HI THERE I’m Laia Tarrés
a Computer Vision PhD student based in sunny Barcelona.

  • 4+ Experience
  • 3 Different Projects
  • >100 Happy Students

About Me

On September 2021 I decided to explore more in depth the possibilities of Deep Learning to help the Deaf and hard of hearing community. This application enables the study of Computer Vision, Multi-modal Language Processing and Generative Models. So I enrolled to a PhD program and I hope to contibute to the field while learning and having fun :) At the same time, I am enjoying teaching Deep Learning to both undergraduate and graduate level.

Core Skills

  • Deep Learning
  • Transformers
  • Generative Models
  • Multi-Modal Language Processing
  • Sign Language Understanding
  • Python
  • Pytorch
  • Github

Other Skills

  • Lecturer
  • Preparing Lecture/Hands on Material
  • Event organizer
  • Matlab
  • C#
  • HTML
  • Voleyball
  • Euphonium + Trombone

Publications

  • [1] Tarrés, L; Gállego, GI; Giró-i-Nieto X; Torres J. Tackling Low-Resourced Sign Language Translation: UPC at WMT-SLT 22. @Eight Conference on Machine Translation (WMT), Sign Language Translation task (SLT) EMNLP 2022. [paper] [code] [poster]
  • [2] Budria A; Tarrés L; Gállego GI; Moreno F; Torres J; Giró-i-Nieto X. Topic Detection in Continuous Sign Language Videos. @Accessibility, Vision and Autonomy Meet Workshop (AVA), CVPR 2022. [paper] [code] [poster]
  • [3] Tarrés, L; Giró-i-Nieto, X, Mrak,M; Górriz, M. Working on image colourisation. @WiCV, CVPR 2021. [paper][poster]
  • [4] Moreno, A.; Bonafonte, A.; Jauk, I.; Tarrés, L.; Pereira, V. Corpus for cyberbullying prevention. IberSPEECH 2018. [paper]

Education

Sep. 2021 - Present

PhD candidate in Computer Architecture

Universitat Politecnica de Catalunya - Barcelona Supercomputing Center

Under the supervision of Prof. Jordi Torres (UPC-BSC) and Prof. Xavier Giró-i-Nieto (Amazon Research). My current research aims at developing systems that enable sign language users to have automatic ways of translating online content. I am currently leading the Speech2Signs project, formerly led by Amanda Duarte, that tackles the task of automatic speech to sign language translation and viceversa through Deep Learning.

I am also participating in the X-prize rainforest, on the Providence Plus team, lead by Ferran Marqués (UPC) and Antonio Torralba (MIT).

2019 - 2021

Masters in Advanced Telecommunication Technologies

Universitat Politecnica de Catalunya

Having selected the Multimedia Track, the program provides an understanding in depth on audiovisual systems, including deep learning techniques applied to language and vision.

2015 - 2019

Undergaduate in Telecommunications Technologies and Services Engineering

Universitat Politecnica de Catalunya

The program provides a solid grounding in the fundamentals of ICT engineering and the specific skills pertaining to the major I selected: Audiovisual Systems. Where I acquired the knowledge to conceive, design, implement and operate products, systems and services in the field of audiovisual systems engineering, including the fields of acoustics, image, audio, video and multimedia environments.

Other Professional Experience

Sep. 2022 - present

UPC School

Co-Director, together with Montse Pardàs of the 8th edition Posgraduate Course of Artificial Intelligence with Deep Learning

The postgraduate course is one of the best in its field. It provides a short yet intensive course on the basis on deep learning and focuses on: computer vision, language, video, reinforcement learning. The curriculum is constantly updated and the instructors are experts on their fields and at various stages of their careers.

  • Curriculum planning, budgeting and scheduling of instructors.
  • Providing support to both instructors and students.
Edition 2022

DeepLearning Barcelona Symposium

Organizer of the 4th edition of the DLBCN 22

The symposium aims at showcasing research on deep learning carried out by scientists in/from Barcelona. This edition will count with 1 keynoite, 41 speakers and 40 posters.

  • Planning and organizing the program and venue.
  • Providing support to presenters, sponsors and other organizers.

Teaching Experience

Selection of lessons imparted

  • Introduction to Deep Learning: Backpropagation, Tensors, Interpretability, MLP, CNN, Monitoring, Distillation [code]. Lab instructor.
  • Sequence Modeling: RNN, Attention [code], Transformers. Lab instructor.
  • Generative modeling: self-supervised, GAN, VAE and Diffusion models. Main theory and lab instructor.
  • Speech: Introduction to Speech, Speech Enhancement, ASR. Lab instructor.
  • Recommender systems: GCN and Recommender systems. Lab instructor.

Latest News

Responsive image

Sign Language Translation Task inside the 8th Conference on Machine Translation, at EMNLP22

Fall 2022

Happy that the paper has been accepted at EMNLP22 for the WMT-SLT challenge, and thankful for the people we will meet. The conference is held Abu Dhabi but we are presenting on GatherTown.

Responsive image

Presented a poster at the Accessibility, Vision and Autonomy Meet Workshop at CVPR22

Summer 2022

Our paper on Topic Detection was accepted as a poster in the Availability and Acessibility workshop (AVA) at CVPR22, held in New Orelans. The work was presented both orally and in a poster format. Meeting fellow researchers at CVPR was awesome!

Responsive image

Giving a Deep Learning conference in Dublin + ACL22

Spring 2022

I was invited, together with Prof. Xavier Giró and Gerard Ion Gállego, to give a seminar on self-supervised to students at the Insight Center phd program at DCU. I also took the opportunity to go to my first conference: ACL.

Responsive image

Presenting my Master Thesis at DLBCN21

Winter 2021

Presented the poster about my Master Thesis in the Deep Learning Barcelona Symposium, and saw how alive the Barcelona Deep Learning community is. I also volunteered to help.

Responsive image

Organizer social event Women in Computer Vision (WiCV) at Neurips 2020

Winter 2020

I took the opportunity to host a session, together with Francisca Cattan titled "Research and job opportunities for ML researchers coming from non-traditional career paths." It was hosted in Gather Town and it was a succes, with many interesting conversations.

Do you want to colaborate or are interested in what I do? Reach me!
© 2022 All rights reserved. Free minimal bootstrap template by Designstub.