Temporal Action Localization on ActivityNet-1.3

Metric: mAP (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	mAP▼	Extra Data	Paper	Date↕	Code
1	RDFA-S6 (InternVideo2-6B)	42.9	No	Enhancing Temporal Action Localization: Advanced...	2024-07-18	Code
2	ActionMamba (InternVideo2-6B)	42.02	No	Video Mamba Suite: State Space Model as a Versat...	2024-03-14	Code
3	PRN+BMN (ensemble)	42	Yes	Proposal Relation Network for Temporal Action De...	2021-06-20	Code
4	AdaTAD (VideoMAEv2-giant)	41.93	No	End-to-End Temporal Action Detection with 1B Par...	2023-11-28	Code
5	InternVideo2-6B	41.2	No	InternVideo2: Scaling Foundation Models for Mult...	2024-03-22	Code
6	InternVideo2-1B	40.4	No	InternVideo2: Scaling Foundation Models for Mult...	2024-03-22	Code
7	UniMD+Sync.	39.83	No	UniMD: Towards Unifying Moment Retrieval and Tem...	2024-04-07	Code
8	PRN (CSN)	39.4	Yes	Proposal Relation Network for Temporal Action De...	2021-06-20	Code
9	InternVideo	39	Yes	InternVideo: General Video Foundation Models via...	2022-12-06	Code
10	TCANet (SlowFast R101)	37.56	No	Temporal Context Aggregation Network for Tempora...	2021-03-24	Code
11	PRN (ViViT)	37.5	No	Proposal Relation Network for Temporal Action De...	2021-06-20	Code
12	AVFusion	36.82	No	Hear Me Out: Fusional Approaches for Audio Augme...	2021-06-27	Code
13	TriDet (TSP features)	36.8	No	TriDet: Temporal Action Detection with Relative ...	2023-03-13	Code
14	TadTR (TSP features)	36.75	No	End-to-end Temporal Action Detection with Transf...	2021-06-18	Code
15	ActionFormer (TSP feautures)	36.6	No	ActionFormer: Localizing Moments of Actions with...	2022-02-16	Code
16	TAGS (I3D)	36.5	No	Proposal-Free Temporal Action Detection via Glob...	2022-07-14	Code
17	VSGN (TSP features)	35.94	No	Video Self-Stitching Graph Network for Temporal ...	2020-11-30	Code
18	TSP	35.81	No	TSP: Temporally-Sensitive Pretraining of Video E...	2020-11-23	Code
19	HCN(I3D features)	35.61	No	-	-	-
20	DCAN (TSN features)	35.39	No	DCAN: Improving Temporal Action Detection via Du...	2021-12-07	Code
21	E2E-TAD (SlowFast R50+TadTR)	35.1	No	An Empirical Study of End-to-End Temporal Action...	2022-04-06	Code
22	LoFi+G-TAD	34.96	No	-	-	-
23	BSN++	34.88	No	BSN++: Complementary Boundary Regressor with Sca...	2020-09-15	Code
24	G-TAD+BSP	34.75	No	Boundary-sensitive Pre-training for Temporal Loc...	2020-11-21	Code
25	SSTAP@100%+	34.48	No	Self-Supervised Learning for Semi-Supervised Tem...	2021-04-07	Code
26	BC-GNN	34.26	No	Boundary Content Graph Neural Network for Tempor...	2020-08-04	-
27	GCM	34.24	No	Graph Convolutional Module for Temporal Action L...	2021-12-01	-
28	G-TAD	34.09	No	G-TAD: Sub-Graph Localization for Temporal Actio...	2019-11-26	Code
29	BMN	33.85	No	BMN: Boundary-Matching Network for Temporal Acti...	2019-07-23	Code
30	SSN	32.26	No	A Pursuit of Temporal Accuracy in General Activi...	2017-03-08	Code
31	P-GCN	31.11	No	Graph Convolutional Networks for Temporal Action...	2019-09-07	Code
32	BSN	30.03	No	BSN: Boundary Sensitive Network for Temporal Act...	2018-06-08	Code
33	ASM-Loc	25.1	No	ASM-Loc: Action-aware Segment Modeling for Weakl...	2022-03-29	Code

#1RDFA-S6 (InternVideo2-6B)SOTA
42.9
mAP· 2024-07-18
Enhancing Temporal Action Localization: Advanced S6 Modeling with Recurrent Mechanism Code
#2ActionMamba (InternVideo2-6B)SOTA
42.02
mAP· 2024-03-14
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding Code
#3PRN+BMN (ensemble)SOTA
42
mAP· Extra Data· 2021-06-20
Proposal Relation Network for Temporal Action Detection Code
#4AdaTAD (VideoMAEv2-giant)
41.93
mAP· 2023-11-28
End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames Code
#5InternVideo2-6B
41.2
mAP· 2024-03-22
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding Code
#6InternVideo2-1B
40.4
mAP· 2024-03-22
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding Code
#7UniMD+Sync.
