atlas

Research map / Video / Action recognition

BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation

AAAI 2021 · Video › Action recognition · approach: Fully supervised temporal action detection · 107 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 bi-directional matching (BBM) (ablation)BSN++ CBG · ActivityNet-1.3 valAUC: 66.02 -> 66.43Helped
add scale-balanced sampling (SBS) (ablation)BSN++ CBG+PRB with e2e training · ActivityNet-1.3 valAUC: 67.77 -> 68.26Helped
use end-to-end joint training (ablation)BSN++ CBG+PRB without SBS · ActivityNet-1.3 valAUC: 67.34 -> 67.77Helped
add position-aware attention module (PAM) (ablation)BSN++ CBG+PRB · ActivityNet-1.3 valAUC: 67.99 -> 68.26Helped
add channel-aware attention module (CAM) (ablation)BSN++ CBG+PRB · ActivityNet-1.3 valAUC: 68.01 -> 68.26Helped
replace BSN with BSN++temporal proposal generation · ActivityNet-1.3 valAUC: 66.17% to 68.26%Helped
replace BSN with BSN++temporal proposal generation · ActivityNet-1.3 valAR@100: 74.16% to 76.52%Helped

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