MERLIN: Multimodal Embedding Refinement Via Llm-based Iterative Navigation For Text-video Retrieval-rerank Pipeline

Abstract

The rapid expansion of multimedia content has made accurately retrieving relevant videos from large collections increasingly challenging. Recent advancements in text-video retrieval have focused on cross-modal interactions, large-scale foundation model training, and probabilistic modeling, yet often neglect the crucial user perspective, leading to discrepancies between user queries and the content retrieved. To address this, we introduce MERLIN (Multimodal Embedding Refinement via LLM-based Iterative Navigation), a novel, training-free pipeline that leverages Large Language Models (LLMs) for iterative feedback learning. MERLIN refines query embeddings from a user perspective, enhancing alignment between queries and video content through a dynamic question answering process. Experimental results on datasets like MSR-VTT, MSVD, and ActivityNet demonstrate that MERLIN substantially improves Recall@1, outperforming existing systems and confirming the benefits of integrating LLMs into multi

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keyhan2024merlin

Related papers

• Verve: Versatile Retrieval For Videos Via Unified Embeddings (2026)0.00
• Context-enhanced Video Moment Retrieval With Large Language Models (2024)5.84
• Mm-embed: Universal Multimodal Retrieval With Multimodal Llms (2024)0.00
• MMMORRF: Multimodal Multilingual Modularized Reciprocal Rank Fusion (2025)2.26
• RETLLM: Training And Data-free Mllms For Multimodal Information Retrieval (2026)1.57
• Bidirectional Likelihood Estimation With Multi-modal Large Language Models For Text-video Retrieval (2025)2.76
• MARVEL: Multimodal Adaptive Reasoning-intensive Expand-rerank And Retrieval (2026)0.00
• Vidvec: Unlocking Video MLLM Embeddings For Video-text Retrieval (2026)0.00