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
An open-source toolbox for action understanding based on PyTorch
Evaluating Taekwondo Moves - This system aims to recognize and evaluate 10 foundational taekwondo moves
FrVD: French Video Description dataset
3D Convolutional Neural Networks for Human Action Recognition
Multimodal version of SlowFast (Vision + Audio inputs)
VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
This repository contains skeleton video classification.
mmWave based action recognition using ROS.
Apply ML to the skeletons from OpenPose; 9 actions; multiple people. (WARNING: I'm sorry that this is only good for course demo, not for real world applications !!! Those ary very difficult !!!)
Human Activity Detection with TensorFlow and Python.
Фреймворк компьютерного зрения для задач, детекции, сегментации, классификации, идентификации людей, анализа настроений и классификации действий
A curated list of action recognition and related area resources
Deep learning algorithm to sort images in time dimension. Images belong to same activity and are corresponding frames in a short duration of time
Hand Action recognition and classification
Conclusion of undergraduate research in NIP-UPD
This project allows to train and test sign language data to identify numbers, the alphabet and poses with the help of opencv and mediapipe
A practical implementation of sign language estimation using an LSTM NN built on TF Keras.
Sign2Sound is dedicated to revolutionizing communication for non-verbal individuals by seamlessly translating sign language gestures into understandable speech in real-time. By bridging the gap between sign language users and those unfamiliar with it, Sign2Sound promotes inclusivity and accessibility, ultimately enriching quality of life for all.
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."