Action Detection on J-HMDB

Metric: Video-mAP 0.2 (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	Video-mAP 0.2▼	Extra Data	Paper	Date↕	Code
1	HIT	89.7	No	Holistic Interaction Transformer Network for Act...	2022-10-23	Code
2	YOWO + LFB	88.3	No	You Only Watch Once: A Unified CNN Architecture ...	2019-11-15	Code
3	YOWO	87.8	No	You Only Watch Once: A Unified CNN Architecture ...	2019-11-15	Code
4	HISAN (ResNet-101 + FPN)	87.59	No	-	-	-
5	HISAN (VGG-16)	85.97	No	-	-	-
6	MOC	80.7	No	Actions as Moving Points	2020-01-14	Code
7	T-CNN	78.4	No	Tube Convolutional Neural Network (T-CNN) for Ac...	2017-03-30	Code
8	DTS	76.1	No	Finding Action Tubes with a Sparse-to-Dense Fram...	2020-08-30	-
9	MR-TS R-CNN	74.3	No	-	-	-
10	TACNet	74.1	No	TACNet: Transition-Aware Context Network for Spa...	2019-05-31	-
11	TS R-CNN	71.1	No	-	-	-

#1HITSOTA
89.7
Video-mAP 0.2· 2022-10-23
Holistic Interaction Transformer Network for Action Detection Code
#2YOWO + LFBSOTA
88.3
Video-mAP 0.2· 2019-11-15
You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization Code
#3YOWO
87.8
Video-mAP 0.2· 2019-11-15
You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization Code
#4HISAN (ResNet-101 + FPN)
87.59
Video-mAP 0.2
No paper
#5HISAN (VGG-16)
85.97
Video-mAP 0.2
No paper
#6MOC
80.7
Video-mAP 0.2· 2020-01-14
Actions as Moving Points Code
#7T-CNNSOTA
78.4
Video-mAP 0.2· 2017-03-30
Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos Code
#8DTS
76.1
Video-mAP 0.2· 2020-08-30
Finding Action Tubes with a Sparse-to-Dense Framework
#9MR-TS R-CNN
74.3
Video-mAP 0.2
No paper
#10TACNet
74.1
Video-mAP 0.2· 2019-05-31
TACNet: Transition-Aware Context Network for Spatio-Temporal Action Detection
#11TS R-CNN
71.1
Video-mAP 0.2
No paper