UAVM: Towards Unifying Audio and Visual Models
Yuan Gong, Alexander H. Liu, Andrew Rouditchenko, James Glass
Abstract
Conventional audio-visual models have independent audio and video branches. In this work, we <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">unify</i> the audio and visual branches by designing a <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">U</u> nified <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">A</u> udio- <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">V</u> isual <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">M</u> odel (UAVM). The UAVM achieves a new state-of-the-art audio-visual event classification accuracy of 65.8% on VGGSound. More interestingly, we also find a few intriguing properties of UAVM that the modality-independent counterparts do not have.