AI Paper Atlas

Research map / Video / Action recognition

Temporal Action Detection With Multi-Level Supervision

Baifeng Shi, Qi Dai, Judy Hoffman, Kate Saenko, Trevor Darrell, Huijuan Xu

ICCV 2021 · Video › Action recognition · approach: Temporal action segmentation · 16 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add unsupervised foreground attention (UFA) (ablation)Mean Teacher SSAD · THUMOS14 (50% labeled)mAP@0.5: 24.62 -> 25.43Improved
add unsupervised foreground attention (UFA) (ablation)MixMatch SSAD · THUMOS14 (50% labeled)mAP@0.5: 24.79 -> 26.18 (mAP@0.7 6.60 -> 7.10)Improved
add unsupervised foreground attention (UFA) (ablation)FixMatch SSAD · THUMOS14 (50% labeled)mAP@0.5: 23.58 -> 24.68Improved
add unsupervised foreground attention (UFA) (ablation)Mean Teacher SSAD · ActivityNet1.2 (10% labeled)mAP@AVG: 11.49 -> 11.74Improved
add unsupervised foreground attention (UFA) (ablation)MixMatch SSAD · ActivityNet1.2 (10% labeled)mAP@AVG: 11.05 -> 11.84Improved
add unsupervised foreground attention (UFA) (ablation)FixMatch SSAD · ActivityNet1.2 (10% labeled)mAP@AVG: 11.88 -> 12.27Improved
use Gaussian or CIS attention instead of no attention (ablation)MixMatch SSAD · THUMOS14 (50% labeled)mAP@0.5: 24.79 -> 24.59 (Gaussian); 24.79 -> 25.01 (CIS)No clear effect
add FixMatch semi-supervision without UFAsupervised-only SSN · THUMOS14 (50% labeled)mAP@0.5: 24.74 -> 23.58Hurt
add weakly-labeled data with video-level loss (OSAD)SSAD · THUMOS14 (10/20/70)mAP@0.5: 8.96 -> 11.37Improved
add information bottleneck (IB) (ablation)OSAD · THUMOS14 (10/20/70)mAP@0.5: 11.37 -> 12.97Improved
add weakly-labeled data with video-level loss (OSAD)SSAD · ActivityNet1.2 (10/20/70)mAP@AVG: 11.84 -> 11.78No clear effect
add information bottleneck (IB) (ablation)OSAD · ActivityNet1.2 (10/20/70)mAP@AVG: 11.78 -> 12.30Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy