Saved in:
Bibliographic Details
Main Authors: Yang, Haoxiang, Yuan, Chengguo, Zhu, Yabin, Chen, Lan, Wang, Xiao, Wang, Futian
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.11123
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914947570597888
author Yang, Haoxiang
Yuan, Chengguo
Zhu, Yabin
Chen, Lan
Wang, Xiao
Wang, Futian
author_facet Yang, Haoxiang
Yuan, Chengguo
Zhu, Yabin
Chen, Lan
Wang, Xiao
Wang, Futian
contents The mainstream human activity recognition (HAR) algorithms are developed based on RGB cameras, which are easily influenced by low-quality images (e.g., low illumination, motion blur). Meanwhile, the privacy protection issue caused by ultra-high definition (HD) RGB cameras aroused more and more people's attention. Inspired by the success of event cameras which perform better on high dynamic range, no motion blur, and low energy consumption, we propose to recognize human actions based on the event stream. We propose a lightweight uncertainty-aware information propagation based Mobile-Former network for efficient pattern recognition, which aggregates the MobileNet and Transformer network effectively. Specifically, we first embed the event images using a stem network into feature representations, then, feed them into uncertainty-aware Mobile-Former blocks for local and global feature learning and fusion. Finally, the features from MobileNet and Transformer branches are concatenated for pattern recognition. Extensive experiments on multiple event-based recognition datasets fully validated the effectiveness of our model. The source code of this work will be released at https://github.com/Event-AHU/Uncertainty_aware_MobileFormer.
format Preprint
id arxiv_https___arxiv_org_abs_2401_11123
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Uncertainty-aware Bridge based Mobile-Former Network for Event-based Pattern Recognition
Yang, Haoxiang
Yuan, Chengguo
Zhu, Yabin
Chen, Lan
Wang, Xiao
Wang, Futian
Computer Vision and Pattern Recognition
The mainstream human activity recognition (HAR) algorithms are developed based on RGB cameras, which are easily influenced by low-quality images (e.g., low illumination, motion blur). Meanwhile, the privacy protection issue caused by ultra-high definition (HD) RGB cameras aroused more and more people's attention. Inspired by the success of event cameras which perform better on high dynamic range, no motion blur, and low energy consumption, we propose to recognize human actions based on the event stream. We propose a lightweight uncertainty-aware information propagation based Mobile-Former network for efficient pattern recognition, which aggregates the MobileNet and Transformer network effectively. Specifically, we first embed the event images using a stem network into feature representations, then, feed them into uncertainty-aware Mobile-Former blocks for local and global feature learning and fusion. Finally, the features from MobileNet and Transformer branches are concatenated for pattern recognition. Extensive experiments on multiple event-based recognition datasets fully validated the effectiveness of our model. The source code of this work will be released at https://github.com/Event-AHU/Uncertainty_aware_MobileFormer.
title Uncertainty-aware Bridge based Mobile-Former Network for Event-based Pattern Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.11123