AI Paper Atlas

Research map / Video / Action recognition

Proposal Score Realignment Guided by Semantic Completeness for Weakly Supervised Temporal Action Localization

Maodong Li, Zhihao Wang, Jingxiong Wang, Jian Wang, Bing Li

ECCV 2026 · Video › Action recognition · approach: Weakly supervised temporal action localization · 0 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 semantic-completeness loss L_SC to MIL loss (ablation)DDG-Net + SCLR · THUMOS14 testavg mAP@0.1:0.7: 47.0 -> 48.6Improved
add generic-center loss L_G (ablation)MIL+SC · THUMOS14 testavg mAP@0.1:0.7: 48.6 -> 49.5Improved
add specific-center loss L_S alone (ablation)MIL+SC · THUMOS14 testavg mAP@0.1:0.7: 48.6 -> 48.6No clear effect
add decorrelation loss L_perp to L_G+L_S (ablation)SCLR · THUMOS14 testavg mAP@0.1:0.7: 49.4 -> 50.4Improved
add SCLR realignment for pseudo-label training (ablation)localization head · THUMOS14 testavg mAP@0.1:0.7: 49.1 -> 53.2Improved
use SCLR alone over baseline (ablation)DDG-Net · THUMOS14 testavg mAP@0.1:0.7: 47.3 -> 50.4Improved
add phi_S(CSE) specific component (ablation)class-center reconstruction · THUMOS14 testavg mAP@0.1:0.7: 48.7 -> 50.4Improved
add EMA on generic component (ablation)class-center reconstruction · THUMOS14 testavg mAP@0.1:0.7: 49.7 -> 50.4Improved
add balancing coefficient delta (ablation)class-center reconstruction · THUMOS14 testavg mAP@0.1:0.7: 49.7 -> 50.4Improved
use discrete argmax(J) anchor instead of Soft-argmax(J) (ablation)SCLR · THUMOS14 testavg mAP@0.1:0.7: 49.0 -> 50.4Improved
use joint anchor instead of Top-A (ablation)SCLR · THUMOS14 testavg mAP@0.1:0.7: 47.9 -> 50.4Improved
add k_cen and k_time cues in fusion weights (ablation)SCLR · THUMOS14 testavg mAP@0.1:0.7: 49.2 -> 50.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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