publications

2026

1. AAAI

   FineVAU: A Novel Human-Aligned Benchmark for Fine-Grained Video Anomaly Understanding

   João Cardeira, Vasco Lopes, João C. Neves, and 1 more author

   In Proceedings of the AAAI Conference on Artificial Intelligence, 2026

   DOI Bib HTML Website

   @inproceedings{cardeira2026finevau,
     title = {FineVAU: A Novel Human-Aligned Benchmark for Fine-Grained Video Anomaly Understanding},
     author = {Cardeira, Jo{\~a}o and Lopes, Vasco and Neves, Jo{\~a}o C. and Semedo, David},
     booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
     volume = {40},
     number = {10},
     pages = {8403--8411},
     year = {2026},
     doi = {10.1609/aaai.v40i10.37790},
   }

2. arXiv

   AMALIA-VL: A Native European Portuguese Open-Source Vision and Language Model

   Diogo Glória-Silva, João Cardeira, Manuel Letras Luz, and 8 more authors

   arXiv preprint arXiv:2606.19100, 2026

   arXiv Bib Code Website

   @article{gloriasilva2026amaliavl,
     title = {AMALIA-VL: A Native European Portuguese Open-Source Vision and Language Model},
     author = {Gl{\'o}ria-Silva, Diogo and Cardeira, Jo{\~a}o and da Luz, Manuel Letras and Simpl{\'i}cio, Afonso and Vinagre, Gon{\c{c}}alo and Tavares, Diogo and Ferreira, Rafael and Calvo, In{\e}s and Vieira, In{\e}s and Semedo, David and Magalh{\~a}es, Jo{\~a}o},
     journal = {arXiv preprint arXiv:2606.19100},
     year = {2026},
   }

3. arXiv

   PorTEXTO: A European Portuguese Benchmark for Visual Text Extraction

   João Cardeira, Diogo Glória-Silva, Manuel Letras Luz, and 4 more authors

   arXiv preprint arXiv:2606.19096, 2026

   arXiv Bib Website

   @article{cardeira2026portexto,
     title = {PorTEXTO: A European Portuguese Benchmark for Visual Text Extraction},
     author = {Cardeira, Jo{\~a}o and Gl{\'o}ria-Silva, Diogo and da Luz, Manuel Letras and Ferreira, Rafael and Tavares, Diogo and Semedo, David and Magalh{\~a}es, Jo{\~a}o},
     journal = {arXiv preprint arXiv:2606.19096},
     year = {2026},
   }

2025

1. ICME

   Self-ReS: Self-Reflection in Large Vision-Language Models for Long Video Understanding

   João Cardeira, Vasco Lopes, David Semedo, and 1 more author

   In IEEE International Conference on Multimedia and Expo (ICME), 2025

   Bib HTML

   @inproceedings{cardeira2025selfres,
     title = {Self-ReS: Self-Reflection in Large Vision-Language Models for Long Video Understanding},
     author = {Cardeira, Jo{\~a}o and Lopes, Vasco and Semedo, David and Neves, Jo{\~a}o C.},
     booktitle = {IEEE International Conference on Multimedia and Expo (ICME)},
     pages = {1--9},
     year = {2025},
   }

2. arXiv

   Chain-of-Anomaly Thoughts with Large Vision-Language Models

   Pedro Domingos, João Cardeira, Vasco Lopes, and 2 more authors

   arXiv preprint arXiv:2512.20417, 2025

   arXiv Bib

   @article{domingos2025chainofanomaly,
     title = {Chain-of-Anomaly Thoughts with Large Vision-Language Models},
     author = {Domingos, Pedro and Cardeira, Jo{\~a}o and Lopes, Vasco and Neves, Jo{\~a}o C. and Semedo, David},
     journal = {arXiv preprint arXiv:2512.20417},
     year = {2025},
   }

3. IbPRIA

   Towards Event-Driven Evaluation of Surveillance Video Understanding Using Natural Language

   João Cardeira, Vasco Lopes, João C. Neves, and 1 more author

   In Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA), 2025

   Bib HTML

   @inproceedings{cardeira2025eventdriven,
     title = {Towards Event-Driven Evaluation of Surveillance Video Understanding Using Natural Language},
     author = {Cardeira, Jo{\~a}o and Lopes, Vasco and Neves, Jo{\~a}o C. and Semedo, David},
     booktitle = {Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA)},
     pages = {43--55},
     year = {2025},
   }

2024

1. arXiv

   Zero-Shot Action Recognition in Surveillance Videos

   João Cardeira, Vasco Lopes, David Semedo, and 1 more author

   arXiv preprint arXiv:2410.21113, 2024

   arXiv Bib

   @article{cardeira2024zeroshot,
     title = {Zero-Shot Action Recognition in Surveillance Videos},
     author = {Cardeira, Jo{\~a}o and Lopes, Vasco and Semedo, David and Neves, Jo{\~a}o C.},
     journal = {arXiv preprint arXiv:2410.21113},
     year = {2024},
   }

2023

1. MSc

   Real-Time Human Action Localization in the Wild

   João Cardeira

   NOVA School of Science and Technology, 2023

   Bib

   @mastersthesis{cardeira2023msc,
     title = {Real-Time Human Action Localization in the Wild},
     author = {Cardeira, Jo{\~a}o},
     school = {NOVA School of Science and Technology},
     year = {2023},
   }