Representation Learning
Evaluation complete

UniShape

A shape-aware foundation model used as a frozen representation backbone for classification.

Method overview

A shape-aware foundation model used as a frozen representation backbone for classification.

Evaluated configurations

RF

Classifier heads are grouped on this page under their shared pretrained model. They remain separate leaderboard entries because they represent different experimental configurations.

Organization
SCUT · A*STAR · Khalifa University
Parameters
3.1M backbone
Checkpoint used
unishape_checkpoint_zeroshot.pth
Input Type
Univariate + multivariate time series
Inference
Frozen representation + fitted classifier

Reading this model's evaluation

The method catalog describes the pretrained model; leaderboard eligibility depends on the actual coverage of each experimental configuration. Catalog inclusion does not imply complete coverage of all 198 datasets.