LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval

TL;DR

LLaVA-MR is a novel multimodal model that improves video moment retrieval by combining advanced encoding, frame selection, and token compression techniques, outperforming existing methods on key benchmarks.

Contribution

The paper introduces LLaVA-MR, a new framework that enhances video moment retrieval accuracy using innovative spatial-temporal encoding, frame selection, and token compression methods.

Findings

Outperforms 11 state-of-the-art methods on benchmarks.

Achieves 1.82% improvement in R1@0.5 on QVHighlights.

Achieves 1.29% improvement in mAP@0.5 on QVHighlights.

Abstract

Multimodal Large Language Models (MLLMs) are widely used for visual perception, understanding, and reasoning. However, long video processing and precise moment retrieval remain challenging due to LLMs' limited context size and coarse frame extraction. We propose the Large Language-and-Vision Assistant for Moment Retrieval (LLaVA-MR), which enables accurate moment retrieval and contextual grounding in videos using MLLMs. LLaVA-MR combines Dense Frame and Time Encoding (DFTE) for spatial-temporal feature extraction, Informative Frame Selection (IFS) for capturing brief visual and motion patterns, and Dynamic Token Compression (DTC) to manage LLM context limitations. Evaluations on benchmarks like Charades-STA and QVHighlights demonstrate that LLaVA-MR outperforms 11 state-of-the-art methods, achieving an improvement of 1.82% in R1@0.5 and 1.29% in mAP@0.5 on the QVHighlights dataset. Our implementation will be open-sourced upon acceptance.