Visual Informatics最新文献

Eye tracking is growing in popularity for multiple application areas, yet analysing and exploring the large volume of complex data remains difficult for most users. We present a comprehensive eye tracking visual analytics system to enable the exploration and presentation of eye-tracking data across time and space in an efficient manner. The application allows the user to gain an overview of general patterns and perform deep visual analysis of local gaze exploration. The ability to link directly to the video of the underlying scene allows the visualisation insights to be verified on the fly. The system was motivated by the need to analyse eye-tracking data collected from an ‘in the wild’ study with energy network operators and has been further evaluated via interviews with 14 eye-tracking experts in multiple domains. Results suggest that, thanks to state-of-the-art visualisation techniques and by providing context with videos, our system could enable an improved analysis of eye-tracking data through interactive exploration, facilitating comparison between different participants or conditions, thus enhancing the presentation of complex data analysis to non-experts. This research paper provides four contributions: (1) analysis of a motivational use case demonstrating the need for rich visual-analytics workflow tools for eye-tracking data; (2) a highly dynamic system to visually explore and present complex eye-tracking data; (3) insights from our applied use case evaluation and interviews with experienced users demonstrating the potential for the system and visual analytics for the wider eye-tracking community.

Classification methods for binary (yes/no) tasks often produce a continuously valued score. Machine learning practitioners must perform model selection, calibration, discretization, performance assessment, tuning, and fairness assessment. Such tasks involve examining classifier results, typically using summary statistics and manual examination of details. In this paper, we provide an interactive visualization approach to support such continuously-valued classifier examination tasks. Our approach addresses the three phases of these tasks: calibration, operating point selection, and examination. We enhance standard views and introduce task-specific views so that they can be integrated into a multi-view coordination (MVC) system. We build on an existing comparison-based approach, extending it to continuous classifiers by treating the continuous values as trinary (positive, unsure, negative) even if the classifier will not ultimately use the 3-way classification. We provide use cases that demonstrate how our approach enables machine learning practitioners to accomplish key tasks.

The design of efficient representations is well established as a fruitful way to explore and analyze complex or large data. In these representations, data are encoded with various visual attributes depending on the needs of the representation itself. To make coherent design choices about visual attributes, the visual search field proposes guidelines based on the human brain’s perception of features. However, information visualization representations frequently need to depict more data than the amount these guidelines have been validated on. Since, the information visualization community has extended these guidelines to a wider parameter space.

This paper contributes to this theme by extending visual search theories to an information visualization context. We consider a visual search task where subjects are asked to find an unknown outlier in a grid of randomly laid out distractors. Stimuli are defined by color and shape features for the purpose of visually encoding categorical data. The experimental protocol is made of a parameters space reduction step (i.e., sub-sampling) based on a machine learning model, and a user evaluation to validate hypotheses and measure capacity limits. The results show that the major difficulty factor is the number of visual attributes that are used to encode the outlier. When redundantly encoded, the display heterogeneity has no effect on the task. When encoded with one attribute, the difficulty depends on that attribute heterogeneity until its capacity limit (7 for color, 5 for shape) is reached. Finally, when encoded with two attributes simultaneously, performances drop drastically even with minor heterogeneity.

We present a multiscale deformed implicit surface network (MDISN) to reconstruct 3D objects from single images by adapting the implicit surface of the target object from coarse to fine to the input image. The basic idea is to optimize the implicit surface according to the change of consecutive feature maps from the input image. And with multi-resolution feature maps, the implicit field is refined progressively, such that lower resolutions outline the main object components, and higher resolutions reveal fine-grained geometric details. To better explore the changes in feature maps, we devise a simple field deformation module that receives two consecutive feature maps to refine the implicit field with finer geometric details. Experimental results on both synthetic and real-world datasets demonstrate the superiority of the proposed method compared to state-of-the-art methods.

Finding a shortest path for a given pair of vertices in a graph drawing is one of the fundamental tasks for qualitative evaluation of graph drawings. In this paper, we present the first machine learning approach to predict human shortest path task performance, including accuracy, response time, and mental effort.

To predict the shortest path task performance, we utilize correlated quality metrics and the ground truth data from the shortest path experiments. Specifically, we introduce path faithfulness metrics and show strong correlations with the shortest path task performance. Moreover, to mitigate the problem of insufficient ground truth training data, we use the transfer learning method to pre-train our deep model, exploiting the correlated quality metrics.

Experimental results using the ground truth human shortest path experiment data show that our models can successfully predict the shortest path task performance. In particular, model MSP achieves an MSE (i.e., test mean square error) of 0.7243 (i.e., data range from −17.27 to 1.81) for prediction.

