dgcnn

A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks

Official Code for ICML 2021 paper "Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline"

Repetition code of the model for the paper "EEG Emotion Recognition Using Dynamical Graph Convolutional Neural Networks" in pytorch

[BIBM2024] MEEG and AT-DGNN: Improving EEG Emotion Recognition with Music Introducing and Graph-based Learning

Dynamic Graph Convolutional Neural Network for 3D point cloud semantic segmentation

This is the official pytorch implementation for paper: IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restoration

支持百度竞赛数据的中文事件抽取，支持ace2005数据的英文事件抽取，本人将苏神的三元组抽取算法中的DGCNN改成了事件抽取任务，并将karas改成了本人习惯使用的pytorch，在数据加载处考虑了各种语言的扩展

Dilate Gated Convolutional Neural Network For Machine Reading Comprehension

Clean & Documented TF2 implementation of "An end-to-end deep learning architecture for graph classification" (M. Zhang et al., 2018).

Code and Data for the paper "LPF-Defense: 3D Adversarial Defense based on Frequency Analysis", PLoS ONE

A pytorch implementation for an optimized DGCNN

PLEASE USE THE NEW REPO https://github.com/salehjg/DeepPoint-V2-FPGA . The deprecated in-order-queue-based repository for "DGCNN on FPGA: Acceleration of The Point CloudClassifier Using FPGAs".

This repository contains the code to train a custom DGCNN segmentation model on 3D point cloud data and carry out post-processing to filter these point clouds from the k-regular graphs produced by the model.

Codes for the Point Cloud Analysis Project (IPL Lab, Sharif UT)

3D intra-oral scan tooth segmentation with DGCNN on Teeth3DS.

Code for our article "Sparse Keypoint Segmentation of Lung Fissures: Efficient Geometric Deep Learning for Abstracting Volumetric Images"

AI-assisted orthodontic treatment planning pipeline for clear aligners with dual-agent deep learning and 4D staging simulation.

3D point cloud classification on ModelNet40: PointNet, DGCNN and a hybrid attention-fusion model from scratch, 85.5% test accuracy

Project for the University Master Degree Course and Thesis of Computer Vision