研究人员开发了 FashionLens，一个利用多模态大语言模型实现多功能时尚图像检索的统一框架。该系统通过支持多样化的查询格式和搜索意图，解决了现有方法的局限性。为实现这一点，FashionLens 引入了用于任务对齐度量空间的 Proposal-Guided Spherical Query Calibrator 和 Gradient-Guided Adaptive Sampling 策略，以平衡不同任务复杂度下的优化。该框架在新 U-FIRE 基准测试中展现了最先进的性能，该基准测试整合了分散的时尚数据集。 AI
影响 该框架通过实现更细致、更多样化的时尚图像检索，有望显著改善电子商务搜索。
排序理由 该集群包含一篇详细介绍时尚图像检索新框架和基准的学术论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
A unified fashion image retrieval framework is proposed that handles diverse query formats and search intentions through multimodal large language models with adaptive calibration and sampling strategies.
arXiv:2605.22552v1 Announce Type: new Abstract: Fashion image retrieval is a cornerstone of modern e-commerce systems. A unified framework that supports diverse query formats and search intentions is highly desired in practice. However, existing approaches focus on narrow retriev…
Fashion image retrieval is a cornerstone of modern e-commerce systems. A unified framework that supports diverse query formats and search intentions is highly desired in practice. However, existing approaches focus on narrow retrieval tasks and do not fully capture such diversity…