Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering

arXiv:2404.12020v1 Announce Type: new
Abstract: Audio-Visual Question Answering (AVQA) is a complex multi-modal reasoning task, demanding intelligent systems to accurately respond to natural language queries based on audio-video input pairs. Nevertheless, prevalent AVQA approaches are prone to overlearning dataset biases, resulting in poor robustness. Furthermore, current datasets may not provide a precise diagnostic for these methods. To tackle these challenges, firstly, we propose a novel dataset, \textit{MUSIC-AVQA-R}, crafted in two steps: rephrasing questions within the test split of a public …

abstract arxiv audio biases cs.cv current dataset datasets intelligent intelligent systems language look modal multi-modal natural natural language natural language queries queries question question answering reasoning robustness systems type video visual