研究人员开发了MM-slotgate，一种新颖的多模态槽编码器，旨在改进可控时尚检索。该系统将Fashion-CLIP嵌入分解为不同的属性槽，从而能够根据类别、颜色、图案和人口统计信息进行更精确的检索控制。该方法在颜色检索方面取得了显著的进步，通过学习属性特定的文本-图像门控，更有效地利用视觉证据来处理某些属性。 AI
影响 这项研究可能为时尚电子商务平台带来更直观、更有效的视觉搜索工具。
排序理由 该集群包含一篇研究论文，详细介绍了一种用于多模态槽分解以进行时尚检索的新方法。
在 arXiv cs.IR (Information Retrieval) 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
Fashion retrieval often requires satisfying multiple attributes at once, such as category, color, pattern, and demographic. Monolithic embeddings mix these signals into a single vector, making attribute-specific control difficult at retrieval time. Many existing semantic-ID metho…
Fashion retrieval often requires satisfying multiple attributes at once, such as category, color, pattern, and demographic. Monolithic embeddings mix these signals into a single vector, making attribute-specific control difficult at retrieval time. Many existing semantic-ID metho…
arXiv:2608.12570v1 Announce Type: new Abstract: Fashion retrieval often requires satisfying multiple attributes at once, such as category, color, pattern, and demographic. Monolithic embeddings mix these signals into a single vector, making attribute-specific control difficult at…