Deep Fragment Embeddings for Bidirectional Image Sentence Mapping

  • 类型:arxiv
  • 标识:1406.5679
  • 链接:https://arxiv.org/abs/1406.5679
  • 主题:multimodal
  • 主分类:rag
  • 形态:method
  • 被引:982
  • 被引来源:Semantic Scholar
  • S2被引:982
  • OpenAlex被引:724
  • 影响力被引:80
  • TLDR:This work introduces a model for bidirectional retrieval of images and sentences through a deep, multi-modal embedding of visual and natural language data and introduces a structured max-margin objective that allows this model to explicitly associate fragments across modalities.
  • OpenAlex ID:W2112912048
  • OpenAlex DOI:10.48550/arxiv.1406.5679
  • DOI:10.48550/arxiv.1406.5679
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://arxiv.org/pdf/1406.5679
  • OpenAlex更新:2026-08-23
  • 待LLM分类:否
  • 标题中文:用于双向图文映射的深度片段嵌入
  • TLDR中文:本文通过深度多模态嵌入视觉与自然语言数据,提出了一种用于图文双向检索的模型,并引入结构化的最大间隔目标,使该模型能够显式地跨模态关联片段。
  • 来源文件
  • [OpenAlex discover]
  • [S2 enrich]