综述文章推荐以下2篇：
[1]Herath S, Harandi M, Porikli F. Going deeper into action recognition: A survey[J]. Image and Vision Computing, 2017, 60: 4-21.
[2]Wu Z, Yao T, Fu Y, et al. Deep Learning for Video Classification and Captioning. arXiv:1609.06782, 2016.
以下是当前不同数据集上效果最好的几篇文章：
Diba A, Sharma V, Gool L V. Deep Temporal Linear Encoding Networks.arXiv:1611.06678, 2016. 【UCF-101 95.6】
Lan Z, Zhu Y, Hauptmann A G. Deep Local Video Feature for Action Recognition.arXiv:1701.07368, 2017.【HMDB51 75.0】Miech A, Laptev I, Sivic J. Learnable pooling with Context Gating for videoclassification[J]. arXiv preprint arXiv:170606905, 2017.【YouTube-8M 84.967】
Wang L, Xiong Y, Lin D, et al. UntrimmedNets for Weakly Supervised Action Recognition and Detection. arXiv:1703.03329, 2017.【ActivityNet 91.3】
Abu-El-Haija S, Kothari N, Lee J, et al. YouTube-8M: A Large-Scale Video Classification Benchmark. arXiv:1609.08675, 2016. 【Sports-1M 67.6】
