Lemonari, MarilenaCharalambous, PanayiotisPanayiotou, AndreasChrysanthou, YiorgosPettré, JulienLiu, LingjieAverkiou, Melinos2024-04-302024-04-302024978-3-03868-239-41017-4656https://doi.org/10.2312/egp.20241039https://diglib.eg.org/handle/10.2312/egp20241039We aim to unravel complex agent-environment interactions from trajectories, by explaining agent paths as combinations of predefined basic behaviors. We detect trajectory points signifying environment-driven behavior changes, ultimately disentangling interactions in space and time; our framework can be used for environment synthesis and authoring, shown by our case studies.Attribution 4.0 International LicenseCCS Concepts: Computing methodologies → Image representations; Neural networks; Motion processingComputing methodologies → Image representationsNeural networksMotion processingBehavioral Landmarks: Inferring Interactions from Data10.2312/egp.202410392 pages