AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Learning Precise Temporal Point Event Detection with Misaligned Labels

Julien Schroeter, Kirill Sidorov, David Marshall

AAAI 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data · 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
replace stepwise cross-entropy with LSoftLocunidirectional RNN · Golf Swing Action Detection, σ = 4mean accuracy: 35.3 -> 50.7Improved
replace stepwise cross-entropy with LSoftLocLSTM · Smoking Puff Detection, σ = 4F1: 55.0 (19.7) -> 79.0 (6.9)Improved
replace label-smoothed squared-error training with LSoftLocCNN-LSTM · Piano Onset Detection, σ = 200msF1: 28.0 -> 73.7Improved
use LSoftLoc instead of the original benchmark modelpiano onset detection model · Piano Onset Detection, σ = 0msF1: 82.1 -> 76.0Hurt
add counting-based sparsity regularization to soft localization learning (ablation)CNN-LSTM · Piano Onset Detection, σ = 200msF1: 46.91 -> 73.68Improved
add soft localization learning to counting-based sparsity regularization (ablation)CNN-LSTM · Piano Onset Detection, σ = 200msF1: 67.26 -> 73.68Improved
vary the smoothing softness from 0ms to 150ms (ablation)LSoftLoc drum detector · Drum DetectionF1No clear effect

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