AI Paper Atlas

Research map / 3D vision / Human pose estimation

Where and Why Are They Looking? Jointly Inferring Human Attention and Intentions in Complex Tasks

Ping Wei, Yang Liu, Tianmin Shu, Nanning Zheng, Song-Chun Zhu

CVPR 2018 · 3D vision › Human pose estimation · approach: Temporal video pose estimation · 70 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
jointly model pose, attention, objects, and their relations with HAOhuman intention prediction · TIAaccuracy: 0.29 -> 0.40Improved
add the human-attention relation to pose features (ablation)HAO intention prediction · TIAaccuracy: 0.34 -> 0.36Improved
add the human-attention relation to attention patches (ablation)HAO intention prediction · TIAaccuracy: 0.07 -> 0.28Improved
add the attention-object relation to attention patches (ablation)HAO intention prediction · TIAaccuracy: 0.07 -> 0.25Improved
add the attention-object relation to object features (ablation)HAO intention prediction · TIAaccuracy: 0.18 -> 0.28Improved
jointly model pose, attention, objects, and their relations with HAOhuman attention prediction · TIA3D location error: 0.655 -> 0.628Improved
jointly model pose, attention, objects, and their relations with HAOhuman attention prediction · TIA3D direction error: 0.540 -> 0.475Improved
jointly model pose, attention, objects, and their relations with HAOhuman attention prediction · TIA2D location error: 97 -> 93Improved
decompose tasks into sequential intentions and jointly use human, attention, and object informationtask recognition · TIAaccuracy: 0.62 -> 0.73Improved
add the human-attention relation to pose features (ablation)HAO task recognition · TIAaccuracy: 0.58 -> 0.61Improved
add the human-attention relation to attention patches (ablation)HAO task recognition · TIAaccuracy: 0.20 -> 0.46Improved
add the attention-object relation to attention patches (ablation)HAO task recognition · TIAaccuracy: 0.20 -> 0.54Improved

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