AI Paper Atlas

Research map / Time series / Causal and generative time series

Uncertainty-DTW for Time Series and Sequences

Lei Wang, Piotr Koniusz

ECCV 2022 · Time series › Causal and generative time series · approach: State-space and latent dynamics forecasting

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 SigmaNet-predicted uncertainty instead of a free-variable Sigma (ablation)uDTW · NTU-60 supervised (50 classes)accuracy: 68.0 -> 72.4Improved
add SigmaNet-predicted uncertainty instead of a free-variable Sigma (ablation)uDTW · NTU-60 supervised (10 classes)accuracy: 54.1 -> 56.9Improved
add SigmaNet-predicted uncertainty instead of a free-variable Sigma (ablation)uDTW · UCR nearest neighbor K=1accuracy: 77.0 -> 80.0Improved
add SigmaNet-predicted uncertainty instead of a free-variable Sigma (ablation)uDTW · UCR nearest centroidaccuracy: 70.9 -> 72.2Improved
add aleatoric uncertainty weighting to soft-DTW divergencesDTW div. · UCR nearest neighbor K=5accuracy: 80.1 -> 83.3Improved
add aleatoric uncertainty weighting to soft-DTW divergencesDTW div. · UCR nearest centroidaccuracy: 70.9 -> 72.2Improved
train forecaster with uDTW loss instead of sDTW div.MLP forecaster · ECG5000MSE: 24.6 -> 23.0Improved
train forecaster with uDTW loss instead of EuclideanMLP forecaster · ECG5000MSE: 32.1 -> 23.0Improved
add uDTW in place of sDTW div. for few-shot recognitionfew-shot AR · NTU-60 supervised (50 classes)accuracy: 69.0 -> 72.4Improved
add uDTW in place of TAPfew-shot AR · NTU-120 supervised (100 classes)accuracy: 47.3 -> 49.0Improved
add uDTW in place of sDTW div. in unsupervised few-shotfew-shot AR · Kinetics-skeleton 3D unsupervisedaccuracy: 28.9 -> 32.7Improved
derive uDTW from Laplace instead of Normal likelihood (ablation)uDTW · NTU-60 supervised (50 classes)accuracy: 72.4 -> 70.3Hurt

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