TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

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

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

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

SotA/Methodology/Zero-Shot Learning/JHMDB (2D poses only)

Zero-Shot Learning on JHMDB (2D poses only)

Metric: Average accuracy of 3 splits (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕Average accuracy of 3 splits▼AugmentationsPaperDate↕Code
1HT-ConvNet86.1No--Code
2DD-Net77.2NoMake Skeleton-based Action Recognition Model Sma...2019-07-23Code
3JMRN (No GT pose)68.55NoPose And Joint-Aware Action Recognition2020-10-16Code
4PoTion67.9No---
5EHPI65.5NoSimple yet efficient real-time pose-based action...2019-04-19Code
6Chained56.8NoChained Multi-stream Networks Exploiting Pose, M...2017-04-03Code