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/DD-Net

DD-Net

Reported on 22 benchmarks across 10 tasks · 1 paper · 22 SOTA

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

Computer Vision12 results

VideoonJHMDB (2D poses only)
Average accuracy of 3 splits· 2019-07-23
77.2
best: 86.1 (HT-ConvNet)
SOTA
Make Skeleton-based Action Recognition Model Smaller, Faster and Better arXiv:1907.09658
VideoonJ-HMDB
Accuracy (pose)· 2019-07-23
77.2
best: 86.1 (HT-ConvNet)
SOTA
Make Skeleton-based Action Recognition Model Smaller, Faster and Better arXiv:1907.09658
Temporal Action LocalizationonJHMDB (2D poses only)
Average accuracy of 3 splits· 2019-07-23
77.2
best: 86.1 (HT-ConvNet)
SOTA
Make Skeleton-based Action Recognition Model Smaller, Faster and Better arXiv:1907.09658
Temporal Action LocalizationonJ-HMDB
Accuracy (pose)· 2019-07-23
77.2
best: 86.1 (HT-ConvNet)
SOTA
Make Skeleton-based Action Recognition Model Smaller, Faster and Better arXiv:1907.09658
Action LocalizationonJHMDB (2D poses only)
Average accuracy of 3 splits· 2019-07-23
77.2
best: 86.1 (HT-ConvNet)
SOTA
Make Skeleton-based Action Recognition Model Smaller, Faster and Better arXiv:1907.09658
Action LocalizationonJ-HMDB
Accuracy (pose)· 2019-07-23
77.2
best: 86.1 (HT-ConvNet)
SOTA
Make Skeleton-based Action Recognition Model Smaller, Faster and Better arXiv:1907.09658
HandonDHG-28
Accuracy· 2019-07-23
91.9
best: 93.57 (DSTSA-GCN)
SOTA
Make Skeleton-based Action Recognition Model Smaller, Faster and Better arXiv:1907.09658
HandonSHREC 2017 track on 3D Hand Gesture Recognition
14 gestures accuracy· 2019-07-23
94.6
best: 73121216 (3DCNN_VIVA_4)
SOTA
Make Skeleton-based Action Recognition Model Smaller, Faster and Better arXiv:1907.09658
HandonDHG-14
Accuracy· 2019-07-23
94.6
best: 95.83 (e2eET)
SOTA
Make Skeleton-based Action Recognition Model Smaller, Faster and Better arXiv:1907.09658
Gesture RecognitiononDHG-28
Accuracy· 2019-07-23
91.9
best: 93.57 (DSTSA-GCN)
SOTA
Make Skeleton-based Action Recognition Model Smaller, Faster and Better arXiv:1907.09658
Gesture RecognitiononSHREC 2017 track on 3D Hand Gesture Recognition
14 gestures accuracy· 2019-07-23
94.6
best: 73121216 (3DCNN_VIVA_4)
SOTA
Make Skeleton-based Action Recognition Model Smaller, Faster and Better arXiv:1907.09658
Gesture RecognitiononDHG-14
Accuracy· 2019-07-23
94.6
best: 95.83 (e2eET)
SOTA
Make Skeleton-based Action Recognition Model Smaller, Faster and Better arXiv:1907.09658

Time Series4 results

Action DetectiononJHMDB (2D poses only)
Average accuracy of 3 splits· 2019-07-23
77.2
best: 86.1 (HT-ConvNet)
SOTA
Make Skeleton-based Action Recognition Model Smaller, Faster and Better arXiv:1907.09658
Action DetectiononJ-HMDB
Accuracy (pose)· 2019-07-23
77.2
best: 86.1 (HT-ConvNet)
SOTA
Make Skeleton-based Action Recognition Model Smaller, Faster and Better arXiv:1907.09658
Action RecognitiononJHMDB (2D poses only)
Average accuracy of 3 splits· 2019-07-23
77.2
best: 86.1 (HT-ConvNet)
SOTA
Make Skeleton-based Action Recognition Model Smaller, Faster and Better arXiv:1907.09658
Action RecognitiononJ-HMDB
Accuracy (pose)· 2019-07-23
77.2
best: 86.1 (HT-ConvNet)
SOTA
Make Skeleton-based Action Recognition Model Smaller, Faster and Better arXiv:1907.09658

Methodology2 results

Zero-Shot LearningonJHMDB (2D poses only)
Average accuracy of 3 splits· 2019-07-23
77.2
best: 86.1 (HT-ConvNet)
SOTA
Make Skeleton-based Action Recognition Model Smaller, Faster and Better arXiv:1907.09658
Zero-Shot LearningonJ-HMDB
Accuracy (pose)· 2019-07-23
77.2
best: 86.1 (HT-ConvNet)
SOTA
Make Skeleton-based Action Recognition Model Smaller, Faster and Better arXiv:1907.09658

Robots2 results

Activity RecognitiononJHMDB (2D poses only)
Average accuracy of 3 splits· 2019-07-23
77.2
best: 86.1 (HT-ConvNet)
SOTA
Make Skeleton-based Action Recognition Model Smaller, Faster and Better arXiv:1907.09658
Activity RecognitiononJ-HMDB
Accuracy (pose)· 2019-07-23
77.2
best: 86.1 (HT-ConvNet)
SOTA
Make Skeleton-based Action Recognition Model Smaller, Faster and Better arXiv:1907.09658

Natural Language Processing2 results

3D Action RecognitiononJHMDB (2D poses only)
Average accuracy of 3 splits· 2019-07-23
77.2
best: 86.1 (HT-ConvNet)
SOTA
Make Skeleton-based Action Recognition Model Smaller, Faster and Better arXiv:1907.09658
3D Action RecognitiononJ-HMDB
Accuracy (pose)· 2019-07-23
77.2
best: 86.1 (HT-ConvNet)
SOTA
Make Skeleton-based Action Recognition Model Smaller, Faster and Better arXiv:1907.09658