Using two stream architecture to implement a classic action recognition method on UCF101 dataset
-
Updated
Apr 8, 2019 - Python
Using two stream architecture to implement a classic action recognition method on UCF101 dataset
Implemented Kernel SVM using Quadratic Programming and Stochastic Gradient Descent
Computer Vision: African Motion Content Network
This project builds a video classification model using CNNs for spatial feature extraction and RNNs for temporal sequence modeling. Utilizing the UCF101 dataset, it covers data preprocessing, feature extraction, model training, and evaluation, providing a comprehensive approach to action recognition in videos.
Simple Action Recognition experimentation with the UCF101 Dataset and EfficientNets.
Pytorch inception v4 for human actions recognition.
Salient Video Frames Sampling Method Using the Mean of Deep Features for Efficient Model Training (KIBME 2021)
Temporal 3D ConvNet
[AAAI 2024] XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning.
A simple and fun video classification/action recognition using VGG16 as a feature extractor and RNN.
Testing code for few-shot action recognition
PyTorch implementation for "Gated Transfer Network for Transfer Learning"
A pytorch implementation of a text to videos GAN
Source Code for Captionomaly: A Deep Learning Toolbox for Anomaly Captioning in Surveillance Videos
Action Recognition using Convolutional Neural Network (CNN)
Video classification exercise using UCF101 data for training an early-fusion and SlowFast architecture model, both using the PyTorch Lightning framework.
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
Add a description, image, and links to the ucf101 topic page so that developers can more easily learn about it.
To associate your repository with the ucf101 topic, visit your repo's landing page and select "manage topics."