AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition

Jungho Lee, Minhyeok Lee, Suhwan Cho, Sungmin Woo, Sungjun Jang, Sangyoun Lee

ICCV 2023 · Graph learning › Knowledge and temporal graphs · approach: Graph reasoning for visual recognition · 38 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 motion vector data stream into the same network (ablation)STC-Net baseline · NTU-RGB+D 120 joint X-Subaccuracy (%): 83.5 -> 84.8Improved
add DK-GC dilated graph kernels without curves (ablation)baseline with motion · NTU-RGB+D 120 joint X-Subaccuracy (%): 84.8 -> 85.8Improved
add intra-curve or inter-curve features via simple non-local block instead of curve aggregation (ablation)baseline with motion · NTU-RGB+D 120 joint X-Subaccuracy (%): 84.8 -> 85.2 / 85.1Improved
add curve aggregation module on top of both curves (ablation)STC module · NTU-RGB+D 120 joint X-Subaccuracy (%): 85.4 -> 85.9Improved
add DK-GC on top of STC module with aggregation (ablation)STC-Net · NTU-RGB+D 120 joint X-Subaccuracy (%): 85.9 -> 86.2Improved
increase DK-GC kernel size from 3 to 5 or 7 (ablation)STC-Net · NTU-RGB+D 120 joint X-Subaccuracy (%): 86.2 -> 86.4 / 86.2No clear effect
exclude structurally identical node in inter-frame k-NN (ablation)STC module · NTU-RGB+D 120 joint X-Subaccuracy (%): 86.2 vs 86.2 X-Sub; 87.8 -> 88.0 X-SetImproved
use curves instead of straight lines (k=1) in spatio-temporal module (ablation)STC module · NTU-RGB+D 120 joint X-Subaccuracy (%): 85.4 -> 85.9Improved
increase ensemble from 4 to 6 streams (ablation)STC-Net · NTU-RGB+D 120 X-Subaccuracy (%): 89.9 -> 90.2Improved
replace InfoGCN with STC-Net at 2 ensemblesskeleton action recognition · NTU-RGB+D 120 X-Subaccuracy (%): 88.5 -> 89.3Improved
replace InfoGCN with STC-Net at 6 ensemblesskeleton action recognition · NTU-RGB+D 120 FLOPsFLOPs: 10.08 G -> 11.10 GHurt

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