Perceptual metric-guided human image generation

Pose transfer, which synthesizes a new image of a target person in a novel pose, is valuable in several applications. Generative adversarial networks (GAN) based pose transfer is a new way for person re-identification (re-ID). Typical perceptual metrics, like Detection Score (DS) and Inception Score (IS), were employed to assess the visual quality after generation in pose transfer task. Thus, the existing GAN-based methods do not directly benefit from these metrics which are highly associated with human ratings. In this paper, a perceptual metrics guided GAN (PIGGAN) framework is proposed to intrinsically optimize generation processing for pose transfer task. Specifically, a novel and general model-Evaluator that matches well the GAN is designed. Accordingly, a new Sort Loss (SL) is constructed to optimize the perceptual quality. Morevover, PIGGAN is highly flexible and extensible and can incorporate both differentiable and indifferentiable indexes to optimize the attitude migration process. Extensive experiments show that PIGGAN can generate photo-realistic results and quantitatively outperforms state-of-the-art (SOTA) methods.

Tool- and Domain-Agnostic Parameterization of Style Transfer Effects Leveraging Pretrained Perceptual Metrics

Current deep learning techniques for style transfer would not be optimal for design support since their "one-shot" transfer does not fit exploratory design processes. To overcome this gap, we propose parametric transcription, which transcribes an end-to-end style transfer effect into parameter values of specific transformations available in an existing content editing tool. With this approach, users can imitate the style of a reference sample in the tool that they are familiar with and thus can easily continue further exploration by manipulating the parameters. To enable this, we introduce a framework that utilizes an existing pretrained model for style transfer to calculate a perceptual style distance to the reference sample and uses black-box optimization to find the parameters that minimize this distance. Our experiments with various third-party tools, such as Instagram and Blender, show that our framework can effectively leverage deep learning techniques for computational design support.

Board Information Technology Governance and Business Agility

The goal of this paper is to empirically investigate and analyze the board's involvement in the information technology governance (ITG) function and how the ITG degree has implications for enterprise agility and financial performance. The analysis primarily relies on perceptual metrics. That is board members' views on the importance and impact of the decisions considered and made on the business outcome. The contribution is reflected in the relation of several of the most significant enterprise resources in complex conditions. The approach seeks to determine whether enterprise agility and business performance are the result of a higher degree of ITG or are critical elements of contingency. The test results show that enterprise agility has a significant indirect impact between ITG attainment and performance and that predefined IT role factors drive this relationship. The limitation of the research is that the capital market is not sufficiently developed in Bosnia and Herzegovina, and the responsibilities of the IT supervisory and audit bodies are not fully formulated.

Color Nameability Predicts Inference Accuracy in Spatial Visualizations

Color encoding is foundational to visualizing quantitative data. Guidelines for colormap design have traditionally emphasized perceptual principles, such as order and uniformity. However, colors also evoke cognitive and linguistic associations whose role in data interpretation remains underexplored. We study how two linguistic factors, name salience and name variation, affect people's ability to draw inferences from spatial visualizations. In two experiments, we found that participants are better at interpreting visualizations when viewing colors with more salient names (e.g., prototypical 'blue', 'yellow', and 'red' over 'teal', 'beige', and 'maroon'). The effect was robust across four visualization types, but was more pronounced in continuous (e.g., smooth geographical maps) than in similar discrete representations (e.g., choropleths). Participants' accuracy also improved as the number of nameable colors increased, although the latter had a less robust effect. Our findings suggest that color nameability is an important design consideration for quantitative colormaps, and may even outweigh traditional perceptual metrics. In particular, we found that the linguistic associations of color are a better predictor of performance than the perceptual properties of those colors. We discuss the implications and outline research opportunities. The data and materials for this study are available at https://osf.io/asb7n

Batch Decorrelation for Active Metric Learning

We present an active learning strategy for training parametric models of distance metrics, given triplet-based similarity assessments: object $x_i$ is more similar to object $x_j$ than to $x_k$. In contrast to prior work on class-based learning, where the fundamental goal is classification and any implicit or explicit metric is binary, we focus on perceptual metrics that express the degree of (dis)similarity between objects. We find that standard active learning approaches degrade when annotations are requested for batches of triplets at a time: our studies suggest that correlation among triplets is responsible. In this work, we propose a novel method to decorrelate batches of triplets, that jointly balances informativeness and diversity while decoupling the choice of heuristic for each criterion. Experiments indicate our method is general, adaptable, and outperforms the state-of-the-art.

