Scholarlink

This paper describes VERGE, an interactive system for retrieving video content, supporting searches over images extracted from videos. The system retains its core retrieval modalities and fusion techniques in an improved form, while introducing new modalities, including optical character recognition, video question answering, underwater object detection, image quality-based retrieval, and surgical scenes understanding. VERGE’s web application continues to offer its user-friendly interface, helping users create queries and efficiently explore the top search results. The system now incorporates newly extracted keyframes for the V3C dataset, generated with a new algorithm developed for this purpose.

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

VERGE in VBS 2026

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Nick Pantelidis,
  • Eleni Kosmidou,
  • Damianos Galanopoulos,
  • Dimitris Georgalis,
  • Stefanos Pasios,
  • Konstantinos Apostolidis,
  • Andreas Goulas,
  • Maria Pegia,
  • Georgios Tsionkis,
  • Konstantinos Gkountakos,
  • Grigorios Kouvrakis,
  • Anastasia Moumtzidou,
  • Ilias Gialampoukidis,
  • Stefanos Vrochidis,
  • Vasileios Mezaris,
  • Ioannis Kompatsiaris

摘要

This paper describes VERGE, an interactive system for retrieving video content, supporting searches over images extracted from videos. The system retains its core retrieval modalities and fusion techniques in an improved form, while introducing new modalities, including optical character recognition, video question answering, underwater object detection, image quality-based retrieval, and surgical scenes understanding. VERGE’s web application continues to offer its user-friendly interface, helping users create queries and efficiently explore the top search results. The system now incorporates newly extracted keyframes for the V3C dataset, generated with a new algorithm developed for this purpose.