AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Constructing Stronger and Faster Baselines for Skeleton-Based Action Recognition

Yifan Song, Zhang Zhang, Caifeng Shan, Liang Wang

TPAMI 2022 · Graph learning › Knowledge and temporal graphs · approach: Graph reasoning for visual recognition · 566 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 ST-JointAtt attention module (ablation)EfficientGCN-B0 · NTU 60 X-subaccuracy (%): 88.9 -> 90.0Improved
use ST-JointAtt instead of STCAtt (ablation)EfficientGCN-B0 · NTU 60 X-subaccuracy (%): 89.5 -> 90.0Improved
use ST-JointAtt instead of PartAtt (ablation)EfficientGCN-B0 · NTU 60 X-subaccuracy (%): 89.4 -> 90.0Improved
add frame-only attention (FrameAtt) instead of none (ablation)EfficientGCN-B0 · NTU 60 X-subaccuracy (%): 88.9 -> 88.5Hurt
add velocity and bone inputs to joint input (ablation)EfficientGCN-B0 · NTU 60 X-subaccuracy (%): 87.7 -> 90.0Improved
fuse input branches after 2nd stage instead of before 1st stage (ablation)EfficientGCN-B0 · NTU 60 X-subaccuracy (%): 88.8 -> 90.0Improved
fuse after 2nd stage instead of at the score layer (ablation)EfficientGCN-B0 · NTU 60 X-subaccuracy (%): 89.9 -> 90.0; FLOPs 3.85 -> 2.73No clear effect
use SGLayer (r_rd=2) instead of BasicLayer for temporal convolution (ablation)EfficientGCN-B0 · NTU 60 X-subaccuracy (%): 90.0 -> 90.0; params 0.34M -> 0.29MNo clear effect
use EpSepLayer (r_ep=4) instead of SGLayer (ablation)EfficientGCN-B0 · NTU 60 X-subaccuracy (%): 90.0 -> 90.1; FLOPs 2.73 -> 3.63No clear effect
apply compound scaling (coefficient 0 to 4) (ablation)EfficientGCN · NTU 60 X-subaccuracy (%): 90.2 -> 92.1Improved
scale only width or only depth instead of compound scaling (ablation)EfficientGCN-B4 · NTU 60 X-subaccuracy (%)Hurt
raise maximum graph distance D from 1 to 2 (L=5) (ablation)EfficientGCN-B0 · NTU 60 X-subaccuracy (%): 88.1 -> 89.9Improved

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