AI Paper Atlas

Research map / Video / Action recognition

In the Eye of Beholder: Joint Learning of Gaze and Actions in First Person Video

Yin Li, Miao Liu, James M. Rehg

ECCV 2018 · Video › Action recognition · approach: Disentangled action recognition · 326 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
joint RGB and flow training instead of RGB only (ablation)I3D · EGTEA Gaze+ action recognitionvideo accuracy: 47.26 -> 49.79Improved
add RGB stream to flow stream (ablation)I3D · EGTEA Gaze+ action recognitionvideo accuracy: 38.31 -> 47.26Improved
joint training instead of late fusion (ablation)I3D · EGTEA Gaze+ action recognitionvideo accuracy: 48.84 -> 49.79Improved
probabilistic gaze modeling instead of deterministic MLE (ablation)Gaze-action model · EGTEA Gaze+ action recognitionvideo accuracy: 51.12 -> 53.30Improved
probabilistic gaze modeling instead of deterministic MLE (ablation)Gaze-action model · EGTEA Gaze+ gaze estimationF1: 24.68 -> 32.97Improved
add dropout after attention-pooled features (ablation)Probabilistic model · EGTEA Gaze+ action recognitionvideo accuracy: 53.30 -> 52.12Hurt
add dropout after attention-pooled features (ablation)Probabilistic model · EGTEA Gaze+ gaze estimationF1: 32.97 -> 32.66Hurt
gaze supervision instead of unsupervised soft attention (ablation)Attention model · EGTEA Gaze+ action recognitionvideo accuracy: 50.30 -> 53.30Improved
soft attention without gaze supervision added to I3D (ablation)I3D Joint · EGTEA Gaze+ action recognitionvideo accuracy: 49.79 -> 50.30Improved
gaze supervision for attention (ablation)Attention model · EGTEA Gaze+ gaze estimationF1: 10.27 -> 32.97Improved
use human gaze at test time instead of predicted gazeI3D+Gaze vs ours · EGTEA Gaze+ action recognitionvideo accuracy: 51.21 -> 53.30Hurt
joint gaze and action modeling instead of gaze-only modelsDeep Gaze · EGTEA Gaze+ gaze estimationF1: 33.51 -> 32.97Hurt

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