[TSN](https://github.com/PaddlePaddle/models/tree/develop/fluid/PaddleCV/video_classification)|视频分类模型|基于长范围时间结构建模,结合了稀疏时间采样策略和视频级监督来保证使用整段视频时学习得有效和高效|[Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://arxiv.org/abs/1608.00859)