Design of Video Quality Metrics with Multi-Way Data Analysis

Keimel, Christian

doi:10.1007/978-981-10-0269-4

Cited by 6 publications

(3 citation statements)

References 245 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…And finally, there was no significant difference in the chance of panicking between the baseline (M = 14.92, SD = 25.84) and the fear-eliciting scenario without cues (M = 19.12, SD = 20.88), t(23) = 1.24, p > .05 (figure 4). Finally, as the reported SUD scores are based on a large scale-range (in this case 1 to 100), three types of biases could occur: contraction bias (i.e., when participating subjects avoid using the extremes of the scales), centering bias (i.e., tendency to use the center of scales), and range equalizing bias (i.e., when participants use the same range of responses independent of the range of stimuli) (Keimel, 2016). Consequently, it was decided to baseline all SUD scores in experimental conditions for each participant by subtracting their average SUD score reported in the baseline condition (i.e., NEU-NW in Table 1), and these values were used in following analyses (Mathôt et al, 2018).…”

Section: Preprocessing and Manipulation Checkmentioning

confidence: 99%

Can You Feel It?

Morton

Letter

All

et al. 2021

International Journal of Virtual and Augmented Reality

View full text Add to dashboard Cite

Virtual reality exposure therapy (VRET) has been widely acknowledged as an effective alternative for in vivo exposure therapy (iVET). So far, previous research focused on long- and short-term effectiveness and comparisons to iVET, whereas the impact of design choices is understudied. Hence, the present study focuses on the effectiveness of several types of anxiety cues for the manipulation of anxiety. More specifically, five interoceptive cues (i.e., “fake” bodily sensations for tunnel vision, light flickering, heartbeat audio, blurred vision, and dizziness) and a physical cue (i.e., heat stimulation) are implemented in the VRET design of a within-subjects experiment with people who have claustrophobic and panic tendencies (N = 24). Results show that adding interoceptive cues significantly increased reported levels of anxiety, independent of the type of interoceptive cue. However, introducing a physical cue in VRET can also be effective but has no real added value when combined. Studies focusing on the design of anxiety cues can be valuable in understanding the effectiveness of VRET.

show abstract

Section: Preprocessing and Manipulation Checkmentioning

confidence: 99%

Can You Feel It?

Morton

Letter

All

et al. 2021

International Journal of Virtual and Augmented Reality

View full text Add to dashboard Cite

show abstract

“…In total 22 people participated. Each visual acuity test took approximately 3 to 4 minutes, while the entire test session was kept under the maximum testing limit of 30 minutes, as recommended by [26].…”

Section: A Experimental Setupmentioning

confidence: 99%

Exploratory Study on User's Dynamic Visual Acuity and Quality Perception of Impaired Images

Letter¹,

All²,

Marez³

et al. 2020

Preprint

View full text Add to dashboard Cite

In this paper we assess the impact of head movement on user's visual acuity and their quality perception of impaired images. There are physical limitations on the amount of visual information a person can perceive and physical limitations regarding the speed at which our body, and as a consequence our head, can explore a scene. In these limitations lie fundamental solutions for the communication of multimedia systems. As such, subjects were asked to evaluate the perceptual quality of static images presented on a TV screen while their head was in a dynamic (moving) state. The idea is potentially applicable to virtual reality applications and therefore, we also measured the image quality perception of each subject on a head mounted display. Experiments show the significant decrease in visual acuity and quality perception when the user's head is not static, and give an indication on how much the quality can be reduced without the user noticing any impairments.

show abstract

“…Objective VQA can be classified with respect to different factors. The most common way of classification in the literature [ 8 , 9 , 10 , 11 ] is based on the availability of the pristine, reference videos, whose visual quality is considered perfect for the objective VQA algorithm. Specifically, objective VQA is categorized into three groups: full-reference (FR), reduced-reference (RR), and no-reference (NR) ones.…”

Section: Introductionmentioning

confidence: 99%

No-Reference Video Quality Assessment Using Multi-Pooled, Saliency Weighted Deep Features and Decision Fusion

Varga

2022

Sensors

View full text Add to dashboard Cite

With the constantly growing popularity of video-based services and applications, no-reference video quality assessment (NR-VQA) has become a very hot research topic. Over the years, many different approaches have been introduced in the literature to evaluate the perceptual quality of digital videos. Due to the advent of large benchmark video quality assessment databases, deep learning has attracted a significant amount of attention in this field in recent years. This paper presents a novel, innovative deep learning-based approach for NR-VQA that relies on a set of in parallel pre-trained convolutional neural networks (CNN) to characterize versatitely the potential image and video distortions. Specifically, temporally pooled and saliency weighted video-level deep features are extracted with the help of a set of pre-trained CNNs and mapped onto perceptual quality scores independently from each other. Finally, the quality scores coming from the different regressors are fused together to obtain the perceptual quality of a given video sequence. Extensive experiments demonstrate that the proposed method sets a new state-of-the-art on two large benchmark video quality assessment databases with authentic distortions. Moreover, the presented results underline that the decision fusion of multiple deep architectures can significantly benefit NR-VQA.

show abstract

Design of Video Quality Metrics with Multi-Way Data Analysis

Cited by 6 publications

References 245 publications

Can You Feel It?

Can You Feel It?

Exploratory Study on User's Dynamic Visual Acuity and Quality Perception of Impaired Images

No-Reference Video Quality Assessment Using Multi-Pooled, Saliency Weighted Deep Features and Decision Fusion

Contact Info

Product

Resources

About