·2,447,543篇论文数据，部分数据来源于NoteExpress
另外，他们发现机器人可以利用仅是表现面庞形状的非常简单的复特征，相比之下，唇读者们需要讲话的完整录像。
Furthermore, they found that machines are able to exploit very simplistic features that represent only the shape of the face, whereas human lip-readers require full video of people speaking.
youdao
应用推荐
模块上移
模块下移
不移动