Metraipolis › archive › dc_b83de129cced
Native Association: Confidence-Aware Human Perception in the Wild with a Foundation VLM — arXiv:2609.33450
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.33450
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:51:37.705Z
- SHA-256 of the archived text
65edffd0314c756aa6ace50388b5ce01b71a05dc9f548b6f8859cb655f12a325- Stable URL of this page
https://metraipolis.com/documento/dc_b83de129cced
How to cite
Native Association: Confidence-Aware Human Perception in the Wild with a Foundation VLM — arXiv:2609.33450 — arXiv (en), https://arxiv.org/abs/2609.33450 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b83de129cced (Metraipolis archive dc_b83de129cced, sha256 65edffd0314c756aa6ace50388b5ce01b71a05dc9f548b6f8859cb655f12a325)
BibTeX
@misc{dcb83de129cced,
title = {Native Association: Confidence-Aware Human Perception in the Wild with a Foundation VLM — arXiv:2609.33450},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.33450},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b83de129cced; sha256 65edffd0314c756aa6ace50388b5ce01b71a05dc9f548b6f8859cb655f12a325},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33450. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Extracting who is where, on which team, wearing which number from a broadcast frame is typically done by stitching a detector, an OCR engine, and classifiers together -- and the stitching step swaps identities under occlusion. We make association native instead: a 0.77B vision-language model (Florence-2) is fine-tuned to emit all per-person attributes as one grammar-constrained sequence, with each attribute generated inside its owner's block. Output is therefore schema-valid on every frame by construction, and no post-hoc binding step exists to attach a correctly read number to the wrong player: residual misassociation is pure perception error, $\approx4\times$ rarer than zero-shot-prompted frontier APIs' (0.057 vs. 0.21-0.24). On a frozen multi-sport test set, this single pass reaches 0.95 detection F1 (APIs: 0.65-0.75). A single extra forward pass yields a per-field confidence that supports a reject option (jersey precision $0.71\rightarrow0.96$ at half coverage) and routes a training-free zoom-and-re-read for small players. Surprisingly, once the grammar is learned, further parameter-efficient tuning yields no measurable gain under the adaptation configurations we test; the identical recipe on WIDER-Attribute reaches 93.1 mAP given-box, yields the first detection-coupled end-to-end results under its standard test protocol (84.5 mAP), and reproduces the same tuning result. In this regime, the gains live in the structure, not in added weights. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.33450 — 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 2026-10-07T23:29:27.212Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).