English(EN) Resolving Ambiguity in Composed Image Retrieval via Calibrated Interaction

新框架通过澄清性问题解决图像检索中的歧义

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-26 04:00

研究人员推出了一种新的组合图像检索（CIR）框架，以解决查询中固有的歧义。与假设单个目标图像的先前系统不同，该方法将 CIR 重构为不确定性下的校准意图解析。它使用一致性预测来提供具有覆盖保证的候选集，并在歧义较高时，提出信息量最大的澄清性问题以缩小选项范围。 AI

影响引入了一种新颖的图像检索方法，有望提高复杂搜索任务中的用户交互和准确性。

排序理由该集群包含一篇详细介绍图像检索新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

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; 该集群包含一篇详细介绍图像检索新方法的论文。[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, other; 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: 127 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。

arXiv cs.CV TIER_1 English(EN) · Amsisan Tran, Baogh Le, Tuan Kiet Pham, Sui Yang Guang · 2026-05-26 04:00

通过校准交互解决组合图像检索中的歧义

arXiv:2605.24634v1 Announce Type: new Abstract: Composed image retrieval (CIR) searches a corpus with a reference image and a text describing how to modify it. Despite rapid progress from triplet-trained compositors to zero-shot and generative methods, essentially all systems sha…