Augmented saliency model using automatic 3D head pose detection and learned gaze following in natural scenes

doi:10.1016/j.visres.2014.10.027

Paper

Augmented saliency model using automatic 3D head pose detection and learned gaze following in natural scenes

Published Nov 1, 2015 · Daniel F. Parks, A. Borji, L. Itti

Vision Research

Q2 SJR score

51

Citations

0

Influential Citations

Full text

Semantic Scholar

Abstract

Abstract removed due to Elsevier request; this does not indicate any issues with the research. Click the full text link above to read the abstract and view the original source.

Study Snapshot

Key takeawayThe Dynamic Weighting of Cues model (DWOC) effectively predicts eye movements of passive observers in natural scenes by combining bottom-up saliency, actor's head pose, and gaze direction, improving our understanding of visual attention mechanisms.

PopulationOlder adults (50-71 years)

Sample size24

MethodsObservational

OutcomesBody Mass Index projections

ResultsSocial networks mitigate obesity in older groups.

Sign up to use Study Snapshot

Consensus is limited without an account. Create an account or sign in to get more searches and use the Study Snapshot.

Create an account

Paper

Augmented saliency model using automatic 3D head pose detection and learned gaze following in natural scenes

Sign up to use Study Snapshot

References

Complementary effects of gaze direction and early saliency in guiding fixations during free viewing.

Gaze direction is a strong attentional cue in guiding eye movements during free viewing, complementing low-level saliency cues and derived from both actor faces and eyes in natural scenes.

ImageNet Large Scale Visual Recognition Challenge

The ImageNet Large Scale Visual Recognition Challenge has led to significant advances in object recognition, highlighting key breakthroughs and comparing current computer vision accuracy to human accuracy.

Modeling Task Control of Eye Movements

Advances in eye tracking and probabilistic modeling techniques can help model the control of eye movements in natural behavior, with fixations selecting task-relevant information based on expected reward and environmental uncertainty.

What/Where to Look Next? Modeling Top-Down Visual Attention in Complex Interactive Environments

Our dynamic Bayesian network model effectively models top-down visual attention in complex interactive environments, outperforming simpler models and state-of-the-art algorithms.

Visual Focus of Attention in Non-calibrated Environments using Gaze Estimation

Our system can estimate visual focus of attention using head rotation and eye gaze estimations, in unpretending environments, using simple hardware like a webcam.

Citations