Context-Enhanced Video Moment Retrieval With Large Language Models

Date

2025

Authors

Liu, W.
Miao, B.
Cao, J.
Zhu, X.
Ge, J.
Liu, B.
Nasim, M.
Mian, A.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Journal article

Citation

IEEE Transactions on Multimedia, 2025; 27:6296-6306

Statement of Responsibility

Weijia Liu, Bo Miao, Jiuxin Cao, Xuelin Zhu, Jiawei Ge, Bo Liu, Mehwish Nasim, Ajmal Mian

Conference Name

Abstract

Current methods for Video Moment Retrieval (VMR) struggle to align complex situations involving specific environmental details, character descriptions, and action narratives. To tackle this issue, we propose a Large Language Model-guided Moment Retrieval (LMR) approach that employs the extensive knowledge of Large Language Models (LLMs) to improve video context representation as well as cross-modal alignment, facilitating accurate localization of target moments. Specifically, LMR introduces a context enhancement technique with LLMs to generate crucial target-related context semantics. These semantics are integrated with visual features for producing discriminative video representations. Finally, a language-conditioned transformer is designed to decode free-form language queries, on the fly, using aligned video representations for moment retrieval. Extensive experiments demonstrate that LMR achieves state-of-the-art results, outperforming the nearest competitor by up to 3.28% and 4.06% on the challenging QVHighlights and Charades-STA benchmarks, respectively. More importantly, the performance gains are significantly higher for localization of complex queries.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

© 2025 IEEE. All rights reserved, including rights for text and data mining, and training of artificial intelligence and similar technologies. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information.

License

Call number

Persistent link to this record