Saved in:
Bibliographic Details
Main Authors: Kuang, Jian, Li, Wenjing, Li, Fang, Zhang, Jun, Wu, Zhongcheng
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.14115
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929223997849600
author Kuang, Jian
Li, Wenjing
Li, Fang
Zhang, Jun
Wu, Zhongcheng
author_facet Kuang, Jian
Li, Wenjing
Li, Fang
Zhang, Jun
Wu, Zhongcheng
contents Distracted driver activity recognition plays a critical role in risk aversion-particularly beneficial in intelligent transportation systems. However, most existing methods make use of only the video from a single view and the difficulty-inconsistent issue is neglected. Different from them, in this work, we propose a novel MultI-camera Feature Integration (MIFI) approach for 3D distracted driver activity recognition by jointly modeling the data from different camera views and explicitly re-weighting examples based on their degree of difficulty. Our contributions are two-fold: (1) We propose a simple but effective multi-camera feature integration framework and provide three types of feature fusion techniques. (2) To address the difficulty-inconsistent problem in distracted driver activity recognition, a periodic learning method, named example re-weighting that can jointly learn the easy and hard samples, is presented. The experimental results on the 3MDAD dataset demonstrate that the proposed MIFI can consistently boost performance compared to single-view models.
format Preprint
id arxiv_https___arxiv_org_abs_2401_14115
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MIFI: MultI-camera Feature Integration for Roust 3D Distracted Driver Activity Recognition
Kuang, Jian
Li, Wenjing
Li, Fang
Zhang, Jun
Wu, Zhongcheng
Computer Vision and Pattern Recognition
Distracted driver activity recognition plays a critical role in risk aversion-particularly beneficial in intelligent transportation systems. However, most existing methods make use of only the video from a single view and the difficulty-inconsistent issue is neglected. Different from them, in this work, we propose a novel MultI-camera Feature Integration (MIFI) approach for 3D distracted driver activity recognition by jointly modeling the data from different camera views and explicitly re-weighting examples based on their degree of difficulty. Our contributions are two-fold: (1) We propose a simple but effective multi-camera feature integration framework and provide three types of feature fusion techniques. (2) To address the difficulty-inconsistent problem in distracted driver activity recognition, a periodic learning method, named example re-weighting that can jointly learn the easy and hard samples, is presented. The experimental results on the 3MDAD dataset demonstrate that the proposed MIFI can consistently boost performance compared to single-view models.
title MIFI: MultI-camera Feature Integration for Roust 3D Distracted Driver Activity Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.14115