# CCLSTM: Coupled Convolutional Long-Short Term Memory Network for Occupancy Flow Forecasting

arXiv: https://arxiv.org/abs/2506.06128 · HTML: https://mlsanity.com/paper/2506.06128/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 14 references that are in the map.
- First posted on arXiv 6 Jun 2025.

## Builds on (most cited first, 13 of 13)

- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset](https://mlsanity.com/paper/2104.10133/) (2021)
- [Unsupervised Learning of Video Representations using LSTMs](https://mlsanity.com/paper/1502.04681/) (2015)
- [Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?](https://mlsanity.com/paper/2206.07959/) (2022)
- [Occupancy Flow Fields for Motion Forecasting in Autonomous Driving](https://mlsanity.com/paper/2203.03875/) (2022)
- [Hybrid-Prediction Integrated Planning for Autonomous Driving](https://mlsanity.com/paper/2402.02426/) (2024)
- [HOPE: Hierarchical Spatial-temporal Network for Occupancy Flow Prediction](https://mlsanity.com/paper/2206.10118/) (2022)
- [STrajNet: Multi-modal Hierarchical Transformer for Occupancy Flow Field Prediction in Autonomous Driving](https://mlsanity.com/paper/2208.00394/) (2022)
- [OFMPNet: Deep End-to-End Model for Occupancy and Flow Prediction in Urban Environment](https://mlsanity.com/paper/2404.02263/) (2024)
- [VectorFlow: Combining Images and Vectors for Traffic Occupancy and Flow Prediction](https://mlsanity.com/paper/2208.04530/) (2022)
- [HGNET: A Hierarchical Feature Guided Network for Occupancy Flow Field Prediction](https://mlsanity.com/paper/2407.01097/) (2024)

## Abstract (arXiv)

Predicting future states of dynamic agents is a fundamental task in autonomous driving. An expressive representation for this purpose is Occupancy Flow Fields, which provide a scalable and unified format for modeling motion, spatial extent, and multi-modal future distributions. While recent methods have achieved strong results using this representation, they often depend on high-quality vectorized inputs, which are unavailable or difficult to generate in practice, and the use of transformer-based architectures, which are computationally intensive and costly to deploy. To address these issues, we propose Coupled Convolutional LSTM (CCLSTM), a lightweight, end-to-end trainable architecture based solely on convolutional operations. Without relying on vectorized inputs or self-attention mechanisms, CCLSTM effectively captures temporal dynamics and spatial occupancy-flow correlations using a compact recurrent convolutional structure. Despite its simplicity, CCLSTM achieves state-of-the-art performance on occupancy flow metrics and, as of this submission, ranks (1st) in all metrics on the 2024 Waymo Occupancy and Flow Prediction Challenge leaderboard.