AI Paper Atlas

Research map / Video / Action recognition

What do I Annotate Next? An Empirical Study of Active Learning for Action Localization

Fabian Caba Heilbron, Joon-Young Lee, Hailin Jin, Bernard Ghanem

ECCV 2018 · Video › Action recognition · approach: Weakly supervised temporal action localization · 43 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
replace random sampling with LAL selectionActive learner · ActivityNet-Selection active learning (150 classes)labeled data to reach 80% of final mAP: 65% -> 35%Improved
replace random sampling with MCLE selectionActive learner · ActivityNet-Selection active learning (150 classes)labeled data to reach 80% of final mAP: 65% -> 38%Improved
replace uncertainty sampling with LAL selectionActive learner · ActivityNet-Selection active learning (150 classes)labeled data to reach 80% of final mAP: 42% -> 35%Improved
replace uncertainty sampling with MCLE selectionActive learner · ActivityNet-Selection active learning (150 classes)labeled data to reach 80% of final mAP: 42% -> 38%Improved
increase sampling batch size from 1 to 64 (ablation)MCLE · ActivityNet-Selection active learning (150 classes)AULC: 0.75% -> 0.65%Hurt
increase sampling batch size to 64 (ablation)LAL · ActivityNet-Selection active learning (150 classes)AULC: drops only 0.05No clear effect
increase sampling batch size to 32 or more (ablation)Uncertainty sampling · ActivityNet-Selection active learning (150 classes)AULCHurt
inject 5% noise into oracle annotations (ablation)LAL · ActivityNet-Selection active learning (150 classes)AULCNo clear effect
train on Kinetics-Localization instead of original KineticsStage-Wise localization model · Kinetics-Localization validation setaverage mAP (%): 8.2 -> 21.3Improved
train on Kinetics-Localization instead of original KineticsEnd-to-End SSN · Kinetics-Localization validation setaverage mAP (%): 8.3 -> 22.8Improved
raise tIoU threshold from 0.1 to 0.2End-to-End SSN trained on Kinetics · Kinetics-Localization validation setmAP (%): 59.4 -> 40.1Hurt

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