Audio-visual synchronisation in the wild
In this paper, we consider the problem of audio-visual synchronisation applied to videos "in-the-wild" (i.e. of general classes beyond speech). As a new task, we identify and curate a test set with high audio-visual correlation, namely VGG-Sound Sync. We compare a number of transformer-bas...
| Main Authors: | , , , , , |
|---|---|
| 格式: | Conference item |
| 語言: | English |
| 出版: |
British Machine Vision Association
2021
|