A crowd counting GUI system developed by pyqt4 which combines 3 models including YOLO, RetinaNet and MCNN.

给yolov5加个gui界面，使用pyqt5，yolov5是5.0版本

Action recognition tutorial using UCF-101 dataset.

Action Recognition in Video Sequences using Deep Bi-directional LSTM with CNN Features

Three steps to train your own model for action recognition based on CNN and LSTM by PyTorch.

Action recognition network -- CNN + LSTM.