可靠且稳健的用户识别与身份认证是许多数字服务中重要且往往必要的需求。在社交虚拟现实(VR)中,这一点变得至关重要,尤其是在与逼真、栩栩如生的虚拟化身进行数字接触时,这些化身是真实人物的忠实复制。近期研究表明,用户在扩展现实(XR)系统中的运动携带用户特定信息,因此可用于验证其身份。本文比较了来自头部和手部的运动数据的三种不同潜在编码方式(场景相对、身体相对和身体相对速度),以及五种不同机器学习架构(随机森林、多层感知机、全循环神经网络、长短期记忆网络、门控循环单元)的性能。我们使用公开数据集“Talking with Hands”,并公开所有代码,以保证可复现性并为未来工作提供基线。经过超参数优化后,长短期记忆网络架构与身体相对数据的组合优于其他竞争组合:该模型在150秒内以100%的准确率正确识别34名受试者中的任意一位。总体而言,我们的方法为基于行为计量的识别与认证提供了有效基础,可为研究人员和实践者提供指导。数据和代码已发布在 https://go.uniwue.de/58w1r。
英文摘要:
Reliable and robust user identification and authentication are important and often necessary requirements for many digital services. It becomes paramount in social virtual reality (VR) to ensure trust, specifically in digital encounters with lifelike realistic-looking avatars as faithful replications of real persons. Recent research has shown that the movements of users in extended reality (XR) systems carry user-specific information and can thus be used to verify their identities. This article compares three different potential encodings of the motion data from head and hands (scene-relative, body-relative, and body-relative velocities), and the performances of five different machine learning architectures (random forest, multi-layer perceptron, fully recurrent neural network, long-short term memory, gated recurrent unit). We use the publicly available dataset "Talking with Hands" and publish all code to allow reproducibility and to provide baselines for future work. After hyperparameter optimization, the combination of a long-short term memory architecture and body-relative data outperformed competing combinations: the model correctly identifies any of the 34 subjects with an accuracy of 100% within 150 seconds. Altogether, our approach provides an effective foundation for behaviometric-based identification and authentication to guide researchers and practitioners. Data and code are published under https://go.uniwue.de/58w1r.
Identification Methods With Arbitrary Interventional Distributions as Inputs
Johns Hopkins University(约翰斯·霍普金斯大学)
因果推断通过估计数据中的反事实参数来量化因果关系。这需要使用\emph{identification theory}在感兴趣的反事实参数和数据可用的分布之间建立联系。一系列工作的特点是非参数识别的各种因果参数的\emph{observed data distribution}。最近,识别结果已扩展到设置中的实验数据从干预分布也是可用的。在本文中,我们使用单世界干预图和嵌套因式分解的模型与混合图给出了一个非常简单的视图,现有的识别理论的实验数据。我们使用这种观点来产生一般的识别算法的设置,其中输入分布包括一组任意的观测和实验分布,包括边际和条件分布。我们表明,对于问题的输入是干预边缘分布的某种类型(祖先边缘),我们的算法是完整的。
Identification of Causal Direction under an Arbitrary Number of Latent Confounders
School of Computer Science, Guangdong University of Technology(广东技术大学计算机科学学院);Department of Philosophy, Carnegie Mellon University(卡内基梅隆大学哲学系);College of Engineering, Shantou University(汕头大学工程学院);Peng Cheng Laboratory, Shenzhen, China(深圳鹏城实验室);Mohamed bin Zayed University of Artificial Intelligence(莫扎德大学人工智能大学)
Improving Vehicle Re-Identification using CNN Latent Spaces: Metrics Comparison and Track-to-track Extension
Institut de Recherche en Informatique de Toulouse(图卢兹计算机科学研究所);Université de Toulouse(图卢兹大学);Solution Data Group, IA department(Solution Data Group(人工智能部门));École nationale supérieure des mines d’Alès(阿尔勒国立高等矿业学校);Toulouse(图卢兹)