Italiano(IT) DocPC: Document-Level Visual Retrieval via Representative Page Composition

DocPC框架通过页面组合增强文档级视觉检索

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-26 06:46

研究人员开发了DocPC，一个新颖的文档级视觉检索框架，解决了以页面为中心方法的局限性。DocPC将代表性页面组合成一个单一的网格图像，显著降低了索引成本和时间。该系统实现了10.1倍的索引图像、向量和存储的减少，同时还将索引时间减少了约7.7倍。DocPC-ColQwen在新DocViRe基准测试中表现强劲，取得了44.09的NDCG@5分数，超越了现有的页面级方法。 AI

影响提高了视觉文档检索系统的效率和准确性，可能影响搜索和信息组织工具。

排序理由该集群描述了一篇在arXiv上发表的研究论文，详细介绍了一种新的文档检索技术框架。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.IR (Information Retrieval) 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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇在arXiv上发表的研究论文，详细介绍了一种新的文档检索技术框架。[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: 7 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.IR (Information Retrieval) TIER_1 Italiano(IT) · Nan Du · 2026-08-26 06:46

DocPC：通过代表性页面组合实现文档级视觉检索

Visual document retrieval has advanced by encoding page screenshots with vision-language models, bypassing OCR pipelines. However, existing methods remain page-centric, misaligned with real-world scenarios requiring complete document retrieval. A naive page-then-document aggregat…

本文如何被排名

报道来源 [1]

DocPC：通过代表性页面组合实现文档级视觉检索

相关实体

相关话题