English(EN) Cascaded Retrieval with Cross-Modal Query Refinement for Efficient Visual Document Search

新的SCOUT框架大幅缩短视觉文档搜索时间

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-15 04:00

研究人员开发了SCOUT，一个新颖的级联检索框架，旨在提高搜索视觉丰富文档的效率。该系统采用双轨方法，利用一个轻量级检索器进行初始语料库过滤，然后在一个较小的候选池上进行更强的重排序。同时，一个语义轨道处理离线摘要以补充视觉匹配。该框架通过跨模态查询细化融合这些信号，将查询时间延迟显著提高了高达80.7倍，同时也提高了检索性能。 AI

影响该框架可以显著加快从复杂的视觉文档中检索信息的速度，使研究人员和任何处理大型、数据丰富的文本的人受益。

排序理由这是一篇描述信息检索新技术的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇描述信息检索新技术的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Diana Turmakhan, Aseem Srivastava, Vivek Gupta, Iryna Gurevych, Thamar Solorio · 2026-10-15 04:00

跨模态查询精炼级联检索用于高效视觉文档搜索

arXiv:2610.20367v1 Announce Type: new Abstract: Retrieving information from visually rich documents requires matching queries against pages that contain complex evidence in tables, figures, and layout-dependent structures. Current vision-language retrievers address this but incur…

本文如何被排名

报道来源 [1]

跨模态查询精炼级联检索用于高效视觉文档搜索

相关实体

相关话题