A typical problem in Visual Analytics (VA) is that users are highly trained experts in their application domains, but have mostly no experience in using VA systems. Thus, users often have difficulties interpreting and working with visual representations. To overcome these problems, user assistance can be incorporated into VA systems to guide experts through the analysis while closing their knowledge gaps. Different types of user assistance can be applied to extend the power of VA, enhance the user’s experience, and broaden the audience for VA. Although different approaches to visualization onboarding and guidance in VA already exist, there is a lack of research on how to design and integrate them in effective and efficient ways. Therefore, we aim at putting together the pieces of the mosaic to form a coherent whole. Based on the Knowledge-Assisted Visual Analytics model, we contribute a conceptual model of user assistance for VA by integrating the process of visualization onboarding and guidance as the two main approaches in this direction. As a result, we clarify and discuss the commonalities and differences between visualization onboarding and guidance, and discuss how they benefit from the integration of knowledge extraction and exploration. Finally, we discuss our descriptive model by applying it to VA tools integrating visualization onboarding and guidance, and showing how they should be utilized in different phases of the analysis in order to be effective and accepted by the user.

Implementing computational methods for preservation, inheritance, and promotion of Cultural Heritage (CH) has become a research trend across the world since the 1990s. In China, generations of scholars have dedicated themselves to studying the country’s rich CH resources; there are great potential and opportunities in the field of computational research on specific cultural artefacts or artforms. Based on previous works, this paper proposes a systematic framework for Chinese Cultural Heritage Computing that consists of three conceptual levels which are Chinese CH protection and development strategy, computing process, and computable cultural ecosystem. The computing process includes three modules: (1) data acquisition and processing, (2) digital modeling and database construction, and (3) data application and promotion. The modules demonstrate the computing approaches corresponding to different phases of Chinese CH protection and development, from digital preservation and inheritance to presentation and promotion. The computing results can become the basis for the generation of cultural genes and eventually the formation of computable cultural ecosystem Case studies on the Mogao caves in Dunhuang and the art of Guqin, recognized as world’s important tangible and intangible cultural heritage, are carried out to elaborate the computing process and methods within the framework. With continuous advances in data collection, processing, and display technologies, the framework can provide constructive reference for building up future research roadmaps in Chinese CH computing and related fields, for sustainable protection and development of Chinese CH in the digital age.

Chinese calligraphy, as a well-known performing art form, occupies an important role in the intangible cultural heritage of China. Previous studies focused on the psychophysiological benefits of Chinese calligraphy. Little attention has been paid to its aesthetic attributes and effectiveness on the cognitive process. To complement our understanding of Chinese calligraphy, this study investigated the aesthetic experience of Chinese cursive-style calligraphy using brain functional network analysis. Subjects stayed on the coach and rested for several minutes. Then, they were requested to appreciate artwork of cursive-style calligraphy. Results showed that (1) changes in functional connectivity between fronto-occipital, fronto-parietal, bilateral parietal, and central–occipital areas are prominent for calligraphy condition, (2) brain functional network showed an increased normalized cluster coefficient for calligraphy condition in alpha2 and gamma bands. These results demonstrate that the brain functional network undergoes a dynamic reconfiguration during the aesthetic experience of Chinese calligraphy. Providing evidence that the aesthetic experience of Chinese calligraphy has several similarities with western art while retaining its unique characters as an eastern traditional art form.

Acoustic quality detection is vital in the manufactured products quality control field since it represents the conditions of machines or products. Recent work employed machine learning models in manufactured audio data to detect anomalous patterns. A major challenge is how to select applicable audio features to meliorate model’s accuracy and precision. To relax this challenge, we extract and analyze three audio feature types including Time Domain Feature, Frequency Domain Feature, and Cepstrum Feature to help identify the potential linear and non-linear relationships. In addition, we design a visual analysis system, namely AFExplorer, to assist data scientists in extracting audio features and selecting potential feature combinations. AFExplorer integrates four main views to present detailed distribution and relevance of the audio features, which helps users observe the impact of features visually in the feature selection. We perform the case study with AFExplore according to the ToyADMOS and MIMII Dataset to demonstrate the usability and effectiveness of the proposed system.

Ancient books that record the history of different periods are precious for human civilization. But the protection of them is facing serious problems such as aging. It is significant to repair the damaged characters in ancient books and restore their original textures. The requirement of the restoration of the damaged character is keeping the stroke shape correct and the font style consistent. In order to solve these problems, this paper proposes a new restoration method based on generative adversarial networks. We use the shape restoration network to complete the stroke shape recovery and the font style recovery. The texture repair network is responsible for reconstructing texture details. In order to improve the accuracy of the generator in the shape restoration network, we use the adversarial feature loss (AFL), which can update the generator and discriminator synchronously to replace the traditional perceptual loss. Meanwhile, the font style loss is proposed to maintain the stylistic consistency for the whole character. Our model is evaluated on the datasets Yi and Qing, and shows that it outperforms current state-of-the-art techniques quantitatively and qualitatively. In particular, the Structural Similarity has increased by 8.0% and 6.7% respectively on the two datasets.