AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Connecting Gaze, Scene, and Attention: Generalized Attention Estimation via Joint Modeling of Gaze and Scene Saliency

Eunji Chong, Nataniel Ruiz, Yongxin Wang, Yun Zhang, Agata Rozga, James M. Rehg

ECCV 2018 · Detection and segmentation › Open-set and few-shot detection · approach: Visual relationship and scene graph detection · 155 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add EYEDIAP training data (ablation)gaze-saliency model · GazeFollow testAUC: 0.887 -> 0.896Improved
add SynHead training data (ablation)gaze-saliency model · GazeFollow testAUC: 0.895 -> 0.896No clear effect
add both EYEDIAP and SynHead (ablation)gaze-saliency model · GazeFollow testAUC: 0.891 -> 0.896Improved
add project-and-compare loss (ablation)gaze-saliency model · GazeFollow testAUC: 0.895 -> 0.896No clear effect
use 10x10 heatmap instead of 15x15 map resolution (ablation)gaze-saliency model · GazeFollow testAUC: 0.778 -> 0.896Improved
use separate scene pathway plus face pathway instead of single ResNet50 with ROI-pooling (ablation)gaze-saliency model · GazeFollow testAUC: 0.700 -> 0.896Improved
add EYEDIAP to GazeFollow-only training (ablation)fixation likelihood model · MMDB fixation likelihoodaverage precision: 0.737 -> 0.820Improved
add SynHead to GazeFollow and EYEDIAP training (ablation)fixation likelihood model · MMDB fixation likelihoodaverage precision: 0.820 -> 0.902Improved
use joint gaze and saliency modeling vs GazeFollow-only baseline on 2x2 grid (ablation)gaze-saliency model · MMDB grid classification 2x2precision: 0.344 -> 0.744Improved
use joint gaze and saliency modeling vs GazeFollow baseline on 5x5 grid (ablation)gaze-saliency model · MMDB grid classification 5x5precision: 0.210 -> 0.614Improved
add gaze angle features to SVM with GazeFollow (ablation)SVM classifier · MMDB fixation likelihoodaverage precision: 0.311 -> 0.531Improved
add head pose features to Random Forest with GazeFollow (ablation)Random Forest classifier · MMDB fixation likelihoodaverage precision: 0.707 -> 0.785Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy