Quantifying the importance of preserving video quality in visually important regions at the expense of background content

Alers, Hani; Redi, Judith; Heynderickx, Ingrid

doi:10.1016/j.image.2015.01.006

Cited by 6 publications

(5 citation statements)

References 34 publications

(45 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When looking at still images, humans rapidly fixate on a specific area in the image, scan it, and then move on to other area. In videos, fixations on moving objects are enabled through smooth pursuit eye movements (Alers, Redi & Heynderickx 2015).…”

Section: Methodsmentioning

confidence: 99%

“America First, the Netherlands Second” on YouTube: “spoofing” destination marketing with political satire

Turnšek

Janeček

2019

EJHR

View full text Add to dashboard Cite

This study attempts to provide initial tentative insights into the audience reception of intertwining political satire and destination marketing imagery by analysing the "America First, the Netherlands Second" video and a student sample audience response. In 2017, a series of YouTube videos named "America First" went viral. The video that started the viral phenomenon was "America First, the Netherlands Second", responding in a satirical manner to the "America First" message of the inaugural speech of U.S. president Donald J. Trump. They achieved extreme popularity both in number of views and number of new memetic videos with similar satirical messages. These videos were a form of political expression and at first sight did not seem to have much in common with communication in tourism. However, the videos included typical destination marketing imagery, intertwined with satirical representations, thus representing a humorous "spoof" on destination marketing. The study analyses participants' memory recall, eye-tracking movements and focus group responses in order to provide initial conclusions on how audiences respond to the intertwining of satirical political expression and destination marketing imagery.

show abstract

Section: Methodsmentioning

confidence: 99%

“America First, the Netherlands Second” on YouTube: “spoofing” destination marketing with political satire

Turnšek

Janeček

2019

EJHR

View full text Add to dashboard Cite

show abstract

“…Eye-tracking studies have been attempted to understand saliency in relation to video quality assessment [30]- [33]. The study in [30] focuses on investigating the relative impact of artifacts in the region of interest (ROI) and that in the background region on the overall video quality. ROI was determined by means of eye-tracking experiments.…”

Section: Related Work and Contributions A Related Workmentioning

confidence: 99%

“…However, existing eye-tracking data relevant to video quality are limited with respect to the number of human subjects, the number of stimuli and the degree of stimulus variability. For example, the eye-tracking experiments reported in [30]- [32] all made use of a single type of distortion (i.e., H.264 compression artifacts), which affects the validity of the results in terms of generalisation. The other drawback to existing eye-tracking data is that they are potentially biased due to the methodology used for data collection.…”

Section: Related Work and Contributions A Related Workmentioning

confidence: 99%

“…A fixation was defined by SMI's Software using the dispersal and duration based algorithm established in [44]. For a given video sequence, a topographic saliency map per frame is constructed by accumulating fixations over all subjects (i.e., 20 in our experiment) and with each fixation location giving rise to a gray-scale patch that simulates the foveal vision of the HVS [30], [32], [33]. The activity of the patch is modelled as a Gaussian distribution, of which the width σ approximates the size of the fovea (i.e., 2°of visual angle, 45 pixels width in our experiment).…”

Section: ) Stimulimentioning

confidence: 99%

“…The intensity of the resulting saliency map is linearly normalised to the range [0, 1]. We follow conventional practice of relevant studies [30]- [33]: when there is no experimental error (e.g., participants failing to complete the entire trial or interrupted data recording due to system failure), all recorded eye-tracking data are deemed valid. Outlier detection may be applied to the dataset.…”

Section: ) Stimulimentioning

confidence: 99%

See 2 more Smart Citations

Study of Saliency in Objective Video Quality Assessment

Zhang

Liu

2017

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Reliably predicting video quality as perceived by humans remains challenging and is of high practical relevance. A significant research trend is to investigate visual saliency and its implications for video quality assessment. Fundamental problems regarding how to acquire reliable eye-tracking data for the purpose of video quality research and how saliency should be incorporated in objective video quality metrics (VQMs) are largely unsolved. In this paper, we propose a refined methodology for reliably collecting eye-tracking data, which essentially eliminates bias induced by each subject having to view multiple variations of the same scene in a conventional experiment. We performed a large-scale eye-tracking experiment that involved 160 human observers and 160 video stimuli distorted with different distortion types at various degradation levels. The measured saliency was integrated into several best known VQMs in the literature. With the assurance of the reliability of the saliency data, we thoroughly assessed the capabilities of saliency in improving the performance of VQMs, and devised a novel approach for optimal use of saliency in VQMs. We also evaluated to what extent the state-of-the-art computational saliency models can improve VQMs in comparison to the improvement achieved by using "ground truth" eye-tracking data. The eye-tracking database is made publicly available to the research community.

show abstract

Did You Notice It?—How Can We Predict the Subjective Detection of Video Quality Changes From Eye Movements?

Radun

Nuutinen

Voigt-Antons

et al. 2017

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

Quantifying the importance of preserving video quality in visually important regions at the expense of background content

Cited by 6 publications

References 34 publications

“America First, the Netherlands Second” on YouTube: “spoofing” destination marketing with political satire

“America First, the Netherlands Second” on YouTube: “spoofing” destination marketing with political satire

Study of Saliency in Objective Video Quality Assessment

Did You Notice It?—How Can We Predict the Subjective Detection of Video Quality Changes From Eye Movements?

Contact Info

Product

Resources

About