Video on JHMDB (2D poses only)

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

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	Average accuracy of 3 splits▼	Extra Data	Paper	Date↕	Code
1	HT-ConvNet	86.1	No	-	-	Code
2	DD-Net	77.2	No	Make Skeleton-based Action Recognition Model Sma...	2019-07-23	Code
3	JMRN (No GT pose)	68.55	No	Pose And Joint-Aware Action Recognition	2020-10-16	Code
4	PoTion	67.9	No	-	-	-
5	EHPI	65.5	No	Simple yet efficient real-time pose-based action...	2019-04-19	Code
6	Chained	56.8	No	Chained Multi-stream Networks Exploiting Pose, M...	2017-04-03	Code

#1HT-ConvNet
86.1
Average accuracy of 3 splits
No paperCode
#2DD-NetSOTA
77.2
Average accuracy of 3 splits· 2019-07-23
Make Skeleton-based Action Recognition Model Smaller, Faster and Better Code
#3JMRN (No GT pose)
68.55
Average accuracy of 3 splits· 2020-10-16
Pose And Joint-Aware Action Recognition Code
#4PoTion
67.9
Average accuracy of 3 splits
No paper
#5EHPISOTA
65.5
Average accuracy of 3 splits· 2019-04-19
Simple yet efficient real-time pose-based action recognition Code
#6ChainedSOTA
56.8
Average accuracy of 3 splits· 2017-04-03
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection Code