We introduce MultiVSR - a large-scale dataset for multilingual visual speech recognition. MultiVSR comprises ~12,000 hours of video data paired with word-aligned transcripts from 13 languages. We ...

The following demos are selected from Appendix A failure cases. Preview images remain in assets/failure_demos/, while showcased videos are hosted through GitHub attachments to keep the repository ...

你有没有看过配音糟糕的电影，嘴唇动作和台词不同步？或者在视频通话中，对方的嘴型和声音不同步？这些同步问题不仅仅是烦人，而是视频制作、广播和实时通信中一个真正的问题。Syncnet论文（见“项目源码”一节）通过一种巧妙的自监督方法正面解决了 ...

OPTICS is a density-based clustering algorithm available in the PyClustering library. PyClustering is an open-source data mining package designed for Python and C++. The library enhances cluster ...