AI Paper Atlas

Research map / Video / Action recognition

BSN: Boundary Sensitive Network for Temporal Action Proposal Generation

Tianwei Lin, Xu Zhao, Haisheng Su, Chongjing Wang, Ming Yang

ECCV 2018 · Video › Action recognition · approach: Fully supervised temporal action detection · 819 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 the proposal evaluation module (PEM) on top of TEM (ablation)BSN · THUMOS14 proposals (ablation)AR@50: 30.72 -> 37.46Improved
add the proposal evaluation module (PEM) on top of TEM (ablation)BSN · THUMOS14 proposals (ablation)AR@100: 40.52 -> 46.06Improved
add the proposal evaluation module (PEM) on top of TEM (ablation)BSN · THUMOS14 proposals (ablation)AR@1000: 63.04 -> 64.52Improved
build BSP feature from both boundary and center regions instead of boundary only (ablation)BSN PEM · THUMOS14 proposals (ablation)AR@50: 35.61 -> 37.46Improved
build BSP feature from both boundary and center regions instead of center only (ablation)BSN PEM · THUMOS14 proposals (ablation)AR@50: 36.80 -> 37.46Improved
build BSP feature from center region instead of boundary regions (ablation)BSN PEM · THUMOS14 proposals (ablation)AR@100: 44.86 -> 45.65Improved
use Soft-NMS instead of Greedy-NMS (ablation)BSN (2-Stream) · THUMOS14 proposalsAR@50: 35.41 -> 37.46Improved
use Soft-NMS instead of Greedy-NMS (ablation)BSN (2-Stream) · THUMOS14 proposalsAR@1000: 65.10 -> 64.52Hurt
replace two-stream features with C3D featuresBSN + Soft-NMS · THUMOS14 proposalsAR@50: 37.46 -> 29.58Hurt
train on seen classes only instead of seen+unseen, evaluate on unseen classesBSN (C3D) · ActivityNet-1.3 generalization (C3D) unseen valAR@100: 71.84 -> 71.32No clear effect
train on seen classes only instead of seen+unseen, evaluate on unseen classesBSN (C3D) · ActivityNet-1.3 generalization (C3D) unseen valAUC: 63.99 -> 63.38No clear effect
use BSN proposals instead of TURN proposals with UntrimmedNet classifierdetector · THUMOS14 detection (test)mAP@0.5: 24.5 -> 36.9Improved

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