AlignNet: A Unifying Approach to Audio-Visual Alignment
CMU（卡内基梅隆大学）；University of Notre Dame（圣母大学）；MIT（麻省理工学院）
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
