这个主题暂时对我太高级了，放一放
https://towardsdatascience.com/real-time-and-video-processing-object-detection-using-tensorflow-opencv-and-docker-2be1694726e5
https://www.pyimagesearch.com/2018/11/12/yolo-object-detection-with-opencv/
https://www.pyimagesearch.com/2017/09/18/real-time-object-detection-with-deep-learning-and-opencv/
https://medium.com/@jonathan_hui/real-time-object-detection-with-yolo-yolov2-28b1b93e2088
Deep Learning for Videos:
A 2018 Guide to Action Recognition
http://blog.qure.ai/notes/deep-learning-for-videos-action-recognition-review
https://medium.com/@jonathan_hui/object-detection-speed-and-accuracy-comparison-faster-r-cnn-r-fcn-ssd-and-yolo-5425656ae359
Human Action Recognition:
| Model | HMDB-51 | UCF-101 | |
| I3D | 80.9% | 98.0% |
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset (May 2017) |
行为识别Action Detection概述及资源合集（持续更新...）
https://zhuanlan.zhihu.com/p/33040925
https://zhuanlan.zhihu.com/p/26460437
https://zhuanlan.zhihu.com/p/45444790
- Deep Learning for Videos: A 2018 Guide to Action Recognition - Summary of major landmark action recognition research papers till 2018
分割算法
Understanding How Mask RCNN Works for Semactic Segmentation - https://ardianumam.wordpress.com/2017/12/16/understanding-how-mask-rcnn-works-for-semactic-segmentation/