Social activation improves human trajectory predictions in crowds
GEAR: From Dynamic Encoding to Dynamic Activation in Social Trajectory Prediction
Computer Vision and Pattern RecognitionArtificial Intelligence
Summary
Predicting how people move in crowds needs understanding both how each person moves alone and how they interact with others. Many existing approaches focus on capturing social information but don’t clearly decide when or how much that social info should influence future steps. The authors propose a new model called GEAR that adjusts how strongly social and individual movement cues affect predictions at each moment. This lets the model better figure out when social interactions matter, improving its accuracy in predicting paths in busy scenes like sidewalks and basketball courts.
What this means in practice
- •For autonomous vehicle developers: Improve pedestrian path predictions in crowded environments by dynamically controlling social interaction influence during trajectory generation.
- •For sports analytics teams: Enhance player movement forecasting by adjusting social activation strengths to better capture interactions on courts or fields.
Authors
Jiaheng Chen, Jiaxing Li, Leixia Wang, Jianan Ju, Tinghe Zhang
Abstract
Human trajectory prediction requires modeling both individual motion patterns and social interactions among agents. Existing methods have made substantial progress by using attention mechanisms, graph structures, and temporal encoders to capture dynamic social context. However, most of them primarily focus on how social information is encoded, while paying less explicit attention to how the encoded social context should take effect during future trajectory generation. In this paper, we argue that dynamic social encoding does not necessarily imply dynamic social activation. The same interaction context may require different activation strengths across future horizons and scene densities: social cues should be strengthened when interaction evidence is strong, but suppressed when they are weak or noisy. To address this issue, we propose GEAR, a generation-aware bias activation model for human trajectory prediction. Built upon a bias-decomposed trajectory generation formulation, GEAR dynamically activates the individual-motion and social-resonance bias terms at each future step before final trajectory composition. This allows the model to explicitly control when and how strongly individual and social bias components participate in generation. Experiments on ETH-UCY, SDD, and NBA show that GEAR consistently improves the resonance-based baseline and achieves competitive state-of-the-art performance. Further analyses of activation patterns and density-grouped errors validate the importance of calibrating encoded social context during trajectory generation. Our code is available at https://github.com/11isnotavailable/GEAR.git.