Metraipolis › archive › dc_1bc4bb55464d

SCVIB: Editable State-Conditioned Visual Instance Binding for Multi-Turn Personalized Localization — arXiv:2608.14148

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.14148
License (as archived): CC0-1.0
Archived: 2026-10-19T04:04:26.013Z
SHA-256 of the archived text: 9ec60f73bf494ad03e69f7a88d2e00d92c281c8406667fd3527ae1e01b47dc23
Stable URL of this page: https://metraipolis.com/documento/dc_1bc4bb55464d

How to cite

SCVIB: Editable State-Conditioned Visual Instance Binding for Multi-Turn Personalized Localization — arXiv:2608.14148 — arXiv (en), https://arxiv.org/abs/2608.14148 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1bc4bb55464d (Metraipolis archive dc_1bc4bb55464d, sha256 9ec60f73bf494ad03e69f7a88d2e00d92c281c8406667fd3527ae1e01b47dc23)

BibTeX

@misc{dc1bc4bb55464d,
  title = {SCVIB: Editable State-Conditioned Visual Instance Binding for Multi-Turn Personalized Localization — arXiv:2608.14148},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14148},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1bc4bb55464d; sha256 9ec60f73bf494ad03e69f7a88d2e00d92c281c8406667fd3527ae1e01b47dc23},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14148. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Stored visual evidence can remain unchanged while its relevance to a current request changes with interaction state. To study this state-dependent source relevance, we introduce SCVIB, a controlled diagnostic benchmark for editable state-conditioned visual instance binding. SCVIB contains 1,050 manually verified support-query pairs and 1,500 multi-turn episodes across five visual domains and four target-state dependencies. Executable state semantics separate target resolution from evidence selection and query-side localization. Direct Qwen3-VL-8B inference achieves 99.53% target-resolution accuracy but 62.00% [email protected], revealing a 37.53-point resolution-localization gap; 563 of its 570 joint failures follow correct target identification. Routing comparisons and fixed-checkpoint support interventions diagnose a post-resolution evidence-utilization bottleneck: successful resolution must be coupled with relevant visual evidence and effective query-side grounding. We introduce TT-VG (Transition-Trace Visual Grounding), a state-conditioned visual grounding framework with an explicit and auditable state-to-evidence-to-grounding path. Target-State Transition Trace (TSTT) executes editable state and selects an auditable support record; Visual Evidence Grounding Adaptation (VEGA) learns support-conditioned grounding from target appearance, boxed support context, and the query. The canonical TT-VG configuration reaches 69.80% [email protected], improving over direct inference by 7.80 points at the combined evidence-utilization and grounding interface. Task adaptation improves the DINOv2 and MASA retrieval baselines to 51.47% and 55.67%, respectively, but both remain substantially below VEGA. These findings highlight state-dependent source selection and evidence utilization as consequential interfaces for interactive multimodal information fusion.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-17 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.14148 — 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 2026-10-19T03:57:57.940Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).