Saved in:
Bibliographic Details
Main Authors: Chen, Siran, Luo, Yuxiao, Ma, Yue, Qiao, Yu, Wang, Yali
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.04302
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929665113849856
author Chen, Siran
Luo, Yuxiao
Ma, Yue
Qiao, Yu
Wang, Yali
author_facet Chen, Siran
Luo, Yuxiao
Ma, Yue
Qiao, Yu
Wang, Yali
contents With the prevalence of Multimodal Large Language Models(MLLMs), autonomous driving has encountered new opportunities and challenges. In particular, multi-modal video understanding is critical to interactively analyze what will happen in the procedure of autonomous driving. However, videos in such a dynamical scene that often contains complex spatial-temporal movements, which restricts the generalization capacity of the existing MLLMs in this field. To bridge the gap, we propose a novel Hierarchical Mamba Adaptation (H-MBA) framework to fit the complicated motion changes in autonomous driving videos. Specifically, our H-MBA consists of two distinct modules, including Context Mamba (C-Mamba) and Query Mamba (Q-Mamba). First, C-Mamba contains various types of structure state space models, which can effectively capture multi-granularity video context for different temporal resolutions. Second, Q-Mamba flexibly transforms the current frame as the learnable query, and attentively selects multi-granularity video context into query. Consequently, it can adaptively integrate all the video contexts of multi-scale temporal resolutions to enhance video understanding. Via a plug-and-play paradigm in MLLMs, our H-MBA shows the remarkable performance on multi-modal video tasks in autonomous driving, e.g., for risk object detection, it outperforms the previous SOTA method with 5.5% mIoU improvement.
format Preprint
id arxiv_https___arxiv_org_abs_2501_04302
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle H-MBA: Hierarchical MamBa Adaptation for Multi-Modal Video Understanding in Autonomous Driving
Chen, Siran
Luo, Yuxiao
Ma, Yue
Qiao, Yu
Wang, Yali
Computer Vision and Pattern Recognition
Artificial Intelligence
With the prevalence of Multimodal Large Language Models(MLLMs), autonomous driving has encountered new opportunities and challenges. In particular, multi-modal video understanding is critical to interactively analyze what will happen in the procedure of autonomous driving. However, videos in such a dynamical scene that often contains complex spatial-temporal movements, which restricts the generalization capacity of the existing MLLMs in this field. To bridge the gap, we propose a novel Hierarchical Mamba Adaptation (H-MBA) framework to fit the complicated motion changes in autonomous driving videos. Specifically, our H-MBA consists of two distinct modules, including Context Mamba (C-Mamba) and Query Mamba (Q-Mamba). First, C-Mamba contains various types of structure state space models, which can effectively capture multi-granularity video context for different temporal resolutions. Second, Q-Mamba flexibly transforms the current frame as the learnable query, and attentively selects multi-granularity video context into query. Consequently, it can adaptively integrate all the video contexts of multi-scale temporal resolutions to enhance video understanding. Via a plug-and-play paradigm in MLLMs, our H-MBA shows the remarkable performance on multi-modal video tasks in autonomous driving, e.g., for risk object detection, it outperforms the previous SOTA method with 5.5% mIoU improvement.
title H-MBA: Hierarchical MamBa Adaptation for Multi-Modal Video Understanding in Autonomous Driving
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2501.04302