39.83
mAP· 2024-04-07
UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection Code
#8PRN (CSN)
39.4
mAP· Extra Data· 2021-06-20
Proposal Relation Network for Temporal Action Detection Code
#9InternVideo
39
mAP· Extra Data· 2022-12-06
InternVideo: General Video Foundation Models via Generative and Discriminative Learning Code
#10TCANet (SlowFast R101)SOTA
37.56
mAP· 2021-03-24
Temporal Context Aggregation Network for Temporal Action Proposal Refinement Code
#11PRN (ViViT)
37.5
mAP· 2021-06-20
Proposal Relation Network for Temporal Action Detection Code
#12AVFusion
36.82
mAP· 2021-06-27
Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization Code
#13TriDet (TSP features)
36.8
mAP· 2023-03-13
TriDet: Temporal Action Detection with Relative Boundary Modeling Code
#14TadTR (TSP features)
36.75
mAP· 2021-06-18
End-to-end Temporal Action Detection with Transformer Code
#15ActionFormer (TSP feautures)
36.6
mAP· 2022-02-16
ActionFormer: Localizing Moments of Actions with Transformers Code
#16TAGS (I3D)
36.5
mAP· 2022-07-14
Proposal-Free Temporal Action Detection via Global Segmentation Mask Learning Code
#17VSGN (TSP features)SOTA
35.94
mAP· 2020-11-30
Video Self-Stitching Graph Network for Temporal Action Localization Code
#18TSPSOTA
35.81
mAP· 2020-11-23
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks Code
#19HCN(I3D features)
35.61
mAP
No paper
#20DCAN (TSN features)
35.39
mAP· 2021-12-07
DCAN: Improving Temporal Action Detection via Dual Context Aggregation Code
#21E2E-TAD (SlowFast R50+TadTR)
35.1
mAP· 2022-04-06
An Empirical Study of End-to-End Temporal Action Detection Code
#22LoFi+G-TAD
34.96
mAP
No paper
#23BSN++SOTA
34.88
mAP· 2020-09-15
BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation Code
#24G-TAD+BSP
34.75
mAP· 2020-11-21
Boundary-sensitive Pre-training for Temporal Localization in Videos Code
#25SSTAP@100%+
34.48
mAP· 2021-04-07
Self-Supervised Learning for Semi-Supervised Temporal Action Proposal Code
#26BC-GNNSOTA
34.26
mAP· 2020-08-04
Boundary Content Graph Neural Network for Temporal Action Proposal Generation
#27GCM
34.24
mAP· 2021-12-01
Graph Convolutional Module for Temporal Action Localization in Videos
#28G-TADSOTA
34.09
mAP· 2019-11-26
G-TAD: Sub-Graph Localization for Temporal Action Detection Code
#29BMNSOTA
33.85
mAP· 2019-07-23
BMN: Boundary-Matching Network for Temporal Action Proposal Generation Code
#30SSNSOTA
32.26
mAP· 2017-03-08
A Pursuit of Temporal Accuracy in General Activity Detection Code
#31P-GCN
31.11
mAP· 2019-09-07
Graph Convolutional Networks for Temporal Action Localization Code
#32BSN
30.03
mAP· 2018-06-08
BSN: Boundary Sensitive Network for Temporal Action Proposal Generation Code
#33ASM-Loc
25.1
mAP· 2022-03-29
ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localization Code