AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition

Jeonghyeok Do, Munchurl Kim

ECCV 2024 · Graph learning › Knowledge and temporal graphs · approach: Graph reasoning for visual recognition · 138 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 four-type partition-specific Skate-MSA instead of no attention (ablation)SkateFormer · NTU RGB+D X-Sub60top-1 accuracy: 90.7 -> 92.6Improved
use naive full self-attention instead of partition-specific attention (ablation)SkateFormer · NTU RGB+D X-View60top-1 accuracy: 95.7 -> 95.0Hurt
Skate-MSA instead of naive self-attention reduces memory (ablation)SkateFormer · NTU RGB+Dmemory (MB): 1612.1 -> 137.6Improved
add skeletal relation partitions only (ablation)SkateFormer · NTU RGB+D X-Sub60top-1 accuracy: 90.7 -> 91.8Improved
add temporal relation partitions only (ablation)SkateFormer · NTU RGB+D X-Sub60top-1 accuracy: 90.7 -> 91.9Improved
add learnable skeletal embedding with fixed temporal embedding (Skate-Embedding) (ablation)SkateFormer · NTU RGB+D X-Sub60top-1 accuracy: 91.9 -> 92.6Improved
make temporal embedding learnable instead of fixed (ablation)Skate-Embedding · NTU RGB+D X-Sub60top-1 accuracy: 92.6 -> 91.4Hurt
use trimmed-uniform random sampling instead of fixed-stride (ablation)SkateFormer · NTU RGB+D X-Sub60top-1 accuracy: 91.4 -> 92.6Improved
add skeletal intra-instance augmentation (ablation)SkateFormer · NTU RGB+D X-Sub60top-1 accuracy: 89.8 -> 92.2Improved
add inter-instance bone-length exchange augmentation alone (ablation)SkateFormer · NTU RGB+D X-View60top-1 accuracy: 94.6 -> 94.3Hurt
add inter-instance augmentation on top of intra-instance augmentation (ablation)SkateFormer · NTU RGB+D X-Sub60top-1 accuracy: 92.2 -> 92.6Improved
increase ensemble from joint-only to four modalitiesSkateFormer · NTU RGB+D X-Sub60top-1 accuracy: 92.6 -> 93.5Improved

Later papers that compared with this method

1 later accepted paper reports SkateFormer as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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