Top-down guided eye movements

Chernyak, Dimitri; Stark, Lawrence

doi:10.1109/3477.938257

Cited by 41 publications

(30 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are a few studies that propose computational models of contextual influences in object recognition. 26,27 Common to these models is the use of object-centered representations in which the context is described as a collection of objects and a model of the joint distribution of objects in a reduced world. This approach requires object-centered mechanisms that provide candidate objects that are transformed into recognizable objects through analysis of the consistency with the other candidate objects in the scene.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Modeling global scene factors in attention

2003

View full text Add to dashboard Cite

Models of visual attention have focused predominantly on bottom-up approaches that ignored structured contextual and scene information. I propose a model of contextual cueing for attention guidance based on the global scene configuration. It is shown that the statistics of low-level features across the whole image can be used to prime the presence or absence of objects in the scene and to predict their location, scale, and appearance before exploring the image. In this scheme, visual context information can become available early in the visual processing chain, which allows modulation of the saliency of image regions and provides an efficient shortcut for object detection and recognition.

show abstract

Section: Discussionmentioning

confidence: 99%

“…[22][23][24] Notwithstanding the accumulating evidence for contextual effects on visual exploration, few models of visual search and attention proposed so far include the use of context. [25][26][27][28][29][30] In this paper a statistical framework for incorporating contextual information in the search task is proposed.…”

Section: Introductionmentioning

confidence: 99%

Modeling global scene factors in attention

2003

View full text Add to dashboard Cite

show abstract

“…The aforementioned WTA scheme [5], [9], or the selection of the proto-object with the highest attentional weight [10] are two examples. Even when probabilistic frameworks are used to infer where to look next, the final decision is often taken via the maximum a posteriori (MAP) criterion, which again is an arg max operation (e.g., [11]- [15]), or variants such as the robust mean (arithmetic mean with maximum value) over candidate positions [16].…”

mentioning

confidence: 99%

Ecological Sampling of Gaze Shifts

Boccignone

Ferraro

2014

IEEE Trans. Cybern.

View full text Add to dashboard Cite

Abstract-Visual attention guides our gaze to relevant parts of the viewed scene, yet the moment-to-moment relocation of gaze can be different among observers even though the same locations are taken into account. Surprisingly, the variability of eye movements has been so far overlooked by the great majority of computational models of visual attention. In this paper we present the ecological sampling model, a stochastic model of eye guidance explaining such variability. The gaze shift mechanism is conceived as an active random sampling that the foraging eye carries out upon the visual landscape, under the constraints set by the observable features and the global complexity of the landscape. By drawing on results reported in the foraging literature, the actual gaze relocation is eventually driven by a stochastic differential equation whose noise source is sampled from a mixture of α-stable distributions. This way, the sampling strategy proposed here allows to mimic a fundamental property of the eye guidance mechanism: where we choose to look next at any given moment in time, it is not completely deterministic, but neither is it completely random To show that the model yields gaze shift motor behaviors that exhibit statistics similar to those displayed by human observers, we compare simulation outputs with those obtained from eye-tracked subjects while viewing complex dynamic scenes.

show abstract

“…Due to the omission of any top-down processes, saliency has been shown to be inadequate for such video contexts (including open sign language [11]). Other techniques [8] introduce the idea of a top-down approach, but rely instead on categorizing objects within an image and then associating predetermined probabilities of eye-fixation with each object. Although this incorporates a top-down approach it ignores prior knowledge available about the scene.…”

Section: Introductionmentioning

confidence: 99%

A Multicue Bayesian State Estimator for Gaze Prediction in Open Signed Video

Davies

Agrafiotis

Canagarajah

et al. 2009

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Abstract-We propose a multicue gaze prediction framework for open signed video content, the benefits of which include coding gains without loss of perceived quality. We investigate which cues are relevant for gaze prediction and find that shot changes, facial orientation of the signer and face locations are the most useful. We then design a face orientation tracker based upon grid-based likelihood ratio trackers, using profile and frontal face detections. These cues are combined using a grid-based Bayesian state estimation algorithm to form a probability surface for each frame. We find that this gaze predictor outperforms a static gaze prediction and one based on face locations within the frame.

show abstract

Top-down guided eye movements

Cited by 41 publications

References 27 publications

Modeling global scene factors in attention

Modeling global scene factors in attention

Ecological Sampling of Gaze Shifts

A Multicue Bayesian State Estimator for Gaze Prediction in Open Signed Video

Contact Info

Product

Resources

About