Quality Evaluation of 3D Objects in Mixed Reality For Different Lighting Conditions

This paper presents a study on Quality of Experience (QoE) evaluation of 3D objects in Mixed Reality (MR) scenarios. In particular, a subjective test was performed with Microsoft HoloLens, considering different degradations affecting the geometry and texture of the content. Apart from the analysis of the perceptual effects of these artifacts, given the need for recommendations for subjective assessment of immersive media, this study was also aimed at: 1) checking the appropriateness of a single stimulus methodology (ACR-HR) for these scenarios where observers have less references than with traditional media, and 2) analyzing the possible impact of environment lighting conditions on the quality evaluation of 3D objects in mixed reality (MR), and 3) benchmark state-of-the-art objective metrics in this context. The subjective results provide insights for recommendations for subjective testing in MR/AR, showing that ACR-HR can be used in similar QoE tests and reflecting the influence among the lighting conditions, the content characteristics, and the type of degradations. The objective results show an acceptable performance of perceptual metrics for geometry quantization artifacts and point out the need of further research on metrics covering both geometry and texture compression degradations.

Assessment Methods and Factors Determining Positive Indoor Soundscapes in Residential Buildings: A Systematic Review

The design of an indoor acoustic environment positively perceived by building occupants requires a perceptual approach to be adopted in order to define what makes it sound good. Soundscape standards ISO 12913 have been introduced to assess how the acoustic environment is perceived, in context, by people. According to the standards, a straightforward characterization of a soundscape as positive is currently possible only through measurements by persons, because of a current gap in linking perceptual metrics to acoustic or psychoacoustic measurements. In addition, despite applying also to indoor contexts, methods and perceptual metrics described by the standards have been mainly derived from studies related to outdoor urban environments and it is not clear whether they could be directly applied indoor. For this reason, a systematic review was performed to investigate: (i) Data collection methods used in the literature for indoor residential soundscapes and (ii) factors, output of such methods, that characterize them positively. For this purpose, a systematic review has been conducted in accordance with the PRISMA guidelines (preferred reporting items for systematic reviews and meta-analyses) guidelines. The Scopus database was searched for peer-reviewed journal papers published in English, between 1 January 2009 and 24 June 2019, including: (1) field or laboratory studies relevant to residential buildings and (2) studies assessing factors that influence the perception by building users of indoor acoustic environments. The search excluded studies related to: (a) Speech perception issues; (b) noise-induced sleep disturbance; (c) acoustic perception by hearing impaired building users; (d) perception of vibrations or impact sounds. The search returned 1087 results. After the screening process, 37 articles were finally included. Given the differences in methodologic approaches, a quantitative meta-analysis could not be performed, and a qualitative approach was adopted instead. A large part of the selected literature reflected a general effort of minimizing noise annoyance by reducing noise exposure and, in particular, noise levels. Questionnaires and guided interviews were used to capture people’s perception, while the adoption of soundwalks and non-participatory behavioral studies did not emerge in the review literature and need further investigation. The evaluation of a variety of auditory sensations both in their positive and negative dimensions, beyond annoyance, would be required to explore the positive perceptual potential of sounds. Besides sound level, a variety of factors related and unrelated to the acoustic environment were found to affect perceptual outcomes and a framework of evaluation has been proposed as a reference for future assessments. Results encourage the integration of soundscape methodologies into IEQ research, in order to enhance user health and well-being.