Audio-Visual Question Answering (AVQA) is a challenging task that involves answering questions based on both auditory and visual information in videos. A significant challenge is interpreting complex multi-modal scenes, which include both visual objects and sound sources, and connecting them to the given question. In this paper, we introduce the Source-aware Semantic Representation Network (SaSR-Net), a novel model designed for AVQA. SaSR-Net utilizes source-wise learnable tokens to efficiently capture and align audio-visual elements with the corresponding question. It streamlines the fusion of audio and visual information using spatial and temporal attention mechanisms to identify answers in multi-modal scenes. Extensive experiments on the Music-AVQA and AVQA-Yang datasets show that SaSR-Net outperforms state-of-the-art AVQA methods.
@article{arxiv.2411.04933,
title = {SaSR-Net: Source-Aware Semantic Representation Network for Enhancing Audio-Visual Question Answering},
author = {Tianyu Yang and Yiyang Nan and Lisen Dai and Zhenwen Liang and Yapeng Tian and Xiangliang Zhang},
journal= {arXiv preprint arXiv:2411.04933},
year = {2024}
}