AI Paper Atlas

Research map / 3D vision / Human pose estimation

Dynamic 3D Gaze From Afar: Deep Gaze Estimation From Temporal Eye-Head-Body Coordination

Soma Nonaka, Shohei Nobuhara, Ko Nishino

CVPR 2022 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture · 37 citations (OpenAlex)

Check 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
Use temporal head-body coordination to estimate gaze (ablation)Ours · GAFA test set, all scenes3D MAE: 24.1 -> 21.7Improved
Use estimated head and body uncertainty in the gaze network (ablation)Ours · GAFA test set, all scenes3D MAE: 22.1 -> 21.7Improved
Include body direction as an input (ablation)Ours · GAFA test set, all scenes3D MAE: 24.1 -> 21.7Improved
Include head direction as an input (ablation)Ours · GAFA test set, all scenes3D MAE: 24.9 -> 21.7Improved
Add opportunistic eye-appearance integration (ablation)Ours · GAFA test set, all scenes3D MAE: 21.7 -> 20.4Improved
Train the head and body network on AGORA rather than GAFA (ablation)Ours · GAFA test set, all scenes3D MAE: 21.7 -> 27.3Hurt
Combine monocular predictions using uncertainty-weighted multiview averaging (ablation)Ours · GAFA test set, all scenes3D MAE: 21.6 -> 20.8Improved
Use multiview observations and 3D body velocity (ablation)Ours · GAFA test set, all scenes3D MAE: 21.6 -> 18.9Improved
Train the head and body network on AGORA and the gaze network on GAFAOurs · MoDiPro2D MAE: 46.3 -> 25.6Improved
Use temporal head-body coordination instead of static facial keypointsOurs versus Dias et al. · MoDiPro2D MAE: 32.1 -> 25.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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