Action Detection on J-HMDB

Metric: Video-mAP 0.5 (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Video-mAP 0.5▼	Extra Data	Paper	Date↕	Code
1	HIT	88.1	No	Holistic Interaction Transformer Network for Act...	2022-10-23	Code
2	HISAN (ResNet-101 + FPN)	86.49	No	-	-	-
3	YOWO + LFB	85.9	No	You Only Watch Once: A Unified CNN Architecture ...	2019-11-15	Code
4	YOWO	85.7	No	You Only Watch Once: A Unified CNN Architecture ...	2019-11-15	Code
5	HISAN (VGG-16)	84.02	No	-	-	-
6	MOC	80.5	No	Actions as Moving Points	2020-01-14	Code
7	Faster-RCNN + two-stream I3D conv	78.6	No	AVA: A Video Dataset of Spatio-temporally Locali...	2017-05-23	Code
8	T-CNN	76.9	No	Tube Convolutional Neural Network (T-CNN) for Ac...	2017-03-30	Code
9	Two-in-one Two Stream	74.74	No	Dance with Flow: Two-in-One Stream Action Detect...	2019-04-01	Code
10	DTS	74.3	No	Finding Action Tubes with a Sparse-to-Dense Fram...	2020-08-30	-
11	TACNet	73.4	No	TACNet: Transition-Aware Context Network for Spa...	2019-05-31	-
12	MR-TS R-CNN	73.09	No	-	-	-
13	TS R-CNN	70.6	No	-	-	-
14	Two-in-one	57.96	No	Dance with Flow: Two-in-One Stream Action Detect...	2019-04-01	Code
15	Actionnness	56.4	No	Actionness Estimation Using Hybrid Fully Convolu...	2016-04-25	-
16	Action Tubes	53.3	No	Finding Action Tubes	2014-11-21	Code

#1HITSOTA
88.1
Video-mAP 0.5· 2022-10-23
Holistic Interaction Transformer Network for Action Detection Code
#2HISAN (ResNet-101 + FPN)
86.49
Video-mAP 0.5
No paper
#3YOWO + LFBSOTA
85.9
Video-mAP 0.5· 2019-11-15
You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization Code
#4YOWO
85.7
Video-mAP 0.5· 2019-11-15
You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization Code
#5HISAN (VGG-16)
84.02
Video-mAP 0.5
No paper
#6MOC
80.5
Video-mAP 0.5· 2020-01-14
Actions as Moving Points Code
#7Faster-RCNN + two-stream I3D convSOTA
78.6
Video-mAP 0.5· 2017-05-23
AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions Code
#8T-CNNSOTA
76.9
Video-mAP 0.5· 2017-03-30
Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos Code
#9Two-in-one Two Stream
74.74
Video-mAP 0.5· 2019-04-01
Dance with Flow: Two-in-One Stream Action Detection Code
#10DTS
74.3
Video-mAP 0.5· 2020-08-30
Finding Action Tubes with a Sparse-to-Dense Framework
#11TACNet
73.4
Video-mAP 0.5· 2019-05-31
TACNet: Transition-Aware Context Network for Spatio-Temporal Action Detection
#12MR-TS R-CNN
73.09
Video-mAP 0.5
No paper
#13TS R-CNN
70.6
Video-mAP 0.5
No paper
#14Two-in-one
57.96
Video-mAP 0.5· 2019-04-01
Dance with Flow: Two-in-One Stream Action Detection Code
#15ActionnnessSOTA
56.4
Video-mAP 0.5· 2016-04-25
Actionness Estimation Using Hybrid Fully Convolutional Networks
#16Action TubesSOTA
53.3
Video-mAP 0.5· 2014-11-21
Finding Action Tubes Code