Active Fixation Control to Predict Saccade Sequences

Wloka, Calden; Kotseruba, Iuliia; Tsotsos, John K.

doi:10.1109/cvpr.2018.00336

Cited by 30 publications

(15 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We measured the similarity of fixation sequences across participants using a metric called the Fréchet distance; a measurement of the maximum distance between two points on two different trajectories [25]. In our case, the sequence of fixations across time represents the trajectories being analyzed.…”

Section: Primary Analysis: Visual Hierarchymentioning

confidence: 99%

See 1 more Smart Citation

Visual Hierarchy Relates to Impressions of Good Design

Urano¹,

Kurosu²,

Henselman-Petrusek³

et al. 2021

Preprint

View full text Add to dashboard Cite

Here we examine an untested assumption among graphic designers that a concept called “visual hierarchy” is tied to theperception of good design. Visual hierarchy refers to the sequence in which graphic elements in a design are seen. From adesign perspective, a stronger visual hierarchy means that a graphic design, such as a poster, will lead to more similar eyemovements among its audience. From a psychology perspective, stronger visual hierarchy may mean that information forguiding overt attention is being more effectively communicated. The consequent cognitive ease may facilitate an aestheticexperience, thereby explaining how visual hierarchy could be linked to perceptions of good design. In an empirical test, wesee that when people agree that a design is good, their eye movements are more likely to be synchronous.

show abstract

Section: Primary Analysis: Visual Hierarchymentioning

confidence: 99%

“…Recent methodological developments establish a suitable analysis of eye movements called Fréchet distance in eye-tracking research [6,25]. It is a measure of similarity between two curves (i.e., trajectories or sequences of points).…”

Section: Introductionmentioning

confidence: 99%

Visual Hierarchy Relates to Impressions of Good Design

Urano¹,

Kurosu²,

Henselman-Petrusek³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Early work on scanpath prediction has typically used bottom-up saliency maps to predict gaze shifts [43,44]. Other models have incorporated cognitively plausible mechanisms, such as inhibition of return [10,45,46] or foveal-peripheral saliency [3,16,47]. Boccignone et al [9] have created a three-stage processing model with a centre-bias, a context/layout and an object-based model to predict scanpaths on natural scenes.…”

Section: Scanpath Predictionmentioning

confidence: 99%

Scanpath Prediction on Information Visualisations

Wang¹,

Bâce²,

Bulling³

2021

Preprint

View full text Add to dashboard Cite

We propose Unified Model of Saliency and Scanpaths (UMSS)-a model that learns to predict visual saliency and scanpaths (i.e. sequences of eye fixations) on information visualisations. Although scanpaths provide rich information about the importance of different visualisation elements during the visual exploration process, prior work has been limited to predicting aggregated attention statistics, such as visual saliency. We present in-depth analyses of gaze behaviour for different information visualisation elements (e.g. Title, Label, Data) on the popular MASSVIS dataset. We show that while, overall, gaze patterns are surprisingly consistent across visualisations and viewers, there are also structural differences in gaze dynamics for different elements. Informed by our analyses, UMSS first predicts multi-duration element-level saliency maps, then probabilistically samples scanpaths from them. Extensive experiments on MASSVIS show that our method consistently outperforms state-of-the-art methods with respect to several, widely used scanpath and saliency evaluation metrics. Our method achieves a relative improvement in sequence score of 11.5 % for scanpath prediction, and a relative improvement in Pearson correlation coefficient of up to 23.6 % for saliency prediction. These results are auspicious and point towards richer user models and simulations of visual attention on visualisations without the need for any eye tracking equipment.

show abstract

“…Led by the pioneering work P.V. Amadori, T. Fischer by Itti et al [8], many studies have focused on designing computational vision attention models that can predict human eye fixations in static image observation [9], [10].…”

Section: Introductionmentioning

confidence: 99%

“…The advent of deep neural networks, together with largescale publicly available datasets and benchmarks, have further improved static visual attention models, up to the point where it is not possible to differentiate model predictions from human fixation maps [9], [11]. However, visual attention models for static image viewing cannot address nor leverage the known correlation between human fixation patterns and time [12].…”

Section: Introductionmentioning

confidence: 99%

HammerDrive: A Task-Aware Driving Visual Attention Model

Amadori

Fischer

Demiris

2022

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

We introduce HammerDrive, a novel architecture for task-aware visual attention prediction in driving. The proposed architecture is learnable from data and can reliably infer the current focus of attention of the driver in real-time, while only requiring limited and easy-to-access telemetry data from the vehicle. We build the proposed architecture on two core concepts: 1) driving can be modeled as a collection of sub-tasks (maneuvers), and 2) each sub-task affects the way a driver allocates visual attention resources, i.e., their eye gaze fixation. HammerDrive comprises two networks: a hierarchical monitoring network of forward-inverse model pairs for sub-task recognition and an ensemble network of task-dependent convolutional neural network modules for visual attention modeling. We assess the ability of HammerDrive to infer driver visual attention on data we collected from 20 experienced drivers in a virtual reality-based driving simulator experiment. We evaluate the accuracy of our monitoring network for sub-task recognition and show that it is an effective and light-weight network for reliable real-time tracking of driving maneuvers with above 90% accuracy. Our results show that HammerDrive outperforms a comparable stateof-the-art deep learning model for visual attention prediction on numerous metrics with ∼13% improvement for both Kullback-Leibler divergence and similarity, and demonstrate that taskawareness is beneficial for driver visual attention prediction.

show abstract

Active Fixation Control to Predict Saccade Sequences

Cited by 30 publications

References 44 publications

Visual Hierarchy Relates to Impressions of Good Design

Visual Hierarchy Relates to Impressions of Good Design

Scanpath Prediction on Information Visualisations

HammerDrive: A Task-Aware Driving Visual Attention Model

Contact Info

Product

Resources

About