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: | Chen, H, Xie, W, Afouras, T, Nagrani, A, Vedaldi, A, Zisserman, A |
---|---|
Format: | Conference item |
Language: | English |
Published: |
British Machine Vision Association
2021
|
Similar Items
-
Sparse in space and time: audio-visual synchronisation with trainable selectors
by: Iashin, V, et al.
Published: (2022) -
Localizing visual sounds the hard way
by: Vedaldi, A, et al.
Published: (2021) -
Vggsound: a large-scale audio-visual dataset
by: Chen, H, et al.
Published: (2020) -
Spot the conversation: Speaker diarisation in the wild
by: Chung, JS, et al.
Published: (2020) -
Audio-visual deep learning
by: Afouras, T, et al.
Published: (2021)