ML Research Wiki / Benchmarks / Temporal Sentence Grounding / Charades-STA

Charades-STA

Temporal Sentence Grounding Benchmark

Performance Over Time

📊 Showing 11 results | 📏 Metric: [email protected]

Top Performing Models

Rank Model Paper [email protected] Date Code
1 DeCafNet DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos 68.79 2025-05-22 📦 zijialewislu/cvpr2025-decafnet
2 AdaFocus (Full, MViT-Charades-Pretrain-feature, MMN model) Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition 62.40 2023-11-28 -
3 AdaFocus (Full, I3D-Charades-Pretrain-feature, MMN model) Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition 56.70 2023-11-28 -
4 MMN (Full, MViT-K400-Pretrain-feature, evaluated by AdaFocus) Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding 55.20 2021-09-10 📦 mcg-nju/mmn 📦 aim3-ruc/youmakeup_challenge2022
5 AdaFocus (Weak, MViT-Charades-Pretrain-feature, CPL model) Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition 51.70 2023-11-28 -
6 AdaFocus (Semi-weak, MViT-Charades-Pretrain-feature, D3G model) Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition 50.10 2023-11-28 -
7 MMN (Full, I3D-K400-Pretrain-feature, evaluated by AdaFocus) Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding 49.40 2021-09-10 📦 mcg-nju/mmn 📦 aim3-ruc/youmakeup_challenge2022
8 AdaFocus (Weak, I3D-Charades-Pretrain-feature, CPL model) Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition 49.10 2023-11-28 -
9 AdaFocus (Semi-weak, I3D-Charades-Pretrain-feature, D3G model) Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition 46.90 2023-11-28 -
10 D3G (Semi-weak, MViT-K400-Pretrain-feature, evaluated by AdaFocus) D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance Annotation 46.00 2023-08-08 📦 solicucu/d3g

All Papers (11)

zijialewislu/cvpr2025-decafnet

Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition

2023
AdaFocus (Full, MViT-Charades-Pretrain-feature, MMN model)

Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition

2023
AdaFocus (Full, I3D-Charades-Pretrain-feature, MMN model)

Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding

2021
MMN (Full, MViT-K400-Pretrain-feature, evaluated by AdaFocus)
mcg-nju/mmn aim3-ruc/youmakeup_challenge2022

Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition

2023
AdaFocus (Weak, MViT-Charades-Pretrain-feature, CPL model)

Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition

2023
AdaFocus (Semi-weak, MViT-Charades-Pretrain-feature, D3G model)

Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding

2021
MMN (Full, I3D-K400-Pretrain-feature, evaluated by AdaFocus)
mcg-nju/mmn aim3-ruc/youmakeup_challenge2022

Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition

2023
AdaFocus (Weak, I3D-Charades-Pretrain-feature, CPL model)

Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition

2023
AdaFocus (Semi-weak, I3D-Charades-Pretrain-feature, D3G model)

D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance Annotation

2023
D3G (Semi-weak, MViT-K400-Pretrain-feature, evaluated by AdaFocus)
solicucu/d3g

D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance Annotation

2023
D3G (Semi-weak, I3D-K400-Pretrain-feature, evaluated by AdaFocus)
solicucu/d3g