Metraipolis › archive › dc_e5cfeb16be08
Learning to Track from Privileged Target Appearances — arXiv:2609.02471
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.02471
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T05:50:06.489Z
- SHA-256 of the archived text
b3b4ff37b80c9a8d3368b08a0b67f15a12ce885b29ebf766bb318e41b1ef371e- Stable URL of this page
https://metraipolis.com/documento/dc_e5cfeb16be08
How to cite
Learning to Track from Privileged Target Appearances — arXiv:2609.02471 — arXiv (en), https://arxiv.org/abs/2609.02471 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e5cfeb16be08 (Metraipolis archive dc_e5cfeb16be08, sha256 b3b4ff37b80c9a8d3368b08a0b67f15a12ce885b29ebf766bb318e41b1ef371e)
BibTeX
@misc{dce5cfeb16be08,
title = {Learning to Track from Privileged Target Appearances — arXiv:2609.02471},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.02471},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e5cfeb16be08; sha256 b3b4ff37b80c9a8d3368b08a0b67f15a12ce885b29ebf766bb318e41b1ef371e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02471. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 target crops, although such crops are unavailable at deployment. We introduce Privileged Appearance Transfer for Tracking (PATT), a teacher-student training framework that transfers these privileged appearances to a deployable tracker through multi-level representation prediction. The privileged teacher observes exact target crops from past, current, and future frames, whereas the student receives only past-frame templates and learns to predict the teacher's search representations. To avoid transferring unreliable teacher signals, PATT weights this transfer by the teacher's relative localization advantage over the student and its absolute localization accuracy. After training, the teacher, latent predictor, reliability weights, and privileged crops are removed, leaving standard student-only inference. Across seven benchmarks at two model scales, PATT achieves consistent gains under both long- and short-term tracking protocols. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-03 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.02471 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T05:25:58.124Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).