LLandMark: A Multi-Agent Framework for Landmark-Aware Multimodal Interactive Video Retrieval

TL;DR

LLandMark is presented, a modular multi-agent framework for landmark-aware multimodal video retrieval to handle real-world complex queries and achieves adaptive, culturally grounded, and explainable retrieval performance.

Abstract

The increasing diversity and scale of video data demand retrieval systems capable of multimodal understanding, adaptive reasoning, and domain-specific knowledge integration. This paper presents LLandMark, a modular multi-agent framework for landmark-aware multimodal video retrieval to handle real-world complex queries. The framework features specialized agents that collaborate across four stages: query parsing and planning, landmark reasoning, multimodal retrieval, and reranked answer synthesis. A key component, the Landmark Knowledge Agent, detects cultural or spatial landmarks and reformulates them into descriptive visual prompts, enhancing CLIP-based semantic matching for Vietnamese scenes. To expand capabilities, we introduce an LLM-assisted image-to-image pipeline, where a large language model (Gemini 2.5 Flash) autonomously detects landmarks, generates image search queries, retrieves representative images, and performs CLIP-based visual similarity matching, removing the need for manual image input. In addition, an OCR refinement module leveraging Gemini and LlamaIndex improves Vietnamese text recognition. Experimental results show that LLandMark achieves adaptive, culturally grounded, and explainable retrieval performance.

Figures (7)

• Figure 1: An overview of our fundamental multi-modal video retrieval system architecture.
• Figure 4: Embedding-based search
• Figure 5: LLandMark search
• Figure 6: Embedding-based search
• Figure 7: LLM-Assisted Landmark Image-to-Image search