Papers with Code · CC BY-SA 4.0

NTU RGB+D

아카이브 평가 135건 · 마지막 적재/변경 2026-10-30

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
JB-AAGCN	Accuracy (CV) 96.0 Accuracy (CS) 89.4	Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks 2019-12-15	코드 1 · 코드 2
GCN-NAS	Accuracy (CV) 95.7 Accuracy (CS) 89.4	Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching 2019-11-11	코드 1
VA-fusion (aug.)	Accuracy (CV) 95.0 Accuracy (CS) 89.4	View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition 2018-04-20	코드 1 · 코드 2
AGC-LSTM (Joint&Part)	Accuracy (CV) 95.0 Accuracy (CS) 89.2	An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition 2019-02-25	연결 없음
3s-HYSP	Accuracy (CV) 95.2 Accuracy (CS) 89.1	HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations 2023-03-10	코드 1
SLnL-rFA	Accuracy (CV) 94.9 Accuracy (CS) 89.1	Skeleton-Based Action Recognition with Synchronous Local and Non-local Spatio-temporal Learning and Frequency Attention 2018-11-10	연결 없음
SGN	Accuracy (CV) 94.5 Accuracy (CS) 89.0	Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition 2019-04-02	코드 1 · 코드 2
CoS-TR* (2-stream)	Accuracy (CV) 94.8 Accuracy (CS) 88.9 GFLOPs per pred 0.3	Continual Spatio-Temporal Graph Convolutional Networks 2022-03-21	코드 1
3SCNN	Accuracy (CV) 93.7 Accuracy (CS) 88.6	Three-Stream Convolutional Neural Network With Multi-Task and Ensemble Learning for 3D Action Recognition 2019-06-16	연결 없음
2s-NLGCN	Accuracy (CV) 95.1 Accuracy (CS) 88.5	Non-Local Graph Convolutional Networks for Skeleton-Based Action Recognition 2019-07-04	코드 1
AutoGCN	Accuracy (CV) 95.5 Accuracy (CS) 88.3	AutoGCN -- Towards Generic Human Activity Recognition with Neural Architecture Search 2024-02-02	코드 1
CoST-GCN* (2-stream)	Accuracy (CV) 95 Accuracy (CS) 88.3 GFLOPs per pred 0.32	Continual Spatio-Temporal Graph Convolutional Networks 2022-03-21	코드 1
PGCN-TCA	Accuracy (CV) 93.6 Accuracy (CS) 88.0	PGCN-TCA: Pseudo Graph Convolutional Network With Temporal and Channel-Wise Attention for Skeleton-Based Action Recognition 2020-01-06	연결 없음
GR-GCN	Accuracy (CV) 94.3 Accuracy (CS) 87.5	Optimized Skeleton-based Action Recognition via Sparsified Graph Regression 2018-11-29	연결 없음
PB-GCN	Accuracy (CV) 93.2 Accuracy (CS) 87.5	Part-based Graph Convolutional Network for Action Recognition 2018-09-13	코드 1
3s RA-GCN	Accuracy (CV) 93.6 Accuracy (CS) 87.3	Richly Activated Graph Convolutional Network for Robust Skeleton-based Action Recognition 2020-08-09	코드 1 · 코드 2 · 코드 3
TS-SAN	Accuracy (CV) 92.7 Accuracy (CS) 87.2	Self-Attention Network for Skeleton-based Human Action Recognition 2019-12-18	연결 없음
3s-USDRL (DSTE) This work	Accuracy (CV) 93.2 Accuracy (CS) 87.1	USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation 2024-12-12	코드 1
AS-GCN	Accuracy (CV) 94.2 Accuracy (CS) 86.8	Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition 2019-04-26	코드 1
RF-Action	Accuracy (CV) 91.6 Accuracy (CS) 86.8	Making the Invisible Visible: Action Recognition Through Walls and Occlusions 2019-09-20	연결 없음
Dense IndRNN	Accuracy (CV) 93.97 Accuracy (CS) 86.70	Deep Independently Recurrent Neural Network (IndRNN) 2019-10-11	코드 1
ST-GCN [Vanilla, 3D Skeleton]	Accuracy (CV) 93.2 Accuracy (CS) 86.6	Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition 2018-01-23	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11 · 코드 12 · 코드 13 · 코드 14 · 코드 15 · 코드 16 · 코드 17 · 코드 18 · 코드 19 · 코드 20 · 코드 21 · 코드 22 · 코드 23 · 코드 24
HYSP	Accuracy (CV) 93.5 Accuracy (CS) 86.5	HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations 2023-03-10	코드 1
HCN	Accuracy (CV) 91.1 Accuracy (CS) 86.5	Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation 2018-04-17	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6
CoST-GCN*	Accuracy (CV) 93.8 Accuracy (CS) 86.3 GFLOPs per pred 0.16	Continual Spatio-Temporal Graph Convolutional Networks 2022-03-21	코드 1
CoS-TR*	Accuracy (CV) 92.4 Accuracy (CS) 86.3 GFLOPs per pred 0.15	Continual Spatio-Temporal Graph Convolutional Networks 2022-03-21	코드 1
Sem-GCN	Accuracy (CV) 94.2 Accuracy (CS) 86.2	A Semantics-Guided Graph Convolutional Network for Skeleton-Based Action Recognition 2020-05-01	연결 없음
ST-GCN	Accuracy (CV) 93.4 Accuracy (CS) 86 GFLOPs per pred 16.73	Continual Spatio-Temporal Graph Convolutional Networks 2022-03-21	코드 1
CoAGCN* (2-stream)	Accuracy (CV) 93.1 Accuracy (CS) 86.0 GFLOPs per pred 0.44	Continual Spatio-Temporal Graph Convolutional Networks 2022-03-21	코드 1
3s RA-GCN	Accuracy (CV) 93.5 Accuracy (CS) 85.9	Richly Activated Graph Convolutional Network for Action Recognition with Incomplete Skeletons 2019-05-16	코드 1 · 코드 2 · 코드 3