AI Paper Atlas

Research map / Video / Action recognition

Masked Motion Predictors are Strong 3D Action Representation Learners

Yunyao Mao, Jiajun Deng, Wengang Zhou, Yao Fang, Wanli Ouyang, Houqiang Li

ICCV 2023 · Video › Action recognition · approach: Skeleton-based action recognition · 76 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
predict motion (temporal difference) of masked joints instead of reconstructing joint coordinates (ablation)MAMP · NTU-60 X-sub (linear eval)accuracy: 74.8 -> 84.9Improved
predict motion instead of joints (ablation)MAMP · NTU-120 X-sub (linear eval)accuracy: 72.5 -> 78.6Improved
feed motion instead of joints as input (ablation)MAMP · NTU-60 X-sub (linear eval)accuracy: 84.9 -> 75.9Hurt
use motion-aware masking instead of random masking (ablation)MAMP · NTU-60 X-sub (linear eval)accuracy: 83.7 -> 84.9Improved
use motion-aware masking instead of random masking (ablation)MAMP · NTU-120 X-sub (linear eval)accuracy: 77.3 -> 78.6Improved
add MAMP pre-training before fine-tuning vanilla transformerTransformer · NTU-60 X-sub (fine-tuned)accuracy: 83.1 -> 93.1Improved
add MAMP pre-training before fine-tuning vanilla transformerTransformer · NTU-120 X-sub (fine-tuned)accuracy: 76.8 -> 90.0Improved
add MAMP pre-training with 1% labeled dataTransformer · NTU-60 X-sub (semi-supervised, 1% labels)accuracy: 38.8 -> 66.0Improved
use MAMP instead of SkeletonMAE* for pre-training under linear evaluationTransformer · NTU-120 X-set (linear eval)accuracy: 73.5 -> 79.1Improved
MAMP versus PoseC3D in fully supervised NTU-60 X-subMAMP · NTU-60 X-sub (supervised, no ensemble)accuracy: 93.1 vs 93.7Hurt

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