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.

GitHub

64 stars
3 watching
20 forks
Language: MATLAB
last commit: over 5 years ago
Linked from 1 awesome list


Backlinks from these awesome lists:

Related projects:

RepositoryDescriptionStars
huguyuehuhu/hcn-pytorchReplication of a PyTorch model for action recognition and detection from skeleton data218
wanglimin/untrimmednetA system for recognizing and detecting actions in untrimmed videos using a weakly supervised learning approach.162
pxiangwu/motionnetThis project aims to predict motion and perceive scenes from bird's eye view maps for autonomous driving169
hszhao/pspnetA PyTorch implementation of a deep learning model for semantic image segmentation1,598
hszhao/psanetA deep learning framework for semantic segmentation with spatial attention mechanisms218
chenjoya/vehicle_detection_recognitionA Matlab project for vehicle detection and recognition using deep learning techniques.202
shahroudy/nturgb-dA large-scale dataset for human action recognition763
juntang-zhuang/laddernetA deep learning implementation of a multi-path network architecture for medical image segmentation140
shaoqingren/spp_netRe-implementation of an object detection algorithm described in the ECCV 2014 paper Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition.364
zhouyanzhao/ornA deep learning framework implementation of an oriented response network for visual recognition tasks223
yonghaoxu/rpnetMatlab implementation of a deep learning-based method for classifying hyperspectral images56
zhzhanp/tcdcn-face-alignmentFacial landmark detection using deep multi-task learning in Matlab232
yechengxi/lightnetA Matlab-based framework for building and training deep learning models271
muhanzhang/dgcnnA 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
yuwenxiong/py-r-fcnAn implementation of R-FCN, an object detection algorithm using region-based fully convolutional networks.1,048