jiachen0212的博客

原文链接：https://arxiv.org/abs/1705.07871v1首先paper的任务是：实现视频中人脸表情的识别，视频转化为10frames的序列进行处理。原文：we divided videos into sequences of ten frames to shape the input tensor for our network。网络总体结构：3DIR(3D Inceptio...