LieNet
Action recognition algorithm
This project uses deep learning and Lie group theory to recognize actions from skeleton data
GitHub repository for "Deep Learning on Lie Groups for Skeleton-based Action Recognition", CVPR 2017.
64 stars
3 watching
20 forks
Language: MATLAB
last commit: over 5 years agoLinked from 1 awesome list
Related projects:
| Repository | Description | Stars |
|---|---|---|
| Replication of a PyTorch model for action recognition and detection from skeleton data | 218 | |
| A system for recognizing and detecting actions in untrimmed videos using a weakly supervised learning approach. | 162 | |
| This project aims to predict motion and perceive scenes from bird's eye view maps for autonomous driving | 169 | |
| A PyTorch implementation of a deep learning model for semantic image segmentation | 1,598 | |
| A deep learning framework for semantic segmentation with spatial attention mechanisms | 218 | |
| A Matlab project for vehicle detection and recognition using deep learning techniques. | 202 | |
| A large-scale dataset for human action recognition | 763 | |
| A deep learning implementation of a multi-path network architecture for medical image segmentation | 140 | |
| Re-implementation of an object detection algorithm described in the ECCV 2014 paper Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. | 364 | |
| A deep learning framework implementation of an oriented response network for visual recognition tasks | 223 | |
| Matlab implementation of a deep learning-based method for classifying hyperspectral images | 56 | |
| Facial landmark detection using deep multi-task learning in Matlab | 232 | |
| A Matlab-based framework for building and training deep learning models | 271 | |
| A deep learning architecture for graph classification that extracts vertex features through propagation-based graph convolution and retains more node information than traditional sum pooling methods. | 174 | |
| An implementation of R-FCN, an object detection algorithm using region-based fully convolutional networks. | 1,048 |