MERLIN: Multimodal Embedding Refinement via LLM-based Iterative Navigation for Text-Video Retrieval-Rerank Pipeline
Donghoon Han, Eunhwan Park, Gisang Lee, Adam J. Lee, Nojun Kwak · 2024
The rapid expansion of multimedia content has made it increasingly challenging to retrieve relevant videos from large collections accurately.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 LLMbased Iterative Navigation), a novel trainingfree 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 R@1, outperforming existing systems and confirming the benefits of integrating LLMs into multimodal retrieval systems for more responsive and context-aware multimedia retrieval 1 .