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

arXiv: https://arxiv.org/abs/2605.04752 · HTML: https://mlsanity.com/paper/2605.04752/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 49 references that are in the map.
- First posted on arXiv 6 May 2026.

## Builds on (most cited first, 21 of 21)

- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [MViTv2: Improved Multiscale Vision Transformers for Classification and Detection](https://mlsanity.com/paper/2112.01526/) (2021)
- [GMFlow: Learning Optical Flow via Global Matching](https://mlsanity.com/paper/2111.13680/) (2021)
- [TEA: Temporal Excitation and Aggregation for Action Recognition](https://mlsanity.com/paper/2004.01398/) (2020)
- [TAM: Temporal Adaptive Module for Video Recognition](https://mlsanity.com/paper/2005.06803/) (2020)
- [The 5th AI City Challenge](https://mlsanity.com/paper/2104.12233/) (2021)
- [Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground](https://mlsanity.com/paper/2211.12883/) (2022)
- [Applications of deep learning in traffic congestion detection, prediction and alleviation: A survey](https://mlsanity.com/paper/2102.09759/) (2021)
- [Advancing Pavement Distress Detection in Developing Countries: A Novel Deep Learning Approach with Locally-Collected Datasets](https://mlsanity.com/paper/2408.05649/) (2024)
- [Integrating Travel Behavior Forecasting and Generative Modeling for Predicting Future Urban Mobility and Spatial Transformations](https://mlsanity.com/paper/2503.21158/) (2025)
- [Self-Supervised Multi-Scale Transformer with Attention-Guided Fusion for Efficient Crack Detection](https://mlsanity.com/paper/2510.10378/) (2025)
- [Task-Specific Dual-Model Framework for Comprehensive Traffic Safety Video Description and Analysis](https://mlsanity.com/paper/2510.11907/) (2025)
- [Seeing Beyond the Scene: Analyzing and Mitigating Background Bias in Action Recognition](https://mlsanity.com/paper/2512.17953/) (2025)
- [Comparing Optical Flow and Deep Learning to Enable Computationally Efficient Traffic Event Detection with Space-Filling Curves](https://mlsanity.com/paper/2408.00768/) (2024)
- [Demographics-Informed Neural Network for Multi-Modal Spatiotemporal forecasting of Urban Growth and Travel Patterns Using Satellite Imagery](https://mlsanity.com/paper/2506.12456/) (2025)
- [Research on Expressway Congestion Warning Technology Based on YOLOv11-DIoU and GRU-Attention](https://mlsanity.com/paper/2509.13361/) (2025)
- [PaveSync: A Unified and Comprehensive Dataset for Pavement Distress Analysis and Classification](https://mlsanity.com/paper/2512.20011/) (2025)

## Abstract (arXiv)

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. These complementary limitations motivate a unified framework that links motion evidence to spatial feature selection while preserving data-adaptive temporal characterization. This study therefore proposes FLO-EMD, a hybrid approach that couples motion-guided attention with empirical, data-driven temporal decomposition. Dense optical flow guides channel and spatial attention so that RGB features are refined toward motion-relevant regions. In parallel, aggregated flow statistics form compact motion traces that are decomposed using Empirical Mode Decomposition (EMD) to extract intrinsic temporal components. The resulting EMD embedding is fused with learned spatiotemporal representations to classify light, medium, and heavy congestion. Experiments on 1,050 five-second clips from four surveillance networks show that FLO-EMD achieves 97.5% overall test accuracy (weighted F1 = 0.9742), outperforming established baselines and remaining robust across diverse environmental conditions; ablation and sensitivity analyses further quantify the contributions of EMD, the number of intrinsic mode functions, and the selected motion descriptors.