From the 1 of 8 linked papers with an AI index.
8 papers
Hierarchical Spatio-Temporal Transformer for Coherent Emergency Department Forecasting
Filipa Lino, Bárbara Tavares, Carlos Santiago +2
The paper introduces HierSTT, a hierarchical Transformer framework that jointly forecasts emergency department demand at hospital, regional, and national levels while enforcing cro…
Native Hierarchical and Compositional Representations with Subspace Embeddings
Gabriel Moreira, Zita Marinho, Manuel Marques +2
Traditional embeddings represent datapoints as vectors, which makes similarity easy to compute but limits how well they capture hierarchies and compositionality. We propose a funda…
Spectral Guidance for Flexible and Efficient Control of Diffusion Models
Gabriel Moreira, Manuel Marques, João Paulo Costeira +1
We introduce Spectral Guidance, a framework for controlling diffusion models by leveraging the intrinsic geometry of the generative process. As data is progressively corrupted by n…
Learning to See Like Humans: Gaze-Aligned Cycling Safety Prediction
LuÃs Maria Perdigão, Miguel Costa, Carlos Santiago +1
Cycling delivers significant public-health and environmental benefits, yet its uptake in cities is often limited by perceived safety. When street environments appear unsafe, indivi…
Face inpainting with Identity Preserving Latent Diffusion Models
João Santos, Carlos Santiago, Manuel Marques
Face inpainting techniques recover missing or occluded facial regions in a visually realistic manner, but preserving the identity in the final output remains a fundamental challeng…
Benchmarking 3D Human Pose Estimation Models under Occlusions
Filipa Lino, Carlos Santiago, Manuel Marques
Human Pose Estimation (HPE) involves detecting and localizing keypoints on the human body from visual data. In 3D HPE, occlusions, where parts of the body are not visible in the im…