Metraipolis › archive › dc_f773b472fda9
Grounding with Confidence: Controllable Generative Video Temporal Grounding — arXiv:2609.39883
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39883
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T14:46:29.001Z
- SHA-256 of the archived text
adc9950901a1c24c2c28cec3fc6c7072bfffae5f87f366fa5154439b14d55fa5- Stable URL of this page
https://metraipolis.com/documento/dc_f773b472fda9
How to cite
Grounding with Confidence: Controllable Generative Video Temporal Grounding — arXiv:2609.39883 — arXiv (en), https://arxiv.org/abs/2609.39883 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f773b472fda9 (Metraipolis archive dc_f773b472fda9, sha256 adc9950901a1c24c2c28cec3fc6c7072bfffae5f87f366fa5154439b14d55fa5)
BibTeX
@misc{dcf773b472fda9,
title = {Grounding with Confidence: Controllable Generative Video Temporal Grounding — arXiv:2609.39883},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39883},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f773b472fda9; sha256 adc9950901a1c24c2c28cec3fc6c7072bfffae5f87f366fa5154439b14d55fa5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39883. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Video temporal grounding supports applications such as video search, content review, and automated editing by localizing events described in natural language. Yet existing generative models typically output timestamps without explicit interval-level confidence scores to guide candidate selection. We separate candidate generation from acceptance by scoring individual intervals within the original decoding pass. A lightweight confidence head reads pooled decoder states, providing an explicit score trained for interval selection. Offline verifier scores supervise the head on fixed candidate sequences, and temporal-overlap labels adapt it to current rollouts during reinforcement learning. GT-anchored candidate-pool supervision and set-level optimization train the generator. The resulting scores support ranking, threshold-based selection, and rejection without invoking an external verifier at inference. On a fixed OMTG-Bench candidate pool, confidence raises query-macro [email protected] from 9.95% to 14.42% over generation order at a 10% global return budget, and from 26.48% to 31.12% at a 25% budget. The continuous scores let downstream applications adjust return budgets or acceptance thresholds to match their precision-recall preferences, without regenerating candidate intervals. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.39883 — 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 2026-10-07T14:19:00.819Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).