Back to Search
Start Over
AlignNet: A Unifying Approach to Audio-Visual Alignment
- Publication Year :
- 2020
-
Abstract
- We present AlignNet, a model that synchronizes videos with reference audios under non-uniform and irregular misalignments. AlignNet learns the end-to-end dense correspondence between each frame of a video and an audio. Our method is designed according to simple and well-established principles: attention, pyramidal processing, warping, and affinity function. Together with the model, we release a dancing dataset Dance50 for training and evaluation. Qualitative, quantitative and subjective evaluation results on dance-music alignment and speech-lip alignment demonstrate that our method far outperforms the state-of-the-art methods. Project video and code are available at https://jianrenw.github.io/AlignNet.<br />Comment: WACV2020. Project video and code are available at https://jianrenw.github.io/AlignNet
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2002.05070
- Document Type :
- Working Paper