AI Paper Atlas

Research map / Video / Action recognition

NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding

Jun Liu, Amir Shahroudy, Mauricio Pérez, Gang Wang, Ling‐Yu Duan, Alex Chichung Kot

TPAMI 2019 · Video › Action recognition · approach: Disentangled action recognition · 1,934 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 3D skeleton input instead of RGB or depth for cross-setup evaluation (ablation)action recognition baselines · NTU RGB+D 120 cross-setupaccuracy: RGB 54.8% -> skeleton 57.9%Improved
use RGB video instead of 3D skeleton for cross-subject evaluation (ablation)action recognition baselines · NTU RGB+D 120 cross-subjectaccuracy: 55.7% -> 58.5%Improved
add depth video to RGB video (ablation)RGB-only model · NTU RGB+D 120 cross-setupaccuracy: 54.8% -> 59.2%Improved
add 3D skeleton to RGB video (ablation)RGB-only model · NTU RGB+D 120 cross-setupaccuracy: 54.8% -> 63.1%Improved
fuse all three modalities (RGB + depth + skeleton) rather than skeleton only (ablation)skeleton model · NTU RGB+D 120 cross-subjectaccuracy: 55.7% -> 64.0%Improved
fuse all three modalities rather than RGB only (ablation)RGB model · NTU RGB+D 120 cross-subjectaccuracy: 58.5% -> 64.0%Improved
use RGB or depth input under camera setup changes (cross-setup vs cross-subject)VGG RGB model · NTU RGB+D 120accuracy: 58.5% -> 54.8%Hurt
increase training set from 20% to full (ablation)FSNet · NTU RGB+D 120 cross-setupaccuracy: 40.6% -> 62.4%Improved
add semantic-relevance weighted pooling (APSR) instead of average pooling (ablation)ST-LSTM feature generator · NTU RGB+D 120 one-shotaccuracy: 42.9% -> 45.3%Improved
add learned attention over joints instead of average pooling (ablation)one-shot ST-LSTM · NTU RGB+D 120 one-shotaccuracy: 42.9% -> 41.0%Hurt
add fully connected layer on ST-LSTM outputs instead of average pooling (ablation)one-shot ST-LSTM · NTU RGB+D 120 one-shotaccuracy: 42.9% -> 42.1%Hurt
increase auxiliary training set from 20 to 100 classes (ablation)APSR · NTU RGB+D 120 one-shotaccuracy: 29.1% -> 45.3%Improved

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