Guardado en:
Detalles Bibliográficos
Autores principales: Phung, Minh-Chi, Le, Thien-Bao, Tran-Thi, Cam-Tu, Nguyen-Thi, Thu-Dieu, Dao, Vu-Hung
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2603.02888
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910039230382080
author Phung, Minh-Chi
Le, Thien-Bao
Tran-Thi, Cam-Tu
Nguyen-Thi, Thu-Dieu
Dao, Vu-Hung
author_facet Phung, Minh-Chi
Le, Thien-Bao
Tran-Thi, Cam-Tu
Nguyen-Thi, Thu-Dieu
Dao, Vu-Hung
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_02888
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LLandMark: A Multi-Agent Framework for Landmark-Aware Multimodal Interactive Video Retrieval
Phung, Minh-Chi
Le, Thien-Bao
Tran-Thi, Cam-Tu
Nguyen-Thi, Thu-Dieu
Dao, Vu-Hung
Computer Vision and Pattern Recognition
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.
title LLandMark: A Multi-Agent Framework for Landmark-Aware Multimodal Interactive Video Retrieval
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.02888