Metraipolis › archive › dc_159ef7fdd17b

StreamClarify: Proactive Clarification for Grounded Streaming Video Question Answering — arXiv:2611.01263

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01263
License (as archived)
CC0-1.0
Archived
2026-11-03T18:53:23.189Z
SHA-256 of the archived text
e05915c4c8c8b3595de3c937ca8b8251415adf9f5d3fe31d68cbfdca3ebd7f2f
Stable URL of this page
https://metraipolis.com/documento/dc_159ef7fdd17b

How to cite

StreamClarify: Proactive Clarification for Grounded Streaming Video Question Answering — arXiv:2611.01263 — arXiv (en), https://arxiv.org/abs/2611.01263 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_159ef7fdd17b (Metraipolis archive dc_159ef7fdd17b, sha256 e05915c4c8c8b3595de3c937ca8b8251415adf9f5d3fe31d68cbfdca3ebd7f2f)
BibTeX
@misc{dc159ef7fdd17b,
  title = {StreamClarify: Proactive Clarification for Grounded Streaming Video Question Answering — arXiv:2611.01263},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01263},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_159ef7fdd17b; sha256 e05915c4c8c8b3595de3c937ca8b8251415adf9f5d3fe31d68cbfdca3ebd7f2f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01263. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Streaming video question answering (QA) requires real-time reasoning over continuous video streams under strict latency and active-context budgets. Current streaming vision-language models (VLMs) often give confident yet ungrounded answers when queries are ambiguous or have false premises, or when relevant visual evidence is no longer in the active context. Proactive clarification can help, but must satisfy the same latency and memory constraints. We present StreamClarify, a training-free framework for grounded streaming QA that combines a pre-answer uncertainty check with hierarchical memory. The check uses the entropy of a binary pre-answer judgment as a lightweight uncertainty score to decide whether to answer directly or request clarification. To support re-answering, a temporal-pyramid KV cache maintains a bounded active visual context, while a CPU-side semantic retrieval archive provides access to historical frames. We further construct StreamClarify-QA, a diagnostic benchmark of 1,837 QA pairs from StreamBench and OVO-Bench, spanning standard, referential ambiguity, and unanswerable scenarios. Across three VLM backbones, StreamClarify improves Macro accuracy by up to 8.2 points over backbone-matched baselines. At comparable trigger rates, entropy-based selection achieves more than 18 points higher precision than random selection in identifying initially incorrect answers. Under oracle user guidance, clarification improves Macro accuracy by up to 3.5 points. We also report a controlled, oracle-assisted Qwen3-VL simulation on Ambiguous QA with generated questions and referent-only user replies, where the entropy-gated condition improves accuracy by 8.3 points.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.01263 — 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 2026-11-03T18:16:52.920Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).