Learning to Answer Questions in Dynamic Audio-Visual Scenarios

TL;DR

This paper introduces a new large-scale dataset and a spatio-temporal grounded network for audio-visual question answering, demonstrating improved multimodal reasoning over videos.

Contribution

The paper presents the MUSIC-AVQA dataset and a novel network architecture for AVQA, advancing multimodal understanding and reasoning in dynamic scenes.

Findings

Our model outperforms recent AVQA approaches.

The dataset enables comprehensive evaluation of audio-visual reasoning.

Multisensory perception enhances question answering performance.

Abstract

In this paper, we focus on the Audio-Visual Question Answering (AVQA) task, which aims to answer questions regarding different visual objects, sounds, and their associations in videos. The problem requires comprehensive multimodal understanding and spatio-temporal reasoning over audio-visual scenes. To benchmark this task and facilitate our study, we introduce a large-scale MUSIC-AVQA dataset, which contains more than 45K question-answer pairs covering 33 different question templates spanning over different modalities and question types. We develop several baselines and introduce a spatio-temporal grounded audio-visual network for the AVQA problem. Our results demonstrate that AVQA benefits from multisensory perception and our model outperforms recent A-, V-, and AVQA approaches. We believe that our built dataset has the potential to serve as testbed for evaluating and promoting progress in audio-visual scene understanding and spatio-temporal reasoning. Code and dataset: http://gewu-lab.github.io/MUSIC-AVQA/