Action Detection on UCF101-24

Metric: Video-mAP 0.5 (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Video-mAP 0.5▼	Extra Data	Paper	Date↕	Code
1	Stable Mean Teacher (I3D)	76.3	No	Stable Mean Teacher for Semi-supervised Video Ac...	2024-12-10	Code
2	HIT	74.3	No	Holistic Interaction Transformer Network for Act...	2022-10-23	Code
3	E2E-SSL (I3D)	72.1	No	End-to-End Semi-Supervised Learning for Video Ac...	2022-03-08	Code
4	STAR/L	71.8	Yes	End-to-End Spatio-Temporal Action Localisation w...	2023-04-24	-
5	Faster-RCNN + two-stream I3D conv	59.9	No	AVA: A Video Dataset of Spatio-temporally Locali...	2017-05-23	Code
6	DTS	54	No	Finding Action Tubes with a Sparse-to-Dense Fram...	2020-08-30	-
7	MOC	53.9	No	Actions as Moving Points	2020-01-14	Code
8	YOWO + LFB	53.1	No	You Only Watch Once: A Unified CNN Architecture ...	2019-11-15	Code
9	TACNet	52.9	No	TACNet: Transition-Aware Context Network for Spa...	2019-05-31	-
10	HISAN (ResNet-101 + FPN)	51.47	No	-	-	-
11	Two-in-one Two Stream	50.3	No	Dance with Flow: Two-in-One Stream Action Detect...	2019-04-01	Code
12	HISAN (VGG-16)	49.5	No	-	-	-
13	YOWO	48.8	No	You Only Watch Once: A Unified CNN Architecture ...	2019-11-15	Code
14	Two-in-one	48.31	No	Dance with Flow: Two-in-One Stream Action Detect...	2019-04-01	Code

#1Stable Mean Teacher (I3D)SOTA
76.3
Video-mAP 0.5· 2024-12-10
Stable Mean Teacher for Semi-supervised Video Action Detection Code
#2HITSOTA
74.3
Video-mAP 0.5· 2022-10-23
Holistic Interaction Transformer Network for Action Detection Code
#3E2E-SSL (I3D)SOTA
72.1
Video-mAP 0.5· 2022-03-08
End-to-End Semi-Supervised Learning for Video Action Detection Code
#4STAR/L
71.8
Video-mAP 0.5· Extra Data· 2023-04-24
End-to-End Spatio-Temporal Action Localisation with Video Transformers
#5Faster-RCNN + two-stream I3D convSOTA
59.9
Video-mAP 0.5· 2017-05-23
AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions Code
#6DTS
54
Video-mAP 0.5· 2020-08-30
Finding Action Tubes with a Sparse-to-Dense Framework
#7MOC
53.9
Video-mAP 0.5· 2020-01-14
Actions as Moving Points Code
#8YOWO + LFB
53.1
Video-mAP 0.5· 2019-11-15
You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization Code
#9TACNet
52.9
Video-mAP 0.5· 2019-05-31
TACNet: Transition-Aware Context Network for Spatio-Temporal Action Detection
#10HISAN (ResNet-101 + FPN)
51.47
Video-mAP 0.5
No paper
#11Two-in-one Two Stream
50.3
Video-mAP 0.5· 2019-04-01
Dance with Flow: Two-in-One Stream Action Detection Code
#12HISAN (VGG-16)
49.5
Video-mAP 0.5
No paper
#13YOWO
48.8
Video-mAP 0.5· 2019-11-15
You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization Code
#14Two-in-one
48.31
Video-mAP 0.5· 2019-04-01
Dance with Flow: Two-in-One Stream Action Detection Code