Papers with Code · CC BY-SA 4.0

NTU RGB+D 120

아카이브 평가 83건 · 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
AGCN (1-stream)	Accuracy (Cross-Subject) 79.7 Accuracy (Cross-Setup) 80.7 GFLOPS per prediction 18.69	Continual Spatio-Temporal Graph Convolutional Networks 2022-03-21	코드 1
CoST-GCN* (1-stream)	Accuracy (Cross-Subject) 79.4 Accuracy (Cross-Setup) 81.6 GFLOPS per prediction 0.16	Continual Spatio-Temporal Graph Convolutional Networks 2022-03-21	코드 1
ST-GCN (1-stream)	Accuracy (Cross-Subject) 79 GFLOPS per prediction 16.73	Continual Spatio-Temporal Graph Convolutional Networks 2022-03-21	코드 1
GVFE + AS-GCN with DH-TCN	Accuracy (Cross-Subject) 78.3% Accuracy (Cross-Setup) 79.8%	Vertex Feature Encoding and Hierarchical Temporal Modeling in a Spatial-Temporal Graph Convolutional Network for Action Recognition 2019-12-20	연결 없음
CoAGCN* (1-stream)	Accuracy (Cross-Subject) 77.3 Accuracy (Cross-Setup) 79.1 GFLOPS per prediction 0.22	Continual Spatio-Temporal Graph Convolutional Networks 2022-03-21	코드 1
Gimme Signals (Skeleton, AIS)	Accuracy (Cross-Subject) 70.8% Accuracy (Cross-Setup) 71.6%	Gimme Signals: Discriminative signal encoding for multimodal activity recognition 2020-03-13	코드 1 · 코드 2
Logsig-RNN	Accuracy (Cross-Subject) 68.3% Accuracy (Cross-Setup) 67.2%	Learning stochastic differential equations using RNN with log signature features 2019-08-22	연결 없음
TSRJI (Late Fusion) + HCN	Accuracy (Cross-Subject) 67.9% Accuracy (Cross-Setup) 62.8%	Skeleton Image Representation for 3D Action Recognition based on Tree Structure and Reference Joints 2019-09-11	코드 1
SkeleMotion + Yang et al. (2018)	Accuracy (Cross-Subject) 67.7% Accuracy (Cross-Setup) 66.9%	SkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action Recognition 2019-07-30	코드 1
TSRJI (Late Fusion)	Accuracy (Cross-Subject) 65.5% Accuracy (Cross-Setup) 59.7%	Skeleton Image Representation for 3D Action Recognition based on Tree Structure and Reference Joints 2019-09-11	코드 1
Body Pose Evolution Map	Accuracy (Cross-Subject) 64.6% Accuracy (Cross-Setup) 66.9%	Recognizing Human Actions as the Evolution of Pose Estimation Maps 2018-06-01	연결 없음
SkeleMotion [Magnitude-Orientation (TSA)]	Accuracy (Cross-Subject) 62.9% Accuracy (Cross-Setup) 63.0%	SkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action Recognition 2019-07-30	코드 1
Multi-Task CNN with RotClips	Accuracy (Cross-Subject) 62.2% Accuracy (Cross-Setup) 61.8%	Learning clip representations for skeleton-based 3d action recognition 2018-03-05	연결 없음
Two-Stream Attention LSTM	Accuracy (Cross-Subject) 61.2% Accuracy (Cross-Setup) 63.3%	Skeleton-Based Human Action Recognition with Global Context-Aware Attention LSTM Networks 2017-07-18	연결 없음
Skeleton Visualization (Single Stream)	Accuracy (Cross-Subject) 60.3% Accuracy (Cross-Setup) 63.2%	Enhanced skeleton visualization for view invariant human action recognition 2017-08-01	연결 없음
FSNet	Accuracy (Cross-Subject) 59.9% Accuracy (Cross-Setup) 62.4%	Skeleton-Based Online Action Prediction Using Scale Selection Network 2019-02-08	연결 없음
Multi-Task Learning Network	Accuracy (Cross-Subject) 58.4% Accuracy (Cross-Setup) 57.9%	A New Representation of Skeleton Sequences for 3D Action Recognition 2017-03-09	연결 없음
GCA-LSTM	Accuracy (Cross-Subject) 58.3% Accuracy (Cross-Setup) 59.2%	Global Context-Aware Attention LSTM Networks for 3D Action Recognition 2017-07-01	연결 없음
Internal Feature Fusion	Accuracy (Cross-Subject) 58.2% Accuracy (Cross-Setup) 60.9%	Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates 2017-06-26	연결 없음
Spatio-Temporal LSTM	Accuracy (Cross-Subject) 55.7% Accuracy (Cross-Setup) 57.9%	Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition 2016-07-24	연결 없음
Dynamic Skeletons	Accuracy (Cross-Subject) 50.8% Accuracy (Cross-Setup) 54.7%	Jointly learning heterogeneous features for rgb-d activity recognition 2016-12-15	연결 없음
Soft RNN	Accuracy (Cross-Subject) 36.3% Accuracy (Cross-Setup) 44.9%	Early action prediction by soft regression 2018-08-06	연결 없음
Part-Aware LSTM	Accuracy (Cross-Subject) 25.5% Accuracy (Cross-Setup) 26.3%	NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis 2016-04-11	코드 1 · 코드 2