PyTorch implementation of Two-stream CNN for 3D action recognition
-
Updated
Jul 31, 2020 - Python
PyTorch implementation of Two-stream CNN for 3D action recognition
Skeleton-based Action Recognition Papers and Small Notes and Top 2 Leaderboard for NTU-RGBD
Offical implementation of paper "MSAF: Multimodal Split Attention Fusion"
Unofficial Tensorflow implementation of the AAAI'18 paper "Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition"
Human Action Recognition using skeleton and infrared data. State-of-the-art results on NTU RBG+D. Implemented with PyTorch.
Course Project for CS763 Computer Vision IIT Bombay
NTU RGB+D Dataset Action Recognition with GNNs and CNNs
Official pytorch implementation for PSUMNet for efficient skeleton action recognition
experiments on classifying actions using poses
Action-Localization, Atomic Visual Actions (AVA) Dataset
Time series Forecasting on the NTU_RGB+D skeleton dataset using AutoFormer and FEDFormer
Explanation-based anonymization for skeleton motion privacy (PAKDD 2025). Integrated Gradients scores per-joint privacy sensitivity; targeted masking and differentially private noise cut re-identification from 81.6% to 21.8%.
Unofficial Tensorflow implementation of the CVPR'19 paper "Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition"
Skeletal join forecasting
Real-time skeleton-based action recognition with from-scratch HRNet-like pose estimation and two-stream ST-GCN, targeting NTU RGB+D 120
To associate your repository with the ntu-rgbd topic, visit your repo's landing page and select "manage topics."