VLG-Net: Video-Language Graph Matching Network for Video Grounding

TL;DR

VLG-Net introduces a graph matching approach using Graph Neural Networks to improve video grounding by aligning video and language representations, achieving superior results on multiple datasets.

Contribution

The paper presents a novel Video-Language Graph Matching Network that models intra- and inter-modality relationships for enhanced video grounding performance.

Findings

Outperforms state-of-the-art methods on ActivityNet-Captions, TACoS, and DiDeMo datasets.

Effectively models multi-modal interactions with graph-based representations.

Demonstrates the effectiveness of graph matching in temporal video localization.

Abstract

Grounding language queries in videos aims at identifying the time interval (or moment) semantically relevant to a language query. The solution to this challenging task demands understanding videos' and queries' semantic content and the fine-grained reasoning about their multi-modal interactions. Our key idea is to recast this challenge into an algorithmic graph matching problem. Fueled by recent advances in Graph Neural Networks, we propose to leverage Graph Convolutional Networks to model video and textual information as well as their semantic alignment. To enable the mutual exchange of information across the modalities, we design a novel Video-Language Graph Matching Network (VLG-Net) to match video and query graphs. Core ingredients include representation graphs built atop video snippets and query tokens separately and used to model intra-modality relationships. A Graph Matching layer is adopted for cross-modal context modeling and multi-modal fusion. Finally, moment candidates are created using masked moment attention pooling by fusing the moment's enriched snippet features. We demonstrate superior performance over state-of-the-art grounding methods on three widely used datasets for temporal localization of moments in videos with language queries: ActivityNet-Captions, TACoS, and DiDeMo.