# A Driving Behavior Recognition Model with Bi-LSTM and Multi-Scale CNN

arXiv: https://arxiv.org/abs/2103.00801 · HTML: https://mlsanity.com/paper/2103.00801/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 23 references that are in the map.
- First posted on arXiv 1 Mar 2021.

## Builds on (most cited first, 8 of 8)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Bidirectional LSTM-CRF Models for Sequence Tagging](https://mlsanity.com/paper/1508.01991/) (2015)
- [Multi-Modal Trajectory Prediction of Surrounding Vehicles with Maneuver based LSTMs](https://mlsanity.com/paper/1805.05499/) (2018)
- [How would surround vehicles move? A Unified Framework for Maneuver Classification and Motion Prediction](https://mlsanity.com/paper/1801.06523/) (2018)
- [BLVD: Building A Large-scale 5D Semantics Benchmark for Autonomous Driving](https://mlsanity.com/paper/1903.06405/) (2019)
- [Online Vehicle Trajectory Prediction using Policy Anticipation Network and Optimization-based Context Reasoning](https://mlsanity.com/paper/1903.00847/) (2019)

## Built on by (most cited first, 2 of 2)

- [A Fast and Map-Free Model for Trajectory Prediction in Traffics](https://mlsanity.com/paper/2307.09831/) (2023)
- [Vehicle Behavior Prediction by Episodic-Memory Implanted NDT](https://mlsanity.com/paper/2402.08423/) (2024)

## Abstract (arXiv)

In autonomous driving, perceiving the driving behaviors of surrounding agents is important for the ego-vehicle to make a reasonable decision. In this paper, we propose a neural network model based on trajectories information for driving behavior recognition. Unlike existing trajectory-based methods that recognize the driving behavior using the hand-crafted features or directly encoding the trajectory, our model involves a Multi-Scale Convolutional Neural Network (MSCNN) module to automatically extract the high-level features which are supposed to encode the rich spatial and temporal information. Given a trajectory sequence of an agent as the input, firstly, the Bi-directional Long Short Term Memory (Bi-LSTM) module and the MSCNN module respectively process the input, generating two features, and then the two features are fused to classify the behavior of the agent. We evaluate the proposed model on the public BLVD dataset, achieving a satisfying performance.