AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

TF-FACE: Time-Frequency Fusion Learning via Frequency-Domain Adaptive and Controllable Enhancement for Trajectory Prediction

Dongjian Song, Yunhao Meng, Songjun Huang, Jiayi Han

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors

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 gated frequency-domain attention (GfreAttn) encoder (ablation)TF-FACE · Argoverse 1 valBrier minFDE6Improved
add low-frequency global feature extraction (LFE, freMLP) (ablation)TF-FACE · Argoverse 1 valminFDE6Improved
add high-frequency local feature extraction (HFE) branch (ablation)TF-FACE · Argoverse 1 valminADE6Improved
add dual-branch parallel decoder (DuaD) stage (ablation)TF-FACE · Argoverse 1 valBrier minFDE6Improved
use full TF-FACE with all four modules (ablation)TF-FACE · Argoverse 1 valBrier minFDE6: 1.496 (full) vs 1.549 to 1.552 ablatedImproved
add random-seed ensembleTF-FACE · Argoverse 1 testBrier minFDE6: 1.73 -> 1.676Improved
use TF-FACE instead of FIMFIM · Argoverse 2 val (30 frames)Brier minFDE6: 1.131 -> 1.092Improved
use TF-FACE instead of QCNet on long horizonQCNet · Argoverse 2 val (60 frames)minFDE6: 1.29 -> 1.31No clear effect
use TF-FACE instead of QCNet on long horizonQCNet · Argoverse 2 val (60 frames)MR6: 0.167 -> 0.164Improved
use TF-FACE instead of HPNetHPNet · Argoverse 1 testDAC: 0.988 -> 0.9911Improved

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