Skills

Preprints/Articles

Research Experience

Alberto Tamajo

MEng Computer Science And Artificial Intelligence

I am an outstanding fourth-year MEng Computer Science and Artificial Intelligence student at the

University of Southampton. I was the recipient of the Netcraft Prize during my first academic year as I

ranked in the top 10 computer science cohort at the University of Southampton. I was granted the DAAD

RISE Germany Scholarship the following year and the ECS Undergraduate Research Scholarship during my

third academic year to conduct research on AI at the Mainz University of Applied Sciences and the

University of Southampton, respectively. I am currently leading a team of 4 students on a pioneering

research and engineering project on 3D multi-person human pose estimation using a 360° camera and

three mmWave radar sensors.

Machine Learning Libraries: Pytorch | Pytorch Geometric |TensorFlow | Keras |

Languages: English | Italian

A. Tamajo, B. Plaß, and T. Klauer. Shrinking unit: a Graph Convolution-Based Unit

for CNN-like 3D Point Cloud Feature Extractors. arxiv preprint arXiv:2209.12770,

2022 (In submission to a top-tier journal)

A. Tamajo. The future of Artificial Intelligence: from statistical learning to acting

and thinking in an imagined space. Towards Data Science, 2022

2022-10 - 2023-01

Master's Group Design Project

University of Southampton, Southampton, United Kingdom

Title: "Real-time 3D multi-person human pose estimation using a 360° camera and

three mmWave radar sensors"

Advisor: Dr. Hansung Kim

External customer: Korea Institute of Science and Technology

Keywords: 3D Computer Vision, Deep Learning, Machine Learning

Address Southampton, United Kingdom

Phone +39 392 849 2091

E-mail tamajoalberto@gmail.com

LinkedIn linkedin.com/in/albertotamajo/

Leading a team of 4 students on a pioneering research and engineering project

on real-time 3D multi-person human pose estimation using a 360° camera and

three mmWave radar sensors.

Developed a pioneering real-time 3D multi-person human pose estimation

algorithm using a 360° camera and three mmWave radar sensors combining

traditional computer vision techniques and deep learning.

2022-05 - 2022-08

Causal Reasoning Research Internship

University of Southampton, Southampton, United Kingdom

Advisor: Dr. Srinandan Dasmahapatra

Keywords: Causal reasoning, Causal Inference, Causal Discovery, Causal

Representation Learning, Neural-Causal AI, Machine Learning, Deep Learning

Conducted literature research on Causal Machine Learning, Causal

Representation Learning, Causal Discovery and Neural-Causal AI

Developed a score-based, iterative and Gumbell-softmax-based continuous

optimisation causal discovery algorithm under the assumption of Gaussian

structural equation models with equal error variances. Due to the latter

assumption, no interventional data is necessary

Developed a variational inference Expectation-Maximisation-like causal

discovery algorithm from unknown interventions using an LSTM as an

autoregressive distribution over the space of DAGs

Implemented the above algorithms using the Pytorch library

Presented my work at the ECS research seminar on 30 September 2022

2021-09 - 2022-05

Bachelor's Dissertation

University of Southampton, Southampton, United Kingdom

Title: "CC3DVAEWGAN: a controllable conditional 3D point cloud VAE-WGAN

based on shrinking layers and extending layers"

Advisor: Dr. Jonathon Hare

Keywords: Computer Vision, Deep Learning, Geometric Deep Learning

Proposed a novel two-stage framework (CC3DVAEWGAN) based on Shrinking

Layers and Extending Layers to achieve conditional and controllable

generation of point clouds

Proposed an innovative architecture combining a VAE and a WGAN, named

VAE-WGAN, capable of learning a latent space distribution for each training

class and a function from a latent vector to a point cloud blueprint

Proposed two novel architectures, named Extending Layer and Stack Extending

Layer, capable of exploring self, local and global correlations between points in

a semantic-based manner for the generation of point clouds

Implemented the proposed architectures and their training procedures using

the Pytorch and Pytorch Geometric libraries. The implementation supports multi-

GPU utilisation on cluster computing

Conducted experiments to verify the validity of the proposed solutions

2021-07 - 2021-09

Deep Learning Research Internship

Mainz University of Applied Sciences, Mainz, Germany

Education

Honors and Awards

Advisors: Prof. Dr.-Ing. Thomas Klauer, M.Sc. Bastian Plaß

Keywords: Computer Vision, Deep Learning, Geometric Deep Learning

Conducted literature research on Geometric Deep Learning, Generative

Adversarial Networks and Variational AutoEncoders for point cloud

representation learning and generation

Proposed a novel graph convolution-based unit, dubbed Shrinking unit, to

extract features from point clouds

Proposed to stack multiple Shrinking units vertically and horizontally for the

development of the first CNN-like 3D point cloud feature extractors

Implemented the proposed architectures and their training procedures using

the Pytorch and Pytorch Geometric libraries. The implementation supports multi-

GPU utilisation on cluster computing

Published preprint on this work in arxiv on 26 September 2022. Currently

submitting the paper to a top-tier journal in the field

2019-09 - 2023-06

Master of Engineering (MEng): Computer Science And Artificial

Intelligence

University of Southampton - Southampton, United Kingdom

Year 1 Grade: 88% (First Class Honours)| Year 2 Grade: 88% (First Class Honours)|

Year 3 Grade: 85% (First Class Honours)

Personal Academic Tutor: Dr. David Millard

Master's Group Design Project: "Real-time 3D multi-person human pose

estimation using a 360° camera and three mmWave radar sensors"

Bachelor's Dissertation: "CC3DVAEWGAN: a controllable conditional 3D point

cloud VAE-WGAN based on Shrinking layers and Extending layers"

Year 4 Modules: Advanced Machine Learning, Differentiable programming and

Deep Learning, Bayesian Reasoning and Reinforcement Learning, Data Mining,

Group Design Project, Data Visualisation

Year 3 Module Marks: Causal Reasoning and Machine Learning-90%,

Foundation of Machine Learning-90%, Computer Vision-93%, Bachelor's

Dissertation-77%, Social Computing Techniques-96%, Engineering Management

and Law-80%

Year 2 Module Marks: Intelligent Systems-95%, Programming III-89%, Theory of

Computing-89%, Programming Language Concepts-97%, Software Engineering

Group Project-78%, Principles of Cyber Security-81%, Distributed Systems-87%,

Interaction Design-90%

Year 1 Module Marks: Foundations of Computer Science-96%, Algorithmics-93%,

Data Management-93%, Programming I-93%, Programming II-93%, Software

Design and Modelling-93%, Computer Systems I-83%, Professional Development-

75%

Extraccuricular activities

ECS Undergraduate Research Scholarship 2022, granted a scholarship to carry

out a research internship at the University of Southampton

DAAD RISE Germany Scholarship 2021, granted a scholarship to carry out a

research internship at the Mainz University of Applied Sciences. Only 268 out of

1635 applicants were granted a research position

NETCRAFT Prize 2020, placed in the top 10 computer science cohort (out of a

cohort of more than 300 students) at the University of Southampton

Alfieri Del Lavoro Prize 2018, shortlisted as one of the most high-achieving italian

high-school diploma student

Sport, music, gaming, writing, reading, philosophy