SMART: Shot-Aware Multimodal Video Moment Retrieval with Audio-Enhanced MLLM

TL;DR

This paper introduces SMART, a multimodal video moment retrieval framework that incorporates audio cues and shot-level temporal structure, significantly improving localization accuracy in complex videos.

Contribution

SMART is the first to integrate audio-enhanced multimodal features with shot-aware token compression for precise temporal localization.

Findings

Achieves 1.61% higher R1@0.5 on Charades-STA

Gains 2.59% in R1@0.7 on Charades-STA

Outperforms state-of-the-art methods significantly

Abstract

Video Moment Retrieval is a task in video understanding that aims to localize a specific temporal segment in an untrimmed video based on a natural language query. Despite recent progress in moment retrieval from videos using both traditional techniques and Multimodal Large Language Models (MLLM), most existing methods still rely on coarse temporal understanding and a single visual modality, limiting performance on complex videos. To address this, we introduce \textit{S}hot-aware \textit{M}ultimodal \textit{A}udio-enhanced \textit{R}etrieval of \textit{T}emporal \textit{S}egments (SMART), an MLLM-based framework that integrates audio cues and leverages shot-level temporal structure. SMART enriches multimodal representations by combining audio and visual features while applying \textbf{Shot-aware Token Compression}, which selectively retains high-information tokens within each shot to reduce redundancy and preserve fine-grained temporal details. We also refine prompt design to better utilize audio-visual cues. Evaluations on Charades-STA and QVHighlights show that SMART achieves significant improvements over state-of-the-art methods, including a 1.61\% increase in R1@0.5 and 2.59\% gain in R1@0.7 on Charades-STA.