AI Paper Atlas

Research map / Time series / Foundation models for time series

Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency

Xiang Zhang, Ziyuan Zhao, Theodoros Tsiligkaridis, Marinka Zitnik

NeurIPS 2022 · Time series › Foundation models for time series · approach: Time series representation learning · 126 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 time-frequency consistency loss (ablation)TF-C · Gesture (SleepEeg → Gesture)precision: 6.1%Improved
Add time-based contrastive loss (ablation)TF-C · Gesture (SleepEeg → Gesture)precision: 7.2%Improved
Add frequency-based contrastive loss (ablation)TF-C · Gesture (SleepEeg → Gesture)precision: 6.7%Improved
Use time-frequency consistency instead of within-time consistency (ablation)TF-C · Gesture (SleepEeg → Gesture)accuracy: 5.3%Improved
Use time-frequency consistency instead of within-frequency consistency (ablation)TF-C · Gesture (SleepEeg → Gesture)accuracy: 7.2%Improved

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