SOURCE-LINKED INTELLIGENCE

Learning to Track from Privileged Target Appearances

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

Target templates define what a visual tracker searches for, yet the templates available at inference trade off localization certainty with appearance freshness: the initial ground-truth template is exact but becomes stale, whereas recent templates better reflect the current appearance but are cropped from uncertain predictions. We quantify this bottleneck with a non-deployable oracle that supplies an exact current-frame target crop, improving AUC on LaSOT by 15.2 percentage points. This gap reveals a training-only opportunity: frame-level ground truths provide exact current- and future-frame t

Read original source ↗ Open in workspace

recordType

paper

region

Global