Temporal Sentence Grounding on Charades-STA

Metric: R1@0.5 (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	R1@0.5▼	Extra Data	Paper	Date↕	Code
1	DeCafNet	68.79	No	DeCafNet: Delegate and Conquer for Efficient Tem...	2025-05-22	Code
2	AdaFocus (Full, MViT-Charades-Pretrain-feature, MMN model)	62.4	No	Towards Weakly Supervised End-to-end Learning fo...	2023-11-28	-
3	AdaFocus (Full, I3D-Charades-Pretrain-feature, MMN model)	56.7	No	Towards Weakly Supervised End-to-end Learning fo...	2023-11-28	-
4	MMN (Full, MViT-K400-Pretrain-feature, evaluated by AdaFocus)	55.2	No	Negative Sample Matters: A Renaissance of Metric...	2021-09-10	Code
5	AdaFocus (Weak, MViT-Charades-Pretrain-feature, CPL model)	51.7	No	Towards Weakly Supervised End-to-end Learning fo...	2023-11-28	-
6	AdaFocus (Semi-weak, MViT-Charades-Pretrain-feature, D3G model)	50.1	No	Towards Weakly Supervised End-to-end Learning fo...	2023-11-28	-
7	MMN (Full, I3D-K400-Pretrain-feature, evaluated by AdaFocus)	49.4	No	Negative Sample Matters: A Renaissance of Metric...	2021-09-10	Code
8	AdaFocus (Weak, I3D-Charades-Pretrain-feature, CPL model)	49.1	No	Towards Weakly Supervised End-to-end Learning fo...	2023-11-28	-
9	CPL (Weak, MViT-K400-Pretrain-feature, evaluated by AdaFocus)	47.8	No	-	-	Code
10	AdaFocus (Semi-weak, I3D-Charades-Pretrain-feature, D3G model)	46.9	No	Towards Weakly Supervised End-to-end Learning fo...	2023-11-28	-
11	D3G (Semi-weak, MViT-K400-Pretrain-feature, evaluated by AdaFocus)	46	No	D3G: Exploring Gaussian Prior for Temporal Sente...	2023-08-08	Code
12	D3G (Semi-weak, I3D-K400-Pretrain-feature, evaluated by AdaFocus)	41.7	No	D3G: Exploring Gaussian Prior for Temporal Sente...	2023-08-08	Code
13	CPL (Weak, I3D-K400-Pretrain-feature, evaluated by AdaFocus)	39.6	No	-	-	Code

#1DeCafNetSOTA
68.79
R1@0.5· 2025-05-22
DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos Code
#2AdaFocus (Full, MViT-Charades-Pretrain-feature, MMN model)SOTA
62.4
R1@0.5· 2023-11-28
Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition
#3AdaFocus (Full, I3D-Charades-Pretrain-feature, MMN model)
56.7
R1@0.5· 2023-11-28
Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition
#4MMN (Full, MViT-K400-Pretrain-feature, evaluated by AdaFocus)SOTA
55.2
R1@0.5· 2021-09-10
Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding Code
#5AdaFocus (Weak, MViT-Charades-Pretrain-feature, CPL model)
51.7
R1@0.5· 2023-11-28
Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition
#6AdaFocus (Semi-weak, MViT-Charades-Pretrain-feature, D3G model)
50.1
R1@0.5· 2023-11-28
Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition
#7MMN (Full, I3D-K400-Pretrain-feature, evaluated by AdaFocus)
49.4
R1@0.5· 2021-09-10
Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding Code
#8AdaFocus (Weak, I3D-Charades-Pretrain-feature, CPL model)
49.1
R1@0.5· 2023-11-28
Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition
#9CPL (Weak, MViT-K400-Pretrain-feature, evaluated by AdaFocus)
47.8
R1@0.5
No paperCode
#10AdaFocus (Semi-weak, I3D-Charades-Pretrain-feature, D3G model)
46.9
R1@0.5· 2023-11-28
Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition
#11D3G (Semi-weak, MViT-K400-Pretrain-feature, evaluated by AdaFocus)
46
R1@0.5· 2023-08-08
D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance Annotation Code
#12D3G (Semi-weak, I3D-K400-Pretrain-feature, evaluated by AdaFocus)
41.7
R1@0.5· 2023-08-08
D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance Annotation Code
#13CPL (Weak, I3D-K400-Pretrain-feature, evaluated by AdaFocus)
39.6
R1@0.5
No paperCode