Scholarlink

In the dynamic field of video retrieval, precise and effective search methods are crucial for managing complex datasets. We present HORUS, a novel approach based on multimodal Large Language Models (mLLMs) that advances video retrieval capabilities through two key innovations: (1) advanced multi-modal feature aggregation, integrating text-to-image search with CLIP, free-text search from captions generated by Video-LLaMA2, and visual features from Video-LLaMA to capture temporal dynamics; and (2) GPT-based query expansion, combined with an advanced filter, addresses issues with low-quality open-ended text queries and refines item searches based on type and location within a scene. This work provides cutting-edge solutions for the VBS 2025 challenge and offers valuable insights into enhancing video search techniques.

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

HORUS: Multimodal Large Language Models Framework for Video Retrieval at VBS 2025

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Tai Nguyen,
  • Vo Ngoc Minh Anh,
  • Duc Dat Pham,
  • Tran Quang Vinh,
  • Nhu Duong Thi Quynh,
  • Le Anh Tien,
  • Tan Duy Le,
  • Binh T. Nguyen

摘要

In the dynamic field of video retrieval, precise and effective search methods are crucial for managing complex datasets. We present HORUS, a novel approach based on multimodal Large Language Models (mLLMs) that advances video retrieval capabilities through two key innovations: (1) advanced multi-modal feature aggregation, integrating text-to-image search with CLIP, free-text search from captions generated by Video-LLaMA2, and visual features from Video-LLaMA to capture temporal dynamics; and (2) GPT-based query expansion, combined with an advanced filter, addresses issues with low-quality open-ended text queries and refines item searches based on type and location within a scene. This work provides cutting-edge solutions for the VBS 2025 challenge and offers valuable insights into enhancing video search techniques.