Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
portfolio
publications
Superformer: Volumetric transformer architectures for mri super-resolution
Published in SASHIMI Workshop - MICCAI 2022, 2022
A 3D Swin-Transformer-based model that uses local self-attention with volumetric and feature-domain fusion to enhance MRI resolution.
Recommended citation: Forigua, C., Escobar, M., & Arbelaez, P. (2022, September). Superformer: Volumetric transformer architectures for mri super-resolution. In International workshop on simulation and synthesis in medical imaging (pp. 132-141). Cham: Springer International Publishing.
Download Paper | Download Bibtex
EgoCOL: Egocentric Camera pose estimation for Open-world 3D object Localization@ Ego4D challenge 2023
Published in Ego4D challenge at CVPR 2023, 2023
A dual-reconstruction egocentric camera pose estimation method that boosts recall and precision for open-world 3D object localization in the Ego4D VQ3D challenge.
Recommended citation: Forigua, C., Escobar, M., Pont-Tuset, J., Maninis, K. K., & Arbeláez, P. (2023). EgoCOL: Egocentric Camera pose estimation for Open-world 3D object Localization@ Ego4D challenge 2023. arXiv preprint arXiv:2306.16606.
Download Paper | Download Bibtex
Ego-exo4d: Understanding skilled human activity from first-and third-person perspectives
Published in CVPR 2024 (Oral presentation), 2024
A large-scale multimodal dataset capturing synchronized egocentric and exocentric video of skilled human activities.
Recommended citation: Grauman, K., Westbury, A., Torresani, L., Kitani, K., Malik, J., Afouras, T., ... & Wray, M. (2024). Ego-exo4d: Understanding skilled human activity from first-and third-person perspectives. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 19383-19400).
Download Paper | Download Bibtex
Egocast: Forecasting egocentric human pose in the wild
Published in WACV 2025, 2025
A bimodal Transformer that forecasts future 3D body poses from first-person video and headset motion using pseudo-ground-truth estimation.
Recommended citation: Escobar, M., Puentes, J., Forigua, C., Pont-Tuset, J., Maninis, K. K., & Arbelaez, P. (2025, February). Egocast: Forecasting egocentric human pose in the wild. In 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (pp. 5831-5841). IEEE.
Download Paper | Download Bibtex
New algorithms for unsupervised cell clustering from scRNA-seq data
Published in Bioinformatics Advances, 2025
Novel k-MST graph-based clustering methods tailored for unsupervised identification of cell types from single-cell RNA-seq datasets.
Recommended citation: Robles, M., Díaz-Riaño, J., Forigua, C., Ojeda, S., Guio, L., Siaucho, P., ... & Duitama, J. (2025). New algorithms for unsupervised cell clustering from scRNA-seq data. Bioinformatics Advances.
Download Paper | Download Bibtex