AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Weakly-Supervised Temporal Localization via Occurrence Count Learning

Julien Schroeter, Kirill Sidorov, David Marshall

ICML 2019 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 5 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
Train with occurrence counts instead of localization labelsLoCo drum transcription · D-DTD Eval RandomF1: 97.5 -> 94.5Hurt
Train with occurrence counts instead of localization labelsLoCo drum transcription · D-DTD Eval SubsetF1: 92.8 -> 87.1Hurt
Train with occurrence counts instead of localization labelsLoCo drum transcription · D-DTP Eval RandomF1: 90.0 -> 88.9Hurt
Train with occurrence counts instead of localization labelsLoCo drum transcription · D-DTP Eval SubsetF1: 79.4 -> 78.1Hurt
Train using occurrence counts instead of onset labelsLoCo piano onset detection · MAPSF1: 82.29 -> 71.99Hurt
Train with counts for weakly supervised digit localizationLoCo digit detection · MNIST synthetic digit imagessingle digit recognition accuracy: 98.51% -> 99.12%Improved
Tighten the event matching toleranceLoCo drum transcription · D-DTD Eval Random, hi-hatsF1: 97.1% -> 96.3%Hurt

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