Author Image

Hi, I am Ricardo

Ricardo G. Sousa

With over a decade of experience in driving the development and successful launch of innovative AI platforms, I bring my passion for leveraging cutting-edge technologies and fostering innovation to help businesses harness the power of AI.

Projects

Book Summarization
Owner August 2024

Book summarization: Exploring RAG and Literacy reviews to generate informative summaries

ai professional
Star
Face Liveness and Age Detections
Owner March 2024 - April 2024

Face liveness and age detection system, providing tools and models to identify real faces and estimate age from videos and images.

ai image processing computer vision face detection professional
Star
Video Short (& Blog) Generator
Video Short (& Blog) Generator
Owner March 2024 - April 2024

The Video Shorts Generator (VSG) streamlines video and blog content creation for brands.

ai llm professional
Star
Farfetch Chat R&D (formerly known as iFetch)
Farfetch Chat R&D (formerly known as iFetch)
Project Coordinator and Principal Investigator April 2020 - April 2023

Multimodal Conversational Agents for the Online Fashion Marketplace.

professional conversational ai
Details
ANI LaTeX Template
ANI LaTeX Template
Owner November 2022

ANI LaTeX Template CLS.

professional LaTeX
Star
Reject Option with Ordinal Learning Algorithms
Owner 2008-2012

Code for the paper “An Ordinal Data Method for the Classification with Reject Option”.

reject-option
Star

Recent Posts

Hero Image
Transform Your Bottom Line: Why Virtual Try-On Technology Is No Longer Optional

With U.S. retailers losing over $25 billion annually to online apparel returns, the traditional e-commerce model is broken. SeeOnMe’s latest analysis reveals how Virtual Try-On (VTON) technology isn’t just solving the fit crisis—it’s revolutionizing retail profitability. From dramatically reducing return rates to boosting conversion through customer confidence, VTON delivers measurable ROI that forward-thinking retailers can’t afford to ignore. Discover why the most innovative companies are growing 16% faster than their competitors and how SeeOnMe’s advanced 3D persona technology is leading this retail revolution. The question isn’t whether you can afford to implement VTON—it’s whether you can afford not to.

Monday, June 16, 2025 Read
Hero Image
Automated Book Summarization

In an era of information abundance, the ability to efficiently extract key insights from vast amounts of text has become an invaluable skill. This is particularly true for books, where complex narratives and intricate arguments can make it challenging to grasp the essence of a work. Consequently, automated book summarization techniques, which employ AI (more recently leveraging the power of Large Language Models (LLMs)) to distill lengthy texts into concise, informative summaries, have emerged as an increasingly reliable resource.

Wednesday, August 7, 2024 Read
Hero Image
Conversational Commerce: An Introduction

In April 2020 I have started working on a new project to revolutionize how customers shop. For that purpose, we have written a blog post introducing Farfetch Chat (previously known as iFETCH), a conversational AI technology with multimodal capabilities developed by FARFETCH in collaboration with Carnegie Mellon University (CMU), Instituto Superior Técnico (IST), and Universidade Nova de Lisboa (NOVA). Farfetch Chat aimed to revolutionize the online high-fashion sector by providing a “physical store”-like experience through natural interaction using both textual and visual data. The project focused on four pillars: natural language understanding and generation, dialogue management, product catalog and multimodal knowledge base, and product retrieval.

Friday, April 12, 2024 Read

Publications

Task Conditioned BERT for Joint Intent Detection and Slot-filling
EPIA Conference on Artificial Intelligence 2023
Tavares, Diogo Azevedo, Pedro Semedo, David Sousa, Ricardo Magalhaes, Joao

nlp conversaional ai
Fill in the Blank for Fashion Complementary Outfit Product Retrieval: VISUM Summer School Competition
Machine Vision and Applications 2022
Rebelo, Ana Afonso, Carolina Cimarelli, Claudio Castro, Eduardo Moreira, Gabriel Yang, Hsiu-yu Hrga, Ingrid Rio-Torto, Isabel Ahmad, Javed Capozzi, Leonardo Ferreira, Mafalda Falcão Keswani, Monish Daoudi, Nadia Ferreira, Pedro M. Sousa, Ricardo Gamelas Beco, Sofia Gonçalves, Tiago Albuquerque, Tomé Silva, Wilson

Computer Vision Competition
iFetch: Multimodal Conversational Agents for the Online Fashion Marketplace.
MuCAI'21: Proceedings of the 2nd ACM Multimedia Workshop on Multimodal Conversational AI, Virtual Event, China 20 October 2021
Sousa, Ricardo Gamelas Ferreira, Pedro Miguel Costa, Pedro Moreira Azevedo, Pedro Costeira, João Paulo Santiago, Carlos Magalhães, João Semedo, David Ferreira, Rafael Rudnicky, Alexander I. Hauptmann, Alexander G.

Machine Learning Conversational AI
Details
A Unified Model with Structured Output for Fashion Images Classification.
AI for Fashion Workshop, KDD 2018, London, United Kingdom 20 August 2018
Ferreira, Beatriz Quintino Baía, Luís Faria, João Sousa, Ricardo Gamelas

Computer Vision Image Search Online Shopping
Details
Measuring the Performance of Ordinal Classification
Int. J. Pattern Recognit. Artif. Intell. 2011
Cardoso, Jaime S. Sousa, Ricardo Gamelas

Machine Learning Ordinal Learning Metrics
Details
An Ordinal Data Method for the Classification with Reject Option
International Conference on Machine Learning and Applications, ICMLA 2009, Miami Beach, Florida, USA December 13, 2009
Sousa, Ricardo Gamelas Mora, Beatriz Cardoso, Jaime S.

Machine Learning Ordinal Learning Metrics
Details