Video saliency detection via bagging-based prediction and spatiotemporal propagation

Background: Herd immunity or community immunity refers to the reduced risk of infection among susceptible individuals in a population through the presence and proximity of immune individuals. Recent studies suggest that improving the understanding of community immunity may increase intentions to get vaccinated.
Objective: This study aims to design a web application about community immunity and optimize it based on users’ cognitive and emotional responses.
Methods: Our multidisciplinary team developed a web application about community immunity to communicate epidemiological evidence in a personalized way. In our application, people build their own community by creating an avatar representing themselves and 8 other avatars representing people around them, for example, their family or coworkers. The application integrates these avatars in a 2-min visualization showing how different parameters (eg, vaccine coverage, and contact within communities) influence community immunity. We predefined communication goals, created prototype visualizations, and tested four iterative versions of our visualization in a university-based human-computer interaction laboratory and community-based settings (a cafeteria, two shopping malls, and a public library). Data included psychophysiological measures (eye tracking, galvanic skin response, facial emotion recognition, and electroencephalogram) to assess participants’ cognitive and affective responses to the visualization and verbal feedback to assess their interpretations of the visualization’s content and messaging.
Results: Among 110 participants across all four cycles, 68 (61.8%) were women and 38 (34.5%) were men (4/110, 3.6%; not reported), with a mean age of 38 (SD 17) years. More than half (65/110, 59.0%) of participants reported having a university-level education. Iterative changes across the cycles included adding the ability for users to create their own avatars, specific signals about who was represented by the different avatars, using color and movement to indicate protection or lack of protection from infectious disease, and changes to terminology to ensure clarity for people with varying educational backgrounds. Overall, we observed 3 generalizable findings. First, visualization does indeed appear to be a promising medium for conveying what community immunity is and how it works. Second, by involving multiple users in an iterative design process, it is possible to create a short and simple visualization that clearly conveys a complex topic. Finally, evaluating users’ emotional responses during the design process, in addition to their cognitive responses, offers insights that help inform the final design of an intervention.
Conclusions: Visualization with personalized avatars may help people understand their individual roles in population health. Our app showed promise as a method of communicating the relationship between individual behavior and community health. The next steps will include assessing the effects of the application on risk perception, knowledge, and vaccination intentions in a randomized controlled trial. This study offers a potential road map for designing health communication materials for complex topics such as community immunity.

/pdf/a-web-application-about-herd-immunity-using-personalized-4frgsgtxei.pdf

A Web Application About Herd Immunity Using Personalized Avatars: Development Study.

Since 2012, usability testing in Italian public administration (PA) has been guided by the eGLU 2.1 technical protocols, which provide a set of principles and procedures to support specialized usability assessments in a controlled and predictable way. This paper describes a new support tool for usability testing that aims to facilitate the application of eGLU 2.1 and the design of its User eXperience (UX) evaluation methodology. The usability evaluation tool described in this paper is called UTAssistant (Usability Tool Assistant). UTAssistant has been entirely developed as a Web platform, supporting evaluators in designing usability tests, analyzing the data gathered during the test and aiding Web users step-by-step to complete the tasks required by an evaluator. It also provides a library of questionnaires to be administered to Web users at the end of the usability test. The UX evaluation methodology adopted to assess the UTAssistant platform uses both standard and new bio-behavioral evaluation methods. From a technological point of view, UTAssistant is an important step forward in the assessment of Web services in PA, fostering a standardized procedure for usability testing without requiring dedicated devices, unlike existing software and platforms for usability testing.

UX Evaluation Design of UTAssistant: A New Usability Testing Support Tool for Italian Public Administrations

We describe a new Objective Video Quality Assessment (VQA) metric, consisting of a method based on spatio-temporal saliency to model human visual perception of quality. Accurate measurement of video quality is an important step in many video-based applications. Algorithms that are able to significantly predict human perception of video quality are still needed to evaluate video processing models, in order to overcome the high cost and time requirement for large-scale subjective evaluations. Objective quality assessment methods are used for several applications, such as monitoring video quality in quality control systems, benchmarking video compression algorithms, and optimizing video processing and transmission systems. Objective Video Quality Assessment (VQA) methods attempt to predict an average of human perception of video quality. Therefore subjective tests are used as a benchmark for evaluating the performance of objective models. This paper presents a new VQA metric, called Sencogi Spatio-Temporal Saliency Metric (Sencogi-STSM). This metric generates subjective quality scores of video compression in terms of prediction efficacy and accuracy than the most used objective VQA models. The paper describes the spatio-temporal model behind the proposed metric, the evaluation of its performance at predicting subjective scores, and the comparison with the most used objective VQA metrics.

