Amran's Projects
Code to accompany "A Method for Animating Children's Drawings of the Human Figure"
"DeepDPM: Deep Clustering With An Unknown Number of Clusters" [Ronen, Finder, and Freifeld, CVPR 2022]
The implementation of DMGNN
A comparative study of supervised and unsupervised approaches in human activity analysis based on skeleton data. Five shallow classifiers with three different features are evaluated.
the results, code and the data for the Force 2020 Machine learning competition after the completion of the competition in October 2020.
Human Action Recognition using skeleton and infrared data. State-of-the-art results on NTU RBG+D. Implemented with PyTorch.
A Comparative Review of Recent Kinect-Based Action Recognition Algorithms (TIP2020, Matlab codes)
This repo is official implementation of HumanBench (CVPR2023)
Easy-to-use Production Ready Container Management Platform
Inference code for LLaMA models
This is a computer vision algorithm that takes a single RGB image as the input and estimates 3D human poses as the output.
Config files for my GitHub profile.
A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.
Mocap data helper
Info and sample codes for "NTU RGB+D Action Recognition Dataset"
Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video tagging and sport action detection.
Python bindings for OpenNI2 and NiTE2
Repository for PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition
Wrapper to expose Kinect for Windows v2 API in Python
A toolbox for skeleton-based action recognition.
All Algorithms implemented in Python
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
A self-driving car simulator built with Unity
A curated list of awesome self-supervised methods
Skeleton Graph Convolution Network is based on the Deep Graph Library and inspired by ST-GCN network designing.
Spatial Temporal Transformer Network for Skeleton-Based Activity Recognition
Human activity dataset captured using Kinect V1
View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition