Using two stream architecture to implement a classic action recognition method on UCF101 dataset

Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101

This repository host the code for real-time action detection paper

Implementation Code of the paper Optical Flow Guided Feature, CVPR 2018

STEP: Spatio-Temporal Progressive Learning for Video Action Detection. CVPR'19 (Oral)

Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"

Video Platform for Action Recognition and Object Detection in Pytorch

Video Recognition using Mixed Convolutional Tube (MiCT) on PyTorch with a ResNet backbone

Use 3D ResNet to extract features of UCF101 and HMDB51 and then classify them.

TensorFlow implementation for "Guided Optical Flow Learning"

My experimentation around action recognition in videos. Contains Keras implementation for C3D network based on original paper "Learning Spatiotemporal Features with 3D Convolutional Networks", Tran et al. and it includes video processing pipelines coded using mPyPl package. Model is being benchmarked on popular UCF101 dataset and achieves results similar to those reported by authors

Video Representation Learning by Recognizing Temporal Transformations. In ECCV, 2020.

由视频数据集生成optical flow，frames，warped flow

Support LRCN(both rgb and optical-flow). This fork of BVLC/Caffe is dedicated to improving performance of this deep learning framework when running on CPU, in particular Intel® Xeon processors (HSW+) and Intel® Xeon Phi processors

Action Recognition using Convolutional Neural Network (CNN)

Temporal 3D ConvNet

PyTorch implementation for "Gated Transfer Network for Transfer Learning"

Pytorch inception v4 for human actions recognition.

Computer Vision Project : Action Recognition on UCF101 Dataset

Simple Action Recognition experimentation with the UCF101 Dataset and EfficientNets.

A pytorch implementation of a text to videos GAN

Computer Vision: African Motion Content Network

Implemented Kernel SVM using Quadratic Programming and Stochastic Gradient Descent

Using two stream architecture to implement a classic action recognition method on UCF101 dataset

Action Recognition Deep Learning

A simple and fun video classification/action recognition using VGG16 as a feature extractor and RNN.