Existing methods use hand-crafted features for a music as a whole while we learn features by a triplet-based neural network on segment-level, focusing on the most similar parts between music versions. We conduct extensive experiments and demonstrate our merits.

Image retargeting attempts to adapt images to different devices while preserving the salient contents. Most existing methods address retargeting of a single image. In this paper, we propose a novel image retargeting method for resizing a pair of stereo images. Naively retargeting each image independently will distort the geometric structure and will impair the perception of the 3-D structure of the scene. We introduce an extension to the 2-D image retargeting method that works on a pair of stereo images. We demonstrate the performance of our method on a number of challenging indoor and outdoor stereo images. Experimental results show that our method is able to provide visually comfortable resized images when the resizing ratio is relatively high.