Zero-Shot Learning on J-HMDB

Metric: Accuracy (pose) (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	Accuracy (pose)▼	Augmentations	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	Potion	67.9	No	-	-	-
4	EHPI	65.5	No	Simple yet efficient real-time pose-based action...	2019-04-19	Code
5	Chained (RGB+Flow +Pose)	56.8	No	Chained Multi-stream Networks Exploiting Pose, M...	2017-04-03	Code

#1HT-ConvNet
86.1
Accuracy (pose)
No paperCode
#2DD-NetSOTA
77.2
Accuracy (pose)· 2019-07-23
Make Skeleton-based Action Recognition Model Smaller, Faster and Better Code
#3Potion
67.9
Accuracy (pose)
No paper
#4EHPISOTA
65.5
Accuracy (pose)· 2019-04-19
Simple yet efficient real-time pose-based action recognition Code
#5Chained (RGB+Flow +Pose)SOTA
56.8
Accuracy (pose)· 2017-04-03
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection Code