Hybrid Congestion Classification Framework Using Flow-Guided Attention and Empirical Mode Decomposition

ArXi:2605.04752v1 Announce Type: cross Accurate traffic congestion classification requires models that jointly capture roadway scene context and non-stationary traffic motion, yet most prior work treats these requirements in isolation. Vision-based methods often depend on appearance cues with standard temporal pooling, which can bias predictions toward static infrastructure, whereas signal-based approaches characterize temporal dynamics but lack the spatial context needed for scene-level localization.