← Skeleton Based Action Recognition

Papers with Code · CC BY-SA 4.0

NTU RGB+D

아카이브 평가 135건 · 마지막 적재/변경 2026-10-30

원본 데이터셋 링크 1

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
URNN-2L-T	Accuracy (CV) 83.2 Accuracy (CS) 74.6	Adaptive RNN Tree for Large-Scale Human Action Recognition 2017-10-22	연결 없음
Ensemble TS-LSTM v2	Accuracy (CV) 81.25 Accuracy (CS) 74.60	Ensemble Deep Learning for Skeleton-Based Action Recognition Using Temporal Sliding LSTM Networks 2017-10-01	코드 1
TCN	Accuracy (CV) 83.1 Accuracy (CS) 74.3	Interpretable 3D Human Action Analysis with Temporal Convolutional Networks 2017-04-14	코드 1
STA-LSTM	Accuracy (CV) 81.2 Accuracy (CS) 73.4	An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data 2016-11-18	연결 없음
TSRJI (Late Fusion) + HCN	Accuracy (CV) 80.3 Accuracy (CS) 73.3	Skeleton Image Representation for 3D Action Recognition based on Tree Structure and Reference Joints 2019-09-11	코드 1
Two-Stream RNN	Accuracy (CV) 79.5 Accuracy (CS) 71.3	Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks 2017-04-09	연결 없음
Spatio-Temporal LSTM	Accuracy (CV) 77.7 Accuracy (CS) 69.2	Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition 2016-07-24	연결 없음
Part-aware LSTM	Accuracy (CV) 70.27 Accuracy (CS) 62.93	NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis 2016-04-11	코드 1 · 코드 2
ST-LSTM	Accuracy (CV) 75.50 Accuracy (CS) 61.70	Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition 2016-07-24	연결 없음
Deep LSTM	Accuracy (CV) 67.3 Accuracy (CS) 60.7	NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis 2016-04-11	코드 1 · 코드 2
Dynamic Skeletons	Accuracy (CV) 65.2 Accuracy (CS) 60.2	Jointly learning heterogeneous features for rgb-d activity recognition 2016-12-15	연결 없음
H-RNN	Accuracy (CV) 64.0 Accuracy (CS) 59.1	Hierarchical recurrent neural network for skeleton based action recognition 2015-06-07	연결 없음
Lie Group	Accuracy (CV) 52.8 Accuracy (CS) 50.1	Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group 2014-06-23	코드 1
Skeleton Quads	Accuracy (CV) 41.4 Accuracy (CS) 38.6	Skeletal quads: Human action recognition using joint quadruples 2014-08-24	연결 없음
Five Spatial Skeleton Features	Accuracy (CV) 82.31	Investigation of Different Skeleton Features for CNN-based 3D Action Recognition 2017-05-02	코드 1