TeMTG: Text-Enhanced Multi-Hop Temporal Graph Modeling for Audio-Visual Video Parsing

TL;DR

TeMTG introduces a multimodal framework that enhances audio-visual video parsing by integrating text embeddings and multi-hop temporal graph modeling, leading to improved event detection accuracy under weak supervision.

Contribution

The paper proposes a novel multimodal optimization framework combining text enhancement with multi-hop temporal graph neural networks for better AVVP performance.

Findings

Achieves state-of-the-art results on LLP dataset.

Effectively models temporal relationships between segments.

Enhances semantic feature representations with text embeddings.

Abstract

Audio-Visual Video Parsing (AVVP) task aims to parse the event categories and occurrence times from audio and visual modalities in a given video. Existing methods usually focus on implicitly modeling audio and visual features through weak labels, without mining semantic relationships for different modalities and explicit modeling of event temporal dependencies. This makes it difficult for the model to accurately parse event information for each segment under weak supervision, especially when high similarity between segmental modal features leads to ambiguous event boundaries. Hence, we propose a multimodal optimization framework, TeMTG, that combines text enhancement and multi-hop temporal graph modeling. Specifically, we leverage pre-trained multimodal models to generate modality-specific text embeddings, and fuse them with audio-visual features to enhance the semantic representation of these features. In addition, we introduce a multi-hop temporal graph neural network, which explicitly models the local temporal relationships between segments, capturing the temporal continuity of both short-term and long-range events. Experimental results demonstrate that our proposed method achieves state-of-the-art (SOTA) performance in multiple key indicators in the LLP dataset.