Using Spatio-Temporal Saliency to Predict Subjective Video Quality: A New High-Speed Objective Assessment Metric

This work investigates the relation between subjective Video Quality Assessment (VQA) metrics and psychophysiological measures of human interaction assessment such as gaze tracking, electroencephalography and facial expression recognition. Subjective quality assessment is based on deliberate judgement attributions of perceived quality and processes that human perceivers are not consciously aware of. Traditional VQA methods ask participants to deliberately assign a quality score to videos in terms of the perceptual video quality. A methodology combining psychophysiological measures with traditional VQA methods is rarely used in the literature. This paper describes a model of video quality assessment which takes into account both explicit and implicit measures of subjective quality, by addressing two questions: (1) Do traditional video quality assessment methods correlate with unaware/implicit psychophysiological measures of quality perception assessment? (2) What can the main psychophysiological methods add to traditional video quality assessment? Findings show that (1) psychophysiological measures are able to measure differences of perceptual quality in compressed videos in terms of number of fixations and that (2) both VQA methods and psychophysiological assessment methods combined are able to provide additional information about cognitive and affective processes of attribution of the affective factors that underlie the attribution of quality.

Explicit and Implicit Measures in Video Quality Assessment

Images are a key element for conveying information about visual systems. However, image-based representation and communication require large information bandwidth. Image compression is currently the leading methodology for reducing bandwidth/load problems thus improving User Experience. Synthetic objective metrics are often used to assess the quality of image compression models, but they often do not reliably predict subjective ratings. This work shows the end-users’ quality evaluation of a new compression plug-in fully compliant with all on-going image formats. The subjective quality assessment of jpeg pictures compressed by the plug-in followed a new Web-based Single Stimulus Continuous Quality Scale method, whose validity and reliability have been described in a previously published study. The results of this study show that pictures compressed by the proposed adaptive image compression plug-in have a 55% compression gain compared to jpeg images compressed by Facebook Mobile, with no loss in perceived

The Web-based Subjective Quality Assessment of an Adaptive Image Compression Plug-in

User experience has a fundamental role in determining the effectiveness of image compression methods. This work presents the subjective evaluation of a new compression plug-in for current compression formats developed by Cogisen. The quality of image compression methods is often evaluated by objective metrics based on subjective quality datasets, rather than by using subjective quality evaluation tests. Cogisen's compression method follows an adaptive compression process that evaluates the saliency of any image and calculates the level of compression beyond which viewers shall be aware of image quality degradation. The Single Stimulus Continuous Quality Scale method was used to conduct the subjective quality evaluation of image compression. Pictures compressed by the Facebook Mobile lossy JPEG compression and by the Cogisen plug-in integrated in the Facebook Mobile compression settings were used. The results of the user quality evaluation of pictures show about a 45i¾?% compression improvement, with no loss in perceived image quality, for pictures compressed by the Cogisen plug-in compared to jpeg pictures as compressed by Facebook Mobile.

Validating a Quality Perception Model for Image Compression: The Subjective Evaluation of the Cogisen's Image Compression Plug-in

Objective Video Quality Assessment (VQA) is often used to predict users visual perception of video quality. In the literature, the performance evaluation of objective measures is based on benchmark subjective scores of perceived quality. This paper shows the evaluation of an algorithmic measure on videos presented on mobile devices. The VQA measure is called Sencogi Spatio-Temporal Saliency Metric (Sencogi-STSM), and it uses a spatio-temporal saliency to model subjective perception of video quality. Since STSM was previously validated with a subjective test conducted on laptop computers, the goal of this work was to verify whether the measure is able to significantly predict users’ perception of video quality also on mobile devices. Results show that, compared to the standard VQA metrics, only Sencogi-STSM is able to significantly predict subjective DMOS. This paper describes Sencogi-STSM’s biologically plausible model, its performance evaluation and the comparison with the most commonly used objective VQA metrics.

Damon Millar

Papers

Using Spatio-Temporal Saliency to Predict Subjective Video Quality: A New High-Speed Objective Assessment Metric

Explicit and Implicit Measures in Video Quality Assessment

The Web-based Subjective Quality Assessment of an Adaptive Image Compression Plug-in

Validating a Quality Perception Model for Image Compression: The Subjective Evaluation of the Cogisen's Image Compression Plug-in

Sencogi Spatio-Temporal Saliency: A New Metric for Predicting Subjective Video Quality on Mobile Devices