Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/STA-LSTM

STA-LSTM

Reported on 16 benchmarks across 8 tasks · 1 paper · 6 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision6 results

VideoonNTU RGB+D
Accuracy (CS)· 2016-11-18
73.4
best: 94.3 (Hulk(Finetune, ViT-L))
SOTA
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data arXiv:1611.06067
Temporal Action LocalizationonNTU RGB+D
Accuracy (CS)· 2016-11-18
73.4
best: 94.3 (Hulk(Finetune, ViT-L))
SOTA
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data arXiv:1611.06067
Action LocalizationonNTU RGB+D
Accuracy (CS)· 2016-11-18
73.4
best: 94.3 (Hulk(Finetune, ViT-L))
SOTA
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data arXiv:1611.06067
VideoonNTU RGB+D
Accuracy (CV)· 2016-11-18
81.2
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data arXiv:1611.06067
Temporal Action LocalizationonNTU RGB+D
Accuracy (CV)· 2016-11-18
81.2
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data arXiv:1611.06067
Action LocalizationonNTU RGB+D
Accuracy (CV)· 2016-11-18
81.2
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data arXiv:1611.06067

Time Series4 results

Action DetectiononNTU RGB+D
Accuracy (CS)· 2016-11-18
73.4
best: 94.3 (Hulk(Finetune, ViT-L))
SOTA
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data arXiv:1611.06067
Action DetectiononNTU RGB+D
Accuracy (CV)· 2016-11-18
81.2
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data arXiv:1611.06067
Action RecognitiononNTU RGB+D
Accuracy (CS)· 2016-11-18
73.4
best: 97.4 (DSCNet (RGB + Pose))
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data arXiv:1611.06067
Action RecognitiononNTU RGB+D
Accuracy (CV)· 2016-11-18
81.2
best: 99.6 (PoseC3D (RGB + Pose))
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data arXiv:1611.06067

Methodology2 results

Zero-Shot LearningonNTU RGB+D
Accuracy (CS)· 2016-11-18
73.4
best: 94.3 (Hulk(Finetune, ViT-L))
SOTA
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data arXiv:1611.06067
Zero-Shot LearningonNTU RGB+D
Accuracy (CV)· 2016-11-18
81.2
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data arXiv:1611.06067

Natural Language Processing2 results

3D Action RecognitiononNTU RGB+D
Accuracy (CS)· 2016-11-18
73.4
best: 94.3 (Hulk(Finetune, ViT-L))
SOTA
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data arXiv:1611.06067
3D Action RecognitiononNTU RGB+D
Accuracy (CV)· 2016-11-18
81.2
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data arXiv:1611.06067

Robots2 results

Activity RecognitiononNTU RGB+D
Accuracy (CS)· 2016-11-18
73.4
best: 97.4 (DSCNet (RGB + Pose))
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data arXiv:1611.06067
Activity RecognitiononNTU RGB+D
Accuracy (CV)· 2016-11-18
81.2
best: 99.6 (PoseC3D (RGB + Pose))
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data arXiv:1611.06067