AI Paper Atlas

Research map / Video / Action recognition

Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition From Egocentric RGB Videos

Yilin Wen, Hao Pan, Lei Yang, Jia Pan, Taku Komura, Wenping Wang

CVPR 2023 · Video › Action recognition · approach: Skeleton-based action recognition · 56 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
Use a short temporal pose window (t=16) instead of image-only pose estimation (ablation)HTT pose block · FPHAAUC(0-80): 0.776 -> 0.810Improved
Use a short temporal pose window (t=16) instead of image-only pose estimation (ablation)HTT pose block · H2O, left handMEPE: 40.12 -> 35.02Improved
Extend pose context from t=16 to t=128 (ablation)HTT pose block · FPHAAUC(0-80): 0.810 -> 0.800Hurt
Extend pose context from t=16 to t=128 (ablation)HTT pose block · H2O, left handMEPE: 35.02 -> 36.41Hurt
Extend action context from T=16 to T=128 (ablation)HTT action block · H2OClassification accuracy: 74.38 -> 86.36Improved
Extend action context from T=16 to T=128 (ablation)HTT action block · FPHAClassification accuracy: 90.96 -> 94.09Improved
Cascade pose and action blocks instead of running them in parallel (ablation)HTT action recognition · FPHAClassification accuracy: 93.22 -> 94.09Improved
Cascade pose and action blocks instead of running them in parallel (ablation)HTT action recognition · H2OClassification accuracy: 80.17 -> 86.36Improved
Add object label to the action-block input (ablation)HTT action recognition · FPHAClassification accuracy: 93.57 -> 94.09Improved
Add object label to the action-block input (ablation)HTT action recognition · H2OClassification accuracy: 82.65 -> 86.36Improved
Add hand pose to the action-block input (ablation)HTT action recognition · FPHAClassification accuracy: 91.65 -> 94.09Improved
Add hand pose to the action-block input (ablation)HTT action recognition · H2OClassification accuracy: 85.12 -> 86.36Improved

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