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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| replace stepwise cross-entropy with LSoftLoc | unidirectional RNN · Golf Swing Action Detection, σ = 4 | mean accuracy: 35.3 -> 50.7 | Improved |
| replace stepwise cross-entropy with LSoftLoc | LSTM · Smoking Puff Detection, σ = 4 | F1: 55.0 (19.7) -> 79.0 (6.9) | Improved |
| replace label-smoothed squared-error training with LSoftLoc | CNN-LSTM · Piano Onset Detection, σ = 200ms | F1: 28.0 -> 73.7 | Improved |
| use LSoftLoc instead of the original benchmark model | piano onset detection model · Piano Onset Detection, σ = 0ms | F1: 82.1 -> 76.0 | Hurt |
| add counting-based sparsity regularization to soft localization learning (ablation) | CNN-LSTM · Piano Onset Detection, σ = 200ms | F1: 46.91 -> 73.68 | Improved |
| add soft localization learning to counting-based sparsity regularization (ablation) | CNN-LSTM · Piano Onset Detection, σ = 200ms | F1: 67.26 -> 73.68 | Improved |
| vary the smoothing softness from 0ms to 150ms (ablation) | LSoftLoc drum detector · Drum Detection | F1 | No clear effect |
Closest papers by meaning
- Weakly-Supervised Temporal Localization via Occurrence Count Learning (ICML 2019 · similarity 0.91)
- Temporal Action Localization in the Deep Learning Era: A Survey (TPAMI 2023 · similarity 0.88)
- HR-Pro: Point-Supervised Temporal Action Localization via Hierarchical Reliability Propagation (AAAI 2024 · similarity 0.87)
- Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correction (AAAI 2025 · similarity 0.87)
- Realigning Confidence with Temporal Saliency Information for Point-Level Weakly-Supervised Temporal Action Localization (CVPR 2024 · similarity 0.86)
- Bridge the Gap: From Weak to Full Supervision for Temporal Action Localization with PseudoFormer (CVPR 2025 · similarity 0.86)
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.
