AI Paper Atlas

Research map / Video / Action recognition

Self-Supervised 3D Action Representation Learning With Skeleton Cloud Colorization

Siyuan Yang, Jun Liu, Shijian Lu, M.H. Er, Yongjian Hu, Alex Chichung Kot

TPAMI 2023 · Video › Action recognition · approach: Skeleton-based action recognition · 37 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
pretrain with skeleton cloud colorization instead of random encoder (ablation)linear classifier · NTU RGB+D C-Subject (unsupervised)accuracy: 61.8 -> 75.2Improved
replace plain masked autoencoder pretraining with colorization repainting (ablation)3s model · NTU RGB+D C-Subject (unsupervised)accuracy: 65.9 -> 75.2Improved
add masked skeleton cloud repainting (ablation)3s-Colorization · NTU RGB+D C-Subject (unsupervised)accuracy: 75.2 -> 77.2Improved
add coarse-fine alignment on top of masking (ablation)3s-Masked Colorization · NTU RGB+D C-Subject (unsupervised)accuracy: 77.2 -> 79.1Improved
add coarse-fine alignment to spatial stream (ablation)SS Masked Colorization · NTU RGB+D C-Subject (unsupervised) SSaccuracy: 69.6 -> 72.5Improved
add person-level colorization stream to TS+SS (ablation)TS+SS Colorization · NTU RGB+D C-Subject (unsupervised)accuracy: 74.6 -> 75.2Improved
use segment masking (15 frames) instead of random masking 0.75 (ablation)TS stream · NTU RGB+D C-Subject (unsupervised) TSaccuracy: 72.8 -> 74.0Improved
use 10-joint masking instead of random masking 0.75 (ablation)SS stream · NTU RGB+D C-Subject (unsupervised) SSaccuracy: 71.7 -> 72.8Improved
use 5-frame segments for coarse temporal colorization instead of 2 (ablation)TS stream · NTU RGB+D C-Subject (unsupervised)accuracy: 72.2 -> 73.2Improved
use 10 body parts instead of 6 for coarse spatial colorization (ablation)SS stream · NTU RGB+D C-Subject (unsupervised)accuracy: 71.3 -> 72.5Improved
add person-level colorization masking (ablation)PS stream · NTU RGB+D C-Subject (unsupervised) PSaccuracy: 64.2 -> 67.9Improved
coarse-fine masked colorization vs prior colorization3s-Colorization · Transfer NTU RGB+D to PKU-MMD IIaccuracy: 51.0 -> 58.1Improved

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