Scholarlink

We present a third version of the PraK system designed around an effective text-image and image-image search model. The system integrates sub-image search options for localized context search for CLIP and image color/texture and interfaces tailored to specific task types. A user study shows the benefits of sub-image search in homogeneous video collections. We further enhance the user experience of the PraK framework by re-designing the frontend and introducing task-specific views.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

PraK Tool V3: Enhancing Video Item Search Using Localized Text and Texture Queries

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Michael Stroh,
  • Vojtěch Kloda,
  • Benjamin Verner,
  • Zuzana Vopálková,
  • Raphael Buchmüller,
  • Bastian Jäckl,
  • Jakub Hajko,
  • Jakub Lokoč

摘要

We present a third version of the PraK system designed around an effective text-image and image-image search model. The system integrates sub-image search options for localized context search for CLIP and image color/texture and interfaces tailored to specific task types. A user study shows the benefits of sub-image search in homogeneous video collections. We further enhance the user experience of the PraK framework by re-designing the frontend and introducing task-specific views.