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/VPN++ (RGB + Pose)

VPN++ (RGB + Pose)

Reported on 12 benchmarks across 8 tasks · 1 paper

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

Time Series4 results

Action DetectiononN-UCLA
Accuracy· uses extra data· 2021-05-17
93.5
best: 99.1 (DSCNet (RGB + Pose))
VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living arXiv:2105.08141
Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· uses extra data· 2021-05-17
90.7
best: 96.7 (DSCNet (RGB + Pose))
VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living arXiv:2105.08141
Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· uses extra data· 2021-05-17
92.5
best: 95.6 (DSCNet (RGB + Pose))
VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living arXiv:2105.08141
Action RecognitiononN-UCLA
Accuracy· uses extra data· 2021-05-17
93.5
best: 99.1 (DSCNet (RGB + Pose))
VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living arXiv:2105.08141

Computer Vision3 results

VideoonN-UCLA
Accuracy· uses extra data· 2021-05-17
93.5
best: 99.1 (DSCNet (RGB + Pose))
VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living arXiv:2105.08141
Temporal Action LocalizationonN-UCLA
Accuracy· uses extra data· 2021-05-17
93.5
best: 99.1 (DSCNet (RGB + Pose))
VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living arXiv:2105.08141
Action LocalizationonN-UCLA
Accuracy· uses extra data· 2021-05-17
93.5
best: 99.1 (DSCNet (RGB + Pose))
VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living arXiv:2105.08141

Robots3 results

Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· uses extra data· 2021-05-17
90.7
best: 96.7 (DSCNet (RGB + Pose))
VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living arXiv:2105.08141
Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· uses extra data· 2021-05-17
92.5
best: 95.6 (DSCNet (RGB + Pose))
VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living arXiv:2105.08141
Activity RecognitiononN-UCLA
Accuracy· uses extra data· 2021-05-17
93.5
best: 99.1 (DSCNet (RGB + Pose))
VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living arXiv:2105.08141

Methodology1 result

Zero-Shot LearningonN-UCLA
Accuracy· uses extra data· 2021-05-17
93.5
best: 99.1 (DSCNet (RGB + Pose))
VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living arXiv:2105.08141

Natural Language Processing1 result

3D Action RecognitiononN-UCLA
Accuracy· uses extra data· 2021-05-17
93.5
best: 99.1 (DSCNet (RGB + Pose))
VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living arXiv:2105.08141