← Skeleton Based Action Recognition
Papers with Code · CC BY-SA 4.0

NTU RGB+D 120

아카이브 평가 83건 · 마지막 적재/변경

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
모델원본 지표·값논문구현
EfficientGCN-B2
Accuracy (Cross-Subject)
87.9
Accuracy (Cross-Setup)
88.0
Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition
2021-06-29
코드 1 · 코드 2 · 코드 3 · 코드 4
Skeletal GNN
Accuracy (Cross-Subject)
87.5
Accuracy (Cross-Setup)
89.2
Ensembled Modalities
4
Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation
2021-08-16
연결 없음
MaskCLR
Accuracy (Cross-Subject)
87.4
Accuracy (Cross-Setup)
89.5
MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning
2024-01-01
연결 없음
MSSTNet
Accuracy (Cross-Subject)
87.4
Accuracy (Cross-Setup)
88.3
Multi-scale spatial–temporal convolutional neural network for skeleton-based action recognition
2023-05-12
코드 1
PA-ResGCN-B19
Accuracy (Cross-Subject)
87.3
Accuracy (Cross-Setup)
88.3
Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition
2020-10-20
코드 1
Ensemble-top5 (MS-G3D Net + 4s Shift-GCN + VA-CNN (ResNeXt101) + 2s SDGCN + GCN-NAS (retrained))
Accuracy (Cross-Subject)
87.22%
Accuracy (Cross-Setup)
88.8%
Quo Vadis, Skeleton Action Recognition ?
2020-07-04
코드 1
PoseC3D (w. HRNet 2D Skeleton)
Accuracy (Cross-Subject)
86.9
Accuracy (Cross-Setup)
90.3
Revisiting Skeleton-based Action Recognition
2021-04-28
코드 1 · 코드 2 · 코드 3 · 코드 4
MS-G3D Net
Accuracy (Cross-Subject)
86.9%
Accuracy (Cross-Setup)
88.4%
Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition
2020-03-31
코드 1 · 코드 2 · 코드 3
DSTA-Net
Accuracy (Cross-Subject)
86.6%
Accuracy (Cross-Setup)
89.0 %
Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action Recognition
2020-07-07
코드 1
VPN
Accuracy (Cross-Subject)
86.3
Accuracy (Cross-Setup)
87.8
VPN: Learning Video-Pose Embedding for Activities of Daily Living
2020-07-06
코드 1
ST-GCN [PYSKL, 3D Skeleton]
Accuracy (Cross-Subject)
86.2
Accuracy (Cross-Setup)
88.4
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
4s Shift-GCN
Accuracy (Cross-Subject)
85.9%
Accuracy (Cross-Setup)
87.6%
Ensembled Modalities
4
Skeleton-Based Action Recognition With Shift Graph Convolutional Network
2020-06-01
코드 1
EfficientGCN-B0
Accuracy (Cross-Subject)
85.9
Accuracy (Cross-Setup)
84.3
Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition
2021-06-29
코드 1 · 코드 2 · 코드 3 · 코드 4
FGCN
Accuracy (Cross-Subject)
85.4%
Accuracy (Cross-Setup)
87.4%
Feedback Graph Convolutional Network for Skeleton-based Action Recognition
2020-03-17
연결 없음
VA-CNN (ResNeXt-101)
Accuracy (Cross-Subject)
84.88
Accuracy (Cross-Setup)
86.90
연결 없음
논문 날짜 미기재
연결 없음
S-TR (2-stream)
Accuracy (Cross-Subject)
84.8
Accuracy (Cross-Setup)
86.2
GFLOPS per prediction
32.4
Continual Spatio-Temporal Graph Convolutional Networks
2022-03-21
코드 1
CoS-TR* (2-stream)
Accuracy (Cross-Subject)
84.8
Accuracy (Cross-Setup)
86.1
GFLOPS per prediction
0.3
Continual Spatio-Temporal Graph Convolutional Networks
2022-03-21
코드 1
ST-GCN [PYSKL, 2D Skeleton]
Accuracy (Cross-Subject)
84.7
Accuracy (Cross-Setup)
89.0
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
3s-HYSP
Accuracy (Cross-Subject)
84.5
Accuracy (Cross-Setup)
86.3
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations
2023-03-10
코드 1
CoST-GCN* (2-stream)
Accuracy (Cross-Subject)
84.0
Accuracy (Cross-Setup)
85.5
GFLOPS per prediction
0.32
Continual Spatio-Temporal Graph Convolutional Networks
2022-03-21
코드 1
AGCN (2-stream)
Accuracy (Cross-Subject)
84
Accuracy (Cross-Setup)
85.4
GFLOPS per prediction
37.38
Continual Spatio-Temporal Graph Convolutional Networks
2022-03-21
코드 1
ST-GCN (2-stream)
Accuracy (Cross-Subject)
83.7
Accuracy (Cross-Setup)
85.1
GFLOPS per prediction
33.46
Continual Spatio-Temporal Graph Convolutional Networks
2022-03-21
코드 1
ST-TR-agcn
Accuracy (Cross-Subject)
82.7%
Accuracy (Cross-Setup)
84.7%
Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks
2020-08-17
코드 1
HYSP
Accuracy (Cross-Subject)
81.4
Accuracy (Cross-Setup)
82
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations
2023-03-10
코드 1
3s RA-GCN
Accuracy (Cross-Subject)
81.1%
Accuracy (Cross-Setup)
82.7%
Richly Activated Graph Convolutional Network for Robust Skeleton-based Action Recognition
2020-08-09
코드 1 · 코드 2 · 코드 3
3s-USDRL (DSTE) This work
Accuracy (Cross-Subject)
80.6
Accuracy (Cross-Setup)
79.3
USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation
2024-12-12
코드 1
Mix-Dimension
Accuracy (Cross-Subject)
80.5%
Accuracy (Cross-Setup)
83.2%
Mix Dimension in Poincaré Geometry for 3D Skeleton-based Action Recognition
2020-07-30
연결 없음
CoAGCN* (2-stream)
Accuracy (Cross-Subject)
80.4
Accuracy (Cross-Setup)
82
GFLOPS per prediction
0.44
Continual Spatio-Temporal Graph Convolutional Networks
2022-03-21
코드 1
S-TR (1-stream)
Accuracy (Cross-Subject)
80.2
Accuracy (Cross-Setup)
81.8
GFLOPS per prediction
16.2
Continual Spatio-Temporal Graph Convolutional Networks
2022-03-21
코드 1
CoS-TR* (1-stream)
Accuracy (Cross-Subject)
79.7
Accuracy (Cross-Setup)
81.7
GFLOPS per prediction
0.15
Continual Spatio-Temporal Graph Convolutional Networks
2022-03-21
코드 1