Context-Enhanced Video Moment Retrieval with Large Language Models
This addresses the challenge of accurately localizing moments in videos for complex queries, which is incremental as it builds on existing VMR methods by integrating LLMs.
The paper tackles the problem of aligning complex situations in Video Moment Retrieval by proposing a Large Language Model-guided approach that enhances video context representation and cross-modal alignment, achieving state-of-the-art results with improvements of up to 3.28% and 4.06% on QVHighlights and Charades-STA benchmarks.
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.