Details

Autor(en) / Beteiligte

• Wang, Jianren
• Fang, Zhaoyuan
• Zhao, Hang

Titel

AlignNet: A Unifying Approach to Audio-Visual Alignment

Ist Teil von

• 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), 2020, p.3298-3306

Ort / Verlag

IEEE

Erscheinungsjahr

2020

Quelle

IEEE Electronic Library Online

Beschreibungen/Notizen

• We present AlignNet, a model that synchronizes videos with reference audios undernon-uniform and irregularmis- alignments. 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. Code, dataset and sample videos are available at our project page 1 .