I am currently a doctoral student in the Network and Information Technologies (NIT) program at the Universitat Oberta de Catalunya (UOC), advised by Prof. Agata Lapedriza. As a member of the AIWELL (AI for Human WELL-being) lab, I explore emotion understanding and model interpretability in multimodal systems.
Prior to my PhD, I earned a Bachelor's degree in Computer Science from the Universitat de Barcelona. I then worked for two years as a Data Scientist at DMD.Solutions, a consulting company focused on reliability and safety in the aerospace industry. After that, I completed a Master's in Computer Vision at the Universitat Autònoma de Barcelona, where I became increasingly interested in human-centered AI and multimodal systems.
I am actively collaborating with Northeastern University and the MIT CSAIL Vision Group in Antonio Torralba’s lab. As part of this collaboration, I completed two mid-term research visits to both institutions in 2024 and 2025. I also contributed to the organization of KDD 2024 in Barcelona and have served as a reviewer for WACV and CVPR 2025. I enjoy being involved in the academic community and regularly engage in research, reviewing, and event organization activities that support knowledge exchange and collaboration.
") does not match the recommended repository name for your site ("
").
", so that your site can be accessed directly at "http://
".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}
" in index.html
.
",
which does not match the baseurl
("
") configured in _config.yml
.
baseurl
in _config.yml
to "
".
Josep Lopez Camuñas, Cristina Bustos, Yanjun Zhu, Raquel Ros, Agata Lapedriza
Submitted to Winter Conference on Applications of Computer Vision (WACV) Workshops 2025
Understanding emotional signals in older adults is crucial for designing virtual assistants that support their well-being. However existing affective computing models often face significant limitations: (1) limited availability of datasets representing older adults especially in non-English-speaking populations and (2) poor generalization of models trained on younger or homogeneous demographics. To address these gaps this study...
Josep Lopez Camuñas, Cristina Bustos, Yanjun Zhu, Raquel Ros, Agata Lapedriza
Submitted to Winter Conference on Applications of Computer Vision (WACV) Workshops 2025
Understanding emotional signals in older adults is crucial for designing virtual assistants that support their well-being. However existing affective computing models often face significant limitations: (1) limited availability of datasets representing older adults especially in non-English-speaking populations and (2) poor generalization of models trained on younger or homogeneous demographics. To address these gaps this study...