There are 1 repository under gcnn topic.
Code for "Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction" CVPR 2020
Code for A GRAPH-CNN FOR 3D POINT CLOUD CLASSIFICATION (ICASSP 2018)
Embedded Graph Convolutional Neural Networks (EGCNN) in TensorFlow
Dynamic Graph Convolutional Neural Network for 3D point cloud semantic segmentation
Code for: "Skeleton-Graph: Long-Term 3D Motion Prediction From 2D Observations Using Deep Spatio-Temporal Graph CNNs", ICCV2021 Workshops
Algorithms for prediction of congestion from Network State
Automated Headline generation and Aspect Based Sentiment Analysis
Marker-Based Motion Capture Data Denoising
Code for HAR-GCNN: Deep Graph CNNs for Human Activity Recognition From Highly Unlabeled Mobile Sensor Data, IEEE PerCom CoMoRea 2022
Android Malware Detection Model Based on Graph Neural Network
Graph Analysis Course Notes
GCNN for EEG Emotion Recognition
GraphCNN + CNN Network for EEG Emotion Recognition
A TensorFlow 2 implementation of Graph Convolutional Networks (GCN)
Graph convolutional networks for structural learning of proteins
Weather prediction on stereo images using a graph equivariant convolutional neural network.
Complexity-based graph convolutional neural network for epilepsy diagnosis in normal, acute, and chronic stages
A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of convolutional neural networks which operate directly on graphs.
ECE271B: Statistical Learning II Final Project with David Glukhov
A collections of all deep learning experiments we have throughout the deep learning courses
Yale Collab with Aarthi (Smita Krishnaswamy group) where I built signalling knowledge graphs to capture cell communications.
The program explores how various network structures influence system behavior under Braess' Paradox — a counterintuitive phenomenon in which adding resources to a network can degrade overall performance. The simulations are implemented using Python and NetworkX to model, analyze, and visualize traffic-like flow in graph-based systems.
PyTorch reproduction for ECCV 2018 paper "Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images""