Name: Amir Atapour-Abarghouei
Type: User
Company: Durham University
Bio: Assistant Professor, Durham University, UK.
Computer Vision, Image Processing, Natural Language Processing, Machine Learning, etc.
Twitter: AmirAtapour
Location: Durham, United Kingdom
Blog: http://www.atapour.co.uk/
Amir Atapour-Abarghouei's Projects
a set of simple excercises in colour filtering from a live video image (inc. invisibility cloaking)
Miscellaneous code demonstrations
This repository contains code for training and testing a model used to predict where holes would appear in a depth image based on an RGB image input.
A real-time depth filling approach based on prior image segmentation (http://www.atapour.co.uk/papers/BMVC2017.pdf).
Deep Generative Neural Networks - Demos
Examples and code demonstrations for the Deep Learning module at Durham University
Material for Introduction to Image Processing and Computer Vision
This repo contains a set of simple excercises in colour filtering from a live video image. The demo will lead to the implementation of a simple "cloak of invisibility".
Examples and code demonstrations for the Image Processing module at Durham University
Examples and demonstration written in Python and Keras used in the "Deep Learning" lecture series at Newcastle University (CSC8637).
Inference pipeline for the CVPR paper entitled "Real-Time Monocular Depth Estimation using Synthetic Data with Domain Adaptation via Image Style Transfer" (http://atapour.co.uk/papers/atapour18monocular.pdf).
Simple PyTorch code demonstration.
Source code for the training pipeline of the text ranking model used in the paper entitled "Rank over Class: The Untapped Potential of Ranking in Natural Language Processing" (https://arxiv.org/abs/2009.05160).
Training and testing pipeline for ransomware classification based on screenshots of the splash screens or ransom notes (https://arxiv.org/pdf/1908.06750.pdf).
Source code (train/test) accompanying the paper entitled "Veritatem Dies Aperit - Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach" in CVPR 2019 (https://arxiv.org/abs/1903.10764).