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
ProtoGCN	Accuracy (Cross-Subject) 90.9 Accuracy (Cross-Setup) 92.2 Ensembled Modalities 6	Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition 2024-11-28	코드 1
JMDA (based on Skeleton MixFormer)	Accuracy (Cross-Subject) 90.9 Accuracy (Cross-Setup) 91.9	Joint Mixing Data Augmentation for Skeleton-based Action Recognition 2024-10-13	코드 1
LA-GCN	Accuracy (Cross-Subject) 90.7 Accuracy (Cross-Setup) 91.8 Ensembled Modalities 6	Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition 2023-05-21	코드 1
MSA-GCN	Accuracy (Cross-Subject) 90.6 Accuracy (Cross-Setup) 92.2 Ensembled Modalities 6	MSA-GCN: Exploiting Multi-Scale Temporal Dynamics With Adaptive Graph Convolution for Skeleton-Based Action Recognition 2024-12-19	연결 없음
Shap-Mix	Accuracy (Cross-Subject) 90.4 Accuracy (Cross-Setup) 91.7 Ensembled Modalities 4	Shap-Mix: Shapley Value Guided Mixing for Long-Tailed Skeleton Based Action Recognition 2024-07-17	코드 1
MMCL	Accuracy (Cross-Subject) 90.3 Accuracy (Cross-Setup) 91.7 Ensembled Modalities 6	Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition 2024-07-22	코드 1
BlockGCN	Accuracy (Cross-Subject) 90.3 Accuracy (Cross-Setup) 91.5 Ensembled Modalities 4	BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition 2024-01-01	코드 1
TSGCNeXt	Accuracy (Cross-Subject) 90.2 Accuracy (Cross-Setup) 91.7 Ensembled Modalities 4	TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential 2023-04-23	코드 1
HD-GCN	Accuracy (Cross-Subject) 90.1 Accuracy (Cross-Setup) 91.6 Ensembled Modalities 6	Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition 2022-08-23	코드 1
MAMP	Accuracy (Cross-Subject) 90.0 Accuracy (Cross-Setup) 91.3	Masked Motion Predictors are Strong 3D Action Representation Learners 2023-08-14	코드 1
STEP-CATFormer	Accuracy (Cross-Subject) 90.0 Accuracy (Cross-Setup) 91.2 Ensembled Modalities 4	STEP CATFormer: Spatial-Temporal Effective Body-Part Cross Attention Transformer for Skeleton-based Action Recognition 2023-12-06	코드 1
Hyperformer	Accuracy (Cross-Subject) 89.9 Accuracy (Cross-Setup) 91.3 Ensembled Modalities 4	Hypergraph Transformer for Skeleton-based Action Recognition 2022-11-17	코드 1
LST	Accuracy (Cross-Subject) 89.9 Accuracy (Cross-Setup) 91.1 Ensembled Modalities 4	Generative Action Description Prompts for Skeleton-based Action Recognition 2022-08-10	코드 1 · 코드 2 · 코드 3
SkateFormer	Accuracy (Cross-Subject) 89.8 Accuracy (Cross-Setup) 91.4 Ensembled Modalities 4	SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition 2024-03-14	코드 1
InfoGCN	Accuracy (Cross-Subject) 89.8 Accuracy (Cross-Setup) 91.2 Ensembled Modalities 6	InfoGCN: Representation Learning for Human Skeleton-Based Action Recognition 2022-01-01	코드 1
Stream-GCN	Accuracy (Cross-Subject) 89.7 Accuracy (Cross-Setup) 91.0	Action Recognition with Multi-stream Motion Modeling and Mutual Information Maximization 2023-06-13	연결 없음
DG-STGCN	Accuracy (Cross-Subject) 89.6 Accuracy (Cross-Setup) 91.3 Ensembled Modalities 4	DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition 2022-10-12	코드 1 · 코드 2 · 코드 3
SkeletonGCL (based on CTR-GCN)	Accuracy (Cross-Subject) 89.5 Accuracy (Cross-Setup) 91.0 Ensembled Modalities 4	Graph Contrastive Learning for Skeleton-based Action Recognition 2023-01-26	코드 1
JPFormer	Accuracy (Cross-Subject) 89.4 Accuracy (Cross-Setup) 91.4 Ensembled Modalities 4	Joint-Partition Group Attention for skeleton-based action recognition 2024-07-30	코드 1
TCA-GCN	Accuracy (Cross-Subject) 89.4 Accuracy (Cross-Setup) 90.8 Ensembled Modalities 4	Skeleton-based Action Recognition via Temporal-Channel Aggregation 2022-05-31	코드 1
PSUMNet	Accuracy (Cross-Subject) 89.4 Accuracy (Cross-Setup) 90.6	PSUMNet: Unified Modality Part Streams are All You Need for Efficient Pose-based Action Recognition 2022-08-11	코드 1
DSTSA-GCN	Accuracy (Cross-Subject) 89.12 Accuracy (Cross-Setup) 90.97 Ensembled Modalities 4	DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling 2025-01-21	코드 1
TSGCNeXT	Accuracy (Cross-Subject) 89.1 Accuracy (Cross-Setup) 90.3 Ensembled Modalities 4	TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential 2023-04-23	코드 1
CTR-GCN	Accuracy (Cross-Subject) 88.9 Accuracy (Cross-Setup) 90.6 Ensembled Modalities 4	Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition 2021-07-26	코드 1 · 코드 2
Lit-llama	Accuracy (Cross-Subject) 88.7 Accuracy (Cross-Setup) 91.5	LLMs are Good Action Recognizers 2024-03-31	연결 없음
STGAT	Accuracy (Cross-Subject) 88.7 Accuracy (Cross-Setup) 90.4 Ensembled Modalities 4	Spatial Temporal Graph Attention Network for Skeleton-Based Action Recognition 2022-08-18	코드 1
EfficientGCN-B4	Accuracy (Cross-Subject) 88.7 Accuracy (Cross-Setup) 89.1	Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition 2021-06-29	코드 1 · 코드 2 · 코드 3 · 코드 4
ST-GCN++ [PYSKL, 3D Skeleton]	Accuracy (Cross-Subject) 88.6 Accuracy (Cross-Setup) 90.8 Ensembled Modalities 4	PYSKL: Towards Good Practices for Skeleton Action Recognition 2022-05-19	코드 1
DualHead-Net	Accuracy (Cross-Subject) 88.2 Accuracy (Cross-Setup) 89.3 Ensembled Modalities 4	Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition 2021-08-10	코드 1
AngNet-JA + BA + JBA + VJBA	Accuracy (Cross-Subject) 88.2% Accuracy (Cross-Setup) 89.2% Ensembled Modalities 4	Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition 2021-05-04	코드 1