AI Paper Atlas

Research map / Video / Action recognition

Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning

Siyuan Yang, Jun Liu, Shijian Lu, Meng Hwa Er, Alex C. Kot

ICCV 2021 · Video › Action recognition · approach: Skeleton-based action recognition · 117 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 colorization pretraining (temporal stream) vs random encoder (ablation)linear classifier · NTU RGB+D cross-subject unsupervisedaccuracy: 61.8 -> 71.6Improved
add spatial colorization stream to the temporal stream (ablation)TS colorization · NTU RGB+D cross-subject unsupervisedaccuracy: 71.6 -> 74.6Improved
add person-level stream to TS+SS (ablation)TS+SS colorization · NTU RGB+D cross-subject unsupervisedaccuracy: 74.6 -> 75.2Improved
add person-level stream to TS+SS (ablation)TS+SS colorization · NTU RGB+D cross-view unsupervisedaccuracy: 82.6 -> 83.1Improved
add colorization pretraining vs random init (ablation)encoder · NW-UCLA unsupervisedaccuracy: 78.6 -> 90.1Improved
add colorization pretraining vs random init (ablation)encoder · NTU RGB+D cross-subject supervisedaccuracy: 76.5 -> 84.2Improved
add colorization pretraining vs random init (ablation)encoder · NTU RGB+D cross-subject 1% labelsaccuracy: 27.1 -> 42.9Improved
add colorization pretraining vs random init (ablation)encoder · NW-UCLA 10% labelsaccuracy: 54.9 -> 71.3Improved
add person-level stream to TS+SS (ablation)TS+SS colorization · NTU RGB+D cross-subject supervisedaccuracy: 86.3 -> 88.0Improved
add person-level stream alone as the only colorization (ablation)PS colorization · NTU RGB+D cross-subject unsupervisedaccuracy: 61.8 -> 64.2Improved
add person-level stream to TS+SS in semi-supervised training (ablation)TS+SS colorization · NTU RGB+D cross-subject 5% labelsaccuracy: 64.7 -> 65.7Improved
colorize 50% of points (odd frames) instead of other ratio (ablation)TS colorization · NTU RGB+D cross-subject unsupervisedaccuracy: 65.7 -> 71.6Improved

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