AI Paper Atlas

Research map / Video / Video segmentation and tracking

Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition

Yifei Huang, Minjie Cai, Zhenqiang Li, Yoichi Sato

ECCV 2018 · Video › Video segmentation and tracking · approach: Physics-inspired motion prediction · 127 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 attention transition module to saliency prediction (full model) (ablation)SP · GTEA Gaze PlusAAE (deg): 5.52 -> 4.05Improved
add attention transition module to saliency prediction (full model) (ablation)SP · GTEA Gaze PlusAUC: 0.928 -> 0.957Improved
add attention transition module to saliency prediction (full model) (ablation)SP · GTEA GazeAAE (deg): 9.43 -> 7.58Improved
add attention transition module to saliency prediction (full model) (ablation)SP · GTEA GazeAUC: 0.861 -> 0.898Improved
add saliency prediction module to attention transition (full model) (ablation)AT · GTEA Gaze PlusAAE (deg): 5.02 -> 4.05Improved
use modified bce loss instead of plain bce for two-stream saliency (ablation)SP · GTEA Gaze PlusAUC: 0.918 -> 0.928Improved
use modified bce loss instead of plain bce for spatial stream (ablation)S-CNN · GTEA Gaze PlusAUC: 0.893 -> 0.905Improved
use modified bce loss instead of plain bce for temporal stream (ablation)T-CNN · GTEA Gaze PlusAAE (deg): 6.15 -> 6.07Improved
use modified bce loss instead of plain bce (ablation)T-CNN · GTEA Gaze PlusAUC: 0.906 -> 0.906No clear effect
combine spatial and temporal streams (SP) versus spatial stream alone (ablation)S-CNN · GTEA Gaze PlusAUC: 0.905 -> 0.928Improved
attention transition module alone versus saliency prediction alone (ablation)SP · GTEA GazeAAE (deg): 9.43 -> 9.51No clear effect
train attention transition on the same task rather than different tasks (ablation)AT · GTEA Gaze Plus cross-taskAAE/AUCImproved

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