Video-friendly caffe -- comes with the most recent version of Caffe (as of Jan 2019), a video reader, 3D(ND) pooling layer, and an example training script for C3D network and UCF-101 data
-
Updated
Dec 24, 2018 - C++
Video-friendly caffe -- comes with the most recent version of Caffe (as of Jan 2019), a video reader, 3D(ND) pooling layer, and an example training script for C3D network and UCF-101 data
Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"
Implementation Code of the paper Optical Flow Guided Feature, CVPR 2018
Real time Fight Detection Based on 2D Pose Estimation and RNN Action Recognition
Tools for movie and video research
[Neurocomputing 2019] Fast and Robust Dynamic Hand Gesture Recognition via Key Frames Extraction and Feature Fusion
Activity Recognition using Temporal Optical Flow Convolutional Features and Multi-Layer LSTM
Surveillance System Against Violence
Activity recognition with volume motion templates and histograms of 3D gradients
Distance-based Methods for Action Recognition in Motion Capture Data
Real-time action recognition on Nvidia Tegra X2 using CSI cameras. The neural network is trained on KTH dataset.
Add a description, image, and links to the action-recognition topic page so that developers can more easily learn about it.
To associate your repository with the action-recognition topic, visit your repo's landing page and select "manage topics."