AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Self-Supervised Learning for Semi-Supervised Temporal Action Proposal

Xiang Wang, Shiwei Zhang, Zhiwu Qing, Yuanjie Shao, Changxin Gao, Nong Sang

CVPR 2021 · Label-efficient and robust learning › Semi-supervised learning · approach: Self-training theory · 67 citations (OpenAlex)

Check 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
Use SSTAP rather than Ji et al.'s semi-supervised baselineBMN-based temporal action proposal · THUMOS14 test, 10% labelsAR@100: 37.43 -> 40.92Improved
Use SSTAP rather than the BMN baselineBMN-based temporal action proposal · ActivityNet v1.3 validation, 60% labelsAR@100: 74.42 -> 75.20Improved
Add temporal feature flip (ablation)SSTAP · THUMOS14 test, 10% labelsAR@100: 40.52 -> 40.92Improved
Add masked feature reconstruction to the variant without flip and clip-order prediction (ablation)SSTAP · THUMOS14 test, 10% labelsAR@100: 38.75 -> 39.24Improved
Add clip-order prediction to the variant without flip or reconstruction (ablation)SSTAP · THUMOS14 test, 10% labelsAR@100: 39.24 -> 40.52Improved
Add temporal feature shift to the variant without reconstruction or clip-order prediction (ablation)SSTAP · THUMOS14 test, 10% labelsAR@100: 37.57 -> 40.92Improved
Add both self-supervised tasks (ablation)SSTAP · THUMOS14 test, 60% labelsAR@100: 46.89 -> 48.02Improved
Add temporal feature flip (ablation)SSTAP · THUMOS14 test, 60% labelsAR@100: 48.00 -> 48.02No clear effect
Add clip-order prediction and masked feature reconstruction (ablation)BMN · THUMOS14 test, 10% labelsAR@100: 31.11 -> 36.13Improved
Add clip-order prediction and masked feature reconstruction (ablation)BMN · THUMOS14 test, 60% labelsAR@100: 42.11 -> 47.00Improved

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