Name: Ali Ghorbanpour
Type: User
Company: Simon Fraser University
Bio: Graduate Research Assistant, Simon Fraser University, Computing Science Dept.
Location: Canada, Vancouver
Ali Ghorbanpour's Projects
Homework files for my Advance NLP class taught at Simon Fraser University - Summer 2023
Ali's Personal Website
Config files for my GitHub profile.
Effective Java for Android
AP Project.
A curated list of image manipulation detection and localization and related resources.
Undergraduate Final Project
Rust SDK for the core C2PA (Coalition for Content Provenance and Authenticity) specification
C project PAC-MAN
error-correction-code
My assignment solutions for CS231n - Convolutional Neural Networks for Visual Recognition
Learning Deep learning.
A light-weight deep reinforcement learning framework for portfolio management. This project explores the possibility of applying deep reinforcement learning algorithms to stock trading in a highly modular and scalable framework.
ใPyTorchใEasy-to-use,Modular and Extendible package of deep-learning based CTR models.
Official repository of "DeepMIH: Deep Invertible Network for Multiple Image Hiding", TPAMI 2022.
DKiS: Decay weight invertible image steganography with private key
Data Structure & Design Algorithm
EdgeConnect: Structure Guided Image Inpainting using Edge Prediction, ICCV 2019 https://arxiv.org/abs/1901.00212
This is the source code of paper FIN: Flow-based Robust Watermarking with Invertible Noise Layer for Black-box Distortions, which is received by AAAI' 23.
From Image to Imuge: Immunized Image Generation, official code, implemented by PyTorch, ACMMM 2021 paper
Pytorch implementation of paper "HiDDeN: Hiding Data With Deep Networks" by Jiren Zhu, Russell Kaplan, Justin Johnson, and Li Fei-Fei
Official PyTorch implementation of "HiNet: Deep Image Hiding by Invertible Network" (ICCV 2021)
The source code for the paper "Robust Data Hiding Using Inverse Gradient Attention".
Paper Title: Learning to Immunize Images for Tamper Localization and Self-Recovery - 2022
Learning a grayscale image that can be fully restored to its orignal color version.
Scripts for the creation of the Kaggle Torrent