Visually-aware Acoustic Event Detection using Heterogeneous Graphs

TL;DR

This paper introduces a novel heterogeneous graph-based method for visually-aware acoustic event detection, explicitly modeling spatial and temporal relationships between audio and visual data, leading to state-of-the-art results on AudioSet.

Contribution

The paper proposes using heterogeneous graphs to explicitly capture intra- and inter-modality relationships for acoustic event detection, improving over existing fusion methods.

Findings

Achieves state-of-the-art performance on AudioSet

Efficiently models spatial and temporal relationships

Easily adaptable to different event scales

Abstract

Perception of auditory events is inherently multimodal relying on both audio and visual cues. A large number of existing multimodal approaches process each modality using modality-specific models and then fuse the embeddings to encode the joint information. In contrast, we employ heterogeneous graphs to explicitly capture the spatial and temporal relationships between the modalities and represent detailed information about the underlying signal. Using heterogeneous graph approaches to address the task of visually-aware acoustic event classification, which serves as a compact, efficient and scalable way to represent data in the form of graphs. Through heterogeneous graphs, we show efficiently modelling of intra- and inter-modality relationships both at spatial and temporal scales. Our model can easily be adapted to different scales of events through relevant hyperparameters. Experiments on AudioSet, a large benchmark, shows that our model achieves state-of-the-art performance.