AI Paper Atlas

Research map / Time series / Foundation models for time series

A Unified Shape-Aware Foundation Model for Time Series Classification

Zhen Liu, Yucheng Wang, Boyuan Li, Junhao Zheng, Emadeldeen Eldele, Min Wu, Qianli Ma

AAAI 2026 · Time series › Foundation models for time series · approach: Time series foundation models · 7 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
pretrain on large multi-domain data before fine-tuning (ablation)UniShape · 18 UCRavg accuracy: 0.8365 -> 0.8529Improved
add shape-aware adapter (ablation)UniShape · 18 UCRavg accuracy: 0.8428 -> 0.8529Improved
use CNN instead of Transformer in adapter (ablation)UniShape · 18 UCRavg accuracy: 0.8446 -> 0.8529Improved
use CNN instead of MLP in adapter (ablation)UniShape · 18 UCRavg accuracy: 0.8431 -> 0.8529Improved
add instance-prototype contrastive loss (ablation)UniShape · 18 UCRavg accuracy: 0.8444 -> 0.8529Improved
add shape-prototype contrastive loss (ablation)UniShape · 18 UCRavg accuracy: 0.8470 -> 0.8529Improved
add both prototype losses (ablation)UniShape · 18 UCRavg accuracy: 0.8411 -> 0.8529Improved
use Transformer instead of Inception CNN as encoder (ablation)UniShape · 18 UCRavg accuracy: 0.8512 -> 0.8529No clear effect
use Transformer instead of MLP as encoder (ablation)UniShape · 18 UCRavg accuracy: 0.5651 -> 0.8529Improved
increase pretraining label ratio from 10% to 100% (ablation)UniShape · 18 UCRavg accuracy: 0.8529 -> 0.8588No clear effect
increase pretraining label ratio from 0% to 10% (ablation)UniShape · 18 UCRavg accuracy: 0.8395 -> 0.8529Improved
scale up pretraining data (UCR to ALL 1.89M) (ablation)UniShape · 18 UCRavg accuracyImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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