BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos

TL;DR

BAM-DETR introduces a boundary-oriented approach with a dual-pathway transformer to improve temporal moment detection accuracy in videos, addressing center misalignment issues present in previous methods.

Contribution

The paper proposes a novel boundary-aligned moment formulation and a dual-pathway transformer architecture for more accurate temporal grounding in videos.

Findings

Outperforms existing methods on three benchmarks.

Effectively reduces center misalignment issues.

Enhances proposal quality ranking.

Abstract

Temporal sentence grounding aims to localize moments relevant to a language description. Recently, DETR-like approaches achieved notable progress by predicting the center and length of a target moment. However, they suffer from the issue of center misalignment raised by the inherent ambiguity of moment centers, leading to inaccurate predictions. To remedy this problem, we propose a novel boundary-oriented moment formulation. In our paradigm, the model no longer needs to find the precise center but instead suffices to predict any anchor point within the interval, from which the boundaries are directly estimated. Based on this idea, we design a boundary-aligned moment detection transformer, equipped with a dual-pathway decoding process. Specifically, it refines the anchor and boundaries within parallel pathways using global and boundary-focused attention, respectively. This separate design allows the model to focus on desirable regions, enabling precise refinement of moment predictions. Further, we propose a quality-based ranking method, ensuring that proposals with high localization qualities are prioritized over incomplete ones. Experiments on three benchmarks validate the effectiveness of the proposed methods. The code is available at https://github.com/Pilhyeon/BAM-DETR.