MERLIN: Multimodal Embedding Refinement via LLM-based Iterative Navigation for Text-Video Retrieval-Rerank Pipeline

Donghoon Han, Eunhwan Park, Gisang Lee, Adam Lee, Nojun Kwak


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 multimodal retrieval systems for more responsive and context-aware multimedia retrieval.
Anthology ID:
2024.emnlp-industry.41
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track
Month:
November
Year:
2024
Address:
Miami, Florida, US
Editors:
Franck Dernoncourt, Daniel Preoţiuc-Pietro, Anastasia Shimorina
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
547–562
Language:
URL:
https://aclanthology.org/2024.emnlp-industry.41
DOI:
Bibkey:
Cite (ACL):
Donghoon Han, Eunhwan Park, Gisang Lee, Adam Lee, and Nojun Kwak. 2024. MERLIN: Multimodal Embedding Refinement via LLM-based Iterative Navigation for Text-Video Retrieval-Rerank Pipeline. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 547–562, Miami, Florida, US. Association for Computational Linguistics.
Cite (Informal):
MERLIN: Multimodal Embedding Refinement via LLM-based Iterative Navigation for Text-Video Retrieval-Rerank Pipeline (Han et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-industry.41.pdf