# TEM^3-Learning: Time-Efficient Multimodal Multi-Task Learning for Advanced Assistive Driving

arXiv: https://arxiv.org/abs/2506.18084 · HTML: https://mlsanity.com/paper/2506.18084/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Video, motion and generative Mamba models, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 29 of its 57 references that are in the map.
- First posted on arXiv 22 Jun 2025.

## Placed in

- State-space sequence models (S4, Mamba) / [Video, motion and generative Mamba models](https://mlsanity.com/ssm/video-motion-and-generative-mamba-models/)

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?](https://mlsanity.com/paper/1711.09577/) (2017)
- [CMT: Convolutional Neural Networks Meet Vision Transformers](https://mlsanity.com/paper/2107.06263/) (2021)
- [OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception](https://mlsanity.com/paper/2303.03991/) (2023)
- [FusionPainting: Multimodal Fusion with Adaptive Attention for 3D Object Detection](https://mlsanity.com/paper/2106.12449/) (2021)
- [YOLOP: You Only Look Once for Panoptic Driving Perception](https://mlsanity.com/paper/2108.11250/) (2021)
- [Knowledge Distillation for Multi-task Learning](https://mlsanity.com/paper/2007.06889/) (2020)
- [Multi-task Learning with Attention for End-to-end Autonomous Driving](https://mlsanity.com/paper/2104.10753/) (2021)
- [EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2112.11088/) (2021)
- [AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception](https://mlsanity.com/paper/2307.13933/) (2023)
- [Cross-Task Knowledge Distillation in Multi-Task Recommendation](https://mlsanity.com/paper/2202.09852/) (2022)
- [Relational Multi-Task Learning: Modeling Relations between Data and Tasks](https://mlsanity.com/paper/2303.07666/) (2023)
- [Multi-modal Fusion Technology based on Vehicle Information: A Survey](https://mlsanity.com/paper/2211.06080/) (2022)
- [MMTL-UniAD: A Unified Framework for Multimodal and Multi-Task Learning in Assistive Driving Perception](https://mlsanity.com/paper/2504.02264/) (2025)
- [Multi-task Learning for Real-time Autonomous Driving Leveraging Task-adaptive Attention Generator](https://mlsanity.com/paper/2403.03468/) (2024)
- [Path Planning for Air-Ground Robot Considering Modal Switching Point Optimization](https://mlsanity.com/paper/2305.08178/) (2023)
- [MIPD: A Multi-sensory Interactive Perception Dataset for Embodied Intelligent Driving](https://mlsanity.com/paper/2411.05881/) (2024)
- [VM-BHINet:Vision Mamba Bimanual Hand Interaction Network for 3D Interacting Hand Mesh Recovery From a Single RGB Image](https://mlsanity.com/paper/2504.14618/) (2025)

## Built on by (most cited first, 3 of 3)

- [Driver-WM: A Driver-Centric Traffic-Conditioned Latent World Model for In-Cabin Dynamics Rollout](https://mlsanity.com/paper/2605.05092/) (2026)
- [UV-M3TL: A Unified and Versatile Multimodal Multi-Task Learning Framework for Assistive Driving Perception](https://mlsanity.com/paper/2602.01594/) (2026)
- [CrossRay3D: Geometry and Distribution Guidance for Efficient Multimodal 3D Detection](https://mlsanity.com/paper/2510.15991/) (2025)

## Abstract (arXiv)

Multi-task learning (MTL) can advance assistive driving by exploring inter-task correlations through shared representations. However, existing methods face two critical limitations: single-modality constraints limiting comprehensive scene understanding and inefficient architectures impeding real-time deployment. This paper proposes TEM^3-Learning (Time-Efficient Multimodal Multi-task Learning), a novel framework that jointly optimizes driver emotion recognition, driver behavior recognition, traffic context recognition, and vehicle behavior recognition through a two-stage architecture. The first component, the mamba-based multi-view temporal-spatial feature extraction subnetwork (MTS-Mamba), introduces a forward-backward temporal scanning mechanism and global-local spatial attention to efficiently extract low-cost temporal-spatial features from multi-view sequential images. The second component, the MTL-based gated multimodal feature integrator (MGMI), employs task-specific multi-gating modules to adaptively highlight the most relevant modality features for each task, effectively alleviating the negative transfer problem in MTL. Evaluation on the AIDE dataset, our proposed model achieves state-of-the-art accuracy across all four tasks, maintaining a lightweight architecture with fewer than 6 million parameters and delivering an impressive 142.32 FPS inference speed. Rigorous ablation studies further validate the effectiveness of the proposed framework and the independent contributions of each module. The code is available on https://github.com/Wenzhuo-Liu/TEM3-Learning.