Image-text matching for large-scale book collections
A. Llabrés, A. U. Dey, D. Karatzas, and E. Valveny, “Image-text matching for large-scale book collections,” Jul. 29, 2024, arXiv: arXiv:2407.19812. doi: 10.48550/arXiv.2407.19812.
CV
I’m Artemis, a PhD student at the Computer Vision Center (CVC), in the Vision and Language group I’m doing research on multimodal models for Document Understanding.
Experience
- Research Engineer at Computer Vision Center (CVC)
🗓️ 09 2022 – present- Research Multimodal Transformers for Document Question Answering.
- Visual and Language Fusion for Automatic Inventory of Libraries and Supermarkets.
Research Assistant at Group of Interactive Coding of Images (GICI)
🗓️ 01 2021 – 11 2023- Research and Development of Coding Techniques for Satellite Imagery.
- Development of Deep Learning Algorithms for Remote Sensing.
- Collaborated on the Open-Source Python Library Experiment Notebook (enb)
- Designed and trained machine learning algorithms for animal welfare in the Clearfarm project.
Bachelor’s Thesis Student at Computer Vision Center (CVC)
🗓️ 11 2021 – 07 2022- Document Analysis Combining Vision and Natural Language.
- Developing Multi-Task Models for Document Analysis: Document Classification, Information Extraction, DocVQA.
- Read the thesis here
Lecturer at SCN2 Python Course for Scientific Programming
🗓️ 02 2021 (first edition) and 03 2022 (second edition)- Lecturer in an introductory Python course for scientific programming for members of the Societat Catalana de Nanociència i Nanotecnologia.
Education
Master’s Degree in Research and Innovation in Computer based Science and Engineering at Universitat Autònoma de Barcelona
🗓️ 09 2023 – 07 2024Bachelor’s Degree in Computational Mathematics and Data Analytics at Universitat Autònoma de Barcelona
🗓️ 09 2018 – 07 2022