MultiFuser: Multimodal Fusion Transformer for Enhanced Driver Action Recognition

TL;DR

MultiFuser is a novel multimodal transformer that effectively integrates various sensor data to improve driver action recognition, especially in challenging lighting conditions, by modeling cross-modal interactions and features.

Contribution

The paper introduces MultiFuser, a transformer-based model with Bi-decomposed Modules for cross-modal fusion, advancing driver behavior analysis in complex environments.

Findings

Outperforms existing methods on Drive&Act dataset

Effectively fuses multimodal data for robust recognition

Demonstrates improved accuracy in dark and gloomy conditions

Abstract

Driver action recognition, aiming to accurately identify drivers' behaviours, is crucial for enhancing driver-vehicle interactions and ensuring driving safety. Unlike general action recognition, drivers' environments are often challenging, being gloomy and dark, and with the development of sensors, various cameras such as IR and depth cameras have emerged for analyzing drivers' behaviors. Therefore, in this paper, we propose a novel multimodal fusion transformer, named MultiFuser, which identifies cross-modal interrelations and interactions among multimodal car cabin videos and adaptively integrates different modalities for improved representations. Specifically, MultiFuser comprises layers of Bi-decomposed Modules to model spatiotemporal features, with a modality synthesizer for multimodal features integration. Each Bi-decomposed Module includes a Modal Expertise ViT block for extracting modality-specific features and a Patch-wise Adaptive Fusion block for efficient cross-modal fusion. Extensive experiments are conducted on Drive&Act dataset and the results demonstrate the efficacy of our proposed approach.