Transavs: End-To-End Audio-Visual Segmentation With Transformer

no code implementations • 12 May 2023 • Yuhang Ling, Yuxi Li, Zhenye Gan, Jiangning Zhang, Mingmin Chi, Yabiao Wang

Generally AVS faces two key challenges: (1) Audio signals inherently exhibit a high degree of information density, as sounds produced by multiple objects are entangled within the same audio stream; (2) Objects of the same category tend to produce similar audio signals, making it difficult to distinguish between them and thus leading to unclear segmentation results.

Scene Understanding Segmentation +1