Activity Recognition on AVA v2.1

Metric: mAP (Val) (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	mAP (Val)▼	Extra Data	Paper	Date↕	Code
1	STAR/L	41.7	Yes	End-to-End Spatio-Temporal Action Localisation w...	2023-04-24	-
2	ACAR-Net, SlowFast R-101 (Kinetics-400 pretraining)	30	No	Actor-Context-Actor Relation Network for Spatio-...	2020-06-14	Code
3	JMRN + SlowFast-R101-NL	28.4	No	Pose And Joint-Aware Action Recognition	2020-10-16	Code
4	SlowFast++ (Kinetics-600 pretraining, NL)	28.3	No	SlowFast Networks for Video Recognition	2018-12-10	Code
5	LFB (Kinetics-400 pretraining)	27.7	No	Long-Term Feature Banks for Detailed Video Under...	2018-12-12	Code
6	I3D Tx HighRes	27.6	No	Video Action Transformer Network	2018-12-06	-
7	SlowFast (Kinetics-600 pretraining, NL)	27.3	No	SlowFast Networks for Video Recognition	2018-12-10	Code
8	SlowFast (Kinetics-600 pretraining)	26.8	No	SlowFast Networks for Video Recognition	2018-12-10	Code
9	SlowFast (Kinetics-400 pretraining)	26.3	No	SlowFast Networks for Video Recognition	2018-12-10	Code
10	I3D I3D	23.4	No	Video Action Transformer Network	2018-12-06	-
11	D3D (ResNet RPN, Kinetics-400 pretraining)	23	No	D3D: Distilled 3D Networks for Video Action Reco...	2018-12-19	Code
12	I3D w/ RPN + JFT (Kinetics-400 pretraining(	22.8	No	A Better Baseline for AVA	2018-07-26	-
13	S3D-G w/ ResNet RPN (Kinetics-400 pretraining(	22	No	AVA: A Video Dataset of Spatio-temporally Locali...	2017-05-23	Code
14	I3D w/ RPN (Kinetics-400 pretraining(	21.9	No	A Better Baseline for AVA	2018-07-26	-
15	YOWO+LFB*	19.2	No	You Only Watch Once: A Unified CNN Architecture ...	2019-11-15	Code
16	ARCN	17.4	No	Actor-Centric Relation Network	2018-07-28	Code

#1STAR/LSOTA
41.7
mAP (Val)· Extra Data· 2023-04-24
End-to-End Spatio-Temporal Action Localisation with Video Transformers
#2ACAR-Net, SlowFast R-101 (Kinetics-400 pretraining)SOTA
30
mAP (Val)· 2020-06-14
Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization Code
#3JMRN + SlowFast-R101-NL
28.4
mAP (Val)· 2020-10-16
Pose And Joint-Aware Action Recognition Code
#4SlowFast++ (Kinetics-600 pretraining, NL)SOTA
28.3
mAP (Val)· 2018-12-10
SlowFast Networks for Video Recognition Code
#5LFB (Kinetics-400 pretraining)
27.7
mAP (Val)· 2018-12-12
Long-Term Feature Banks for Detailed Video Understanding Code
#6I3D Tx HighResSOTA
27.6
mAP (Val)· 2018-12-06
Video Action Transformer Network
#7SlowFast (Kinetics-600 pretraining, NL)
27.3
mAP (Val)· 2018-12-10
SlowFast Networks for Video Recognition Code
#8SlowFast (Kinetics-600 pretraining)
26.8
mAP (Val)· 2018-12-10
SlowFast Networks for Video Recognition Code
#9SlowFast (Kinetics-400 pretraining)
26.3
mAP (Val)· 2018-12-10
SlowFast Networks for Video Recognition Code
#10I3D I3D
23.4
mAP (Val)· 2018-12-06
Video Action Transformer Network
#11D3D (ResNet RPN, Kinetics-400 pretraining)
23
mAP (Val)· 2018-12-19
D3D: Distilled 3D Networks for Video Action Recognition Code
#12I3D w/ RPN + JFT (Kinetics-400 pretraining(SOTA
22.8
mAP (Val)· 2018-07-26
A Better Baseline for AVA
#13S3D-G w/ ResNet RPN (Kinetics-400 pretraining(SOTA
22
mAP (Val)· 2017-05-23
AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions Code
#14I3D w/ RPN (Kinetics-400 pretraining(
21.9
mAP (Val)· 2018-07-26
A Better Baseline for AVA
#15YOWO+LFB*
19.2
mAP (Val)· 2019-11-15
You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization Code
#16ARCN
17.4
mAP (Val)· 2018-07-28
Actor-Centric Relation Network Code