Background-aware Moment Detection for Video Moment Retrieval

TL;DR

This paper introduces BM-DETR, a background-aware transformer model for video moment retrieval that improves alignment accuracy by leveraging negative queries and background information, demonstrating superior results on multiple benchmarks.

Contribution

We propose a novel contrastive transformer model that effectively utilizes background context and negative queries to enhance video moment retrieval accuracy.

Findings

Outperforms existing methods on four benchmarks.

Improves moment sensitivity and alignment accuracy.

Effectively leverages background information and negative queries.

Abstract

Video moment retrieval (VMR) identifies a specific moment in an untrimmed video for a given natural language query. This task is prone to suffer the weak alignment problem innate in video datasets. Due to the ambiguity, a query does not fully cover the relevant details of the corresponding moment, or the moment may contain misaligned and irrelevant frames, potentially limiting further performance gains. To tackle this problem, we propose a background-aware moment detection transformer (BM-DETR). Our model adopts a contrastive approach, carefully utilizing the negative queries matched to other moments in the video. Specifically, our model learns to predict the target moment from the joint probability of each frame given the positive query and the complement of negative queries. This leads to effective use of the surrounding background, improving moment sensitivity and enhancing overall alignments in videos. Extensive experiments on four benchmarks demonstrate the effectiveness of our approach. Our code is available at: \url{https://github.com/minjoong507/BM-DETR}