Juanpablo Heredia
I am a PhD student in data science, currently affiliated with the Visual Data Science Lab at Fundação Getulio Vargas (FGV), Rio de Janeiro, Brazil, under the supervision of Prof. Jorge Poco. I hold a full doctoral scholarship from FAPESP (São Paulo Research Foundation) in the Direct Doctoral modality.
My work focuses on spatiotemporal data analysis and visual analytics, with particular interest in geometric deep learning and explainable AI.
Previously, I was a researcher in the RUTAS project at Universidad Católica San Pablo (UCSP) in Arequipa, Peru, where I worked on computer vision and multimodal deep learning. I hold a BSc in Computer Science (2021) from the Computer Science Department at UCSP.
selected publications
-
Topology-Aware Visual Analysis of GNN Explanations in Dynamic GraphsComputer Graphics Forum (Proc. EuroVis) - Posters and Demos, 2026 -
URBANCLIPATLAS: A Visual Analytics Framework for Event and Scene Retrieval in Urban VideosComputer Graphics Forum (Proc. EuroVis), 2026 -
Interactive Exploration and Explanation of Spatio-Temporal Anomalies with Graph-LLM IntegrationIn 38th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), 2025 -
Adaptive multimodal emotion detection architecture for social robotsIeee Access, 2022 -
A multi-modal visual emotion recognition method to instantiate an ontologyIn 16th International conference on software technologies, 2021