Clustering of Gaze During Dynamic Scene Viewing is Predicted by Motion

Mital, Parag K.; Smith, Tim J.; Hill, Rebecca J.; Henderson, John M.

doi:10.1007/s12559-010-9074-z

Cited by 399 publications

(425 citation statements)

References 106 publications

Supporting

Mentioning

404

Contrasting

Unclassified

Order By: Relevance

“…Gaze of multiple participants was visualized on top of the original video and a fixation density heatmap created by spreading a circular gaussian (2° standard deviation) around each fixation (Mital, Smith, Hill, & Henderson, 2011). Hotter colors indicate a greater concentration of gaze (see Figure 1).…”

Section: Resultsmentioning

confidence: 99%

The Penny Drops: Change Blindness at Fixation

2012

View full text Add to dashboard Cite

Our perception of the visual world is fallible. Unattended objects may change without us noticing as long as the change does not capture attention (change blindness). However, it is often assumed that changes to a fixated object will be noticed if it is attended. In this experiment we demonstrate that participants fail to detect a change in identity of a coin during a magic trick even though eyetracking indicates that the coin is tracked by the eyes throughout the trick. The change is subsequently detected when participants are instructed to look for it. These results suggest that during naturalistic viewing attention can be focused on an object at fixation without including all of its features.

show abstract

Section: Resultsmentioning

confidence: 99%

The Penny Drops: Change Blindness at Fixation

2012

View full text Add to dashboard Cite

show abstract

“…Fried et al [16] provided a distractor dataset for still images only. Existing video saliency datasets or eye-tracking databases [54] contain the labeling of the spatial and temporal parts of a video that will gain viewers' attentions when watching it, but both the main subjects and the distractors can have high visual saliency. On the other hand, even if a video contains only one object, the object could still be a distractor.…”

Section: The Datasetmentioning

confidence: 99%

Detecting and Removing Visual Distractors for Video Aesthetic Enhancement

Zhang

et al. 2018

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Abstract-Personal videos often contain visual distractors, which are objects that are accidentally captured that can distract viewers from focusing on the main subjects. We propose a method to automatically detect and localize these distractors through learning from a manually labeled dataset. To achieve spatially and temporally coherent detection, we propose extracting features at the Temporal-Superpixel (TSP) level using a traditional SVM-based learning framework. We also experiment with end-to-end learning using Convolutional Neural Networks (CNNs), which achieves slightly higher performance than other methods. The classification result is further refined in a post-processing step based on graph-cut optimization. Experimental results show that our method achieves an accuracy of 81% and a recall of 86%. We demonstrate several ways of removing the detected distractors to improve the video quality, including video hole filling; video frame replacement; and camera path re-planning. The user study results show that our method can significantly improve the aesthetic quality of videos.

show abstract

“…Therefore, it makes sense that the researchers looking at the perceptual and cognitive understanding of films are applying findings from the eye tracking of dynamic scenes (Smith, Levin, & Cutting, 2012). For instance, Mital, Smith, Hill, and Henderson (2011) found that observers attend to areas of high motion in a dynamic scene. These findings can be applied to CCTV observation, which features different amounts of motion in the footage.…”

Section: Effects Of Event Type On Eye Movementsmentioning

confidence: 99%

CCTV Observation: The Effects of Event Type and Instructions on Fixation Behaviour in an Applied Change Blindness Task

Graham

Sauer

Akehurst

et al. 2017

Applied Cognitive Psychology

View full text Add to dashboard Cite

Although closed-circuit television (CCTV) footage is used in both crime prevention and police investigations to prosecute criminals, relatively little is known about the strategies that observers use when monitoring and interpreting (criminal) events observed in such footage. Howard, Troscianko, Gilchrist, Behera, and Hogg (2009) stated that measuring eye movements during CCTV monitoring might produce innovative data to determine the strategies people use when attending to footage. Stainer, Scott-Brown, and Tatler (2013) examined the eye movements of two trained CCTV operators monitoring multiple display screens on a wall, compared to a single-spot monitor (the operator could select only one of multiple screens to inspect in more detail). They found that more attention was allocated to the single-screen-spot monitor than the multiplex display, with the more (cf. less) experienced operator utilising the spot monitor more often. Stainer et al. (2013) identified that their observers selectively allocated attention based on expected informativeness. This replicated Howard, Troscianko, and Gilchrist's (2010) finding that participants with more experience watching football matches shifted their eyes to more informative areas of the footage earlier than did non-experienced observers. Following on from this work, we investigated whether event type and instructions affected fixation behaviour during CCTV observation and whether fixation behaviour predicted observers' detection of critical changes in the footage.

show abstract

Clustering of Gaze During Dynamic Scene Viewing is Predicted by Motion

Cited by 399 publications

References 106 publications

The Penny Drops: Change Blindness at Fixation

The Penny Drops: Change Blindness at Fixation

Detecting and Removing Visual Distractors for Video Aesthetic Enhancement

CCTV Observation: The Effects of Event Type and Instructions on Fixation Behaviour in an Applied Change Blindness Task

Contact Info

Product

Resources

About