410 citations
- Universitat Politècnica de CatalunyaES53 papers
- Consejo Superior de Investigaciones CientíficasES11 papers
- Carnegie Mellon UniversityUS3 papers
- Centre National de la Recherche ScientifiqueFR3 papers
- Italian Institute of TechnologyIT3 papers
- The University of Texas at AustinUS3 papers
- Aalto UniversityFI2 papers
- Barcelona Supercomputing CenterES2 papers
- California Institute of TechnologyUS2 papers
- CentraleSupélecFR2 papers
- Delft University of TechnologyNL2 papers
- ETH ZurichCH2 papers
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026★ 1 cited
Heteroscedastic Diffusion for Multi-Agent Trajectory Modeling
Guillem Capellera, Antonio Rubio, Luis Ferraz +1
Multi-agent trajectory modeling traditionally focuses on forecasting, often neglecting more general tasks like trajectory completion, which is essential for real-world applications…
cs.LG2019★ 11 cited
Learning event representations for temporal segmentation of image sequences by dynamic graph embedding
Mariella Dimiccoli, Herwig Wendt
Recently, self-supervised learning has proved to be effective to learn representations of events suitable for temporal segmentation in image sequences, where events are understood…
cs.LG2018
Possibility results for graph clustering: A novel consistency axiom
Fabio Strazzeri, Rubén J. Sánchez-García
Kleinberg introduced three natural clustering properties, or axioms, and showed they cannot be simultaneously satisfied by any clustering algorithm. We present a new clustering pro…