AI Paper Atlas

Research map / 3D vision / Human pose estimation

Future Person Localization in First-Person Videos

Takuma Yagi, Karttikeya Mangalam, Ryo Yonetani, Yoichi Sato

CVPR 2018 · 3D vision › Human pose estimation · approach: Temporal video pose estimation · 190 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 person scale to location inputs (ablation)Future person localization model · FPL DatasetFDE (pixels), Average: 88.16 -> 81.86Improved
Add ego-motion to location-scale inputs (ablation)Future person localization model · FPL DatasetFDE (pixels), Average: 81.86 -> 79.09Improved
Add pose to location-scale inputs (ablation)Future person localization model · FPL DatasetFDE (pixels), Average: 81.86 -> 80.57Improved
Combine ego-motion and pose with location-scale cues (ablation)Future person localization model · FPL DatasetFDE (pixels), Average: 80.57 -> 77.26Improved
Add ego-motion to location-scale inputs (ablation)Future person localization model · First-Person Social Interaction DatasetFDE (pixels), Average: 127.40 -> 127.28No clear effect
Add pose to location-scale inputs (ablation)Future person localization model · First-Person Social Interaction DatasetFDE (pixels), Average: 127.40 -> 125.78Improved
Combine ego-motion and pose with location-scale cues (ablation)Future person localization model · First-Person Social Interaction DatasetFDE (pixels), Average: 125.78 -> 125.42Improved
Shorten the input history from 10 frames to 6 frames (ablation)Future person localization model · FPL Dataset, 10-frame futureFDE (pixels), Average: 77.26 -> 79.77Hurt
Lengthen the input history from 6 frames to 10 frames (ablation)Future person localization model · FPL Dataset, 6-frame futureFDE (pixels), Average: 46.16 -> 45.92Improved
Predict a 20-frame future instead of the standard 10-frame future (ablation)Future person localization model · FPL DatasetFDE (pixels), Average: 77.26 -> 124.85Hurt

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