arXiv subjects

Mark Roman Miller

Publications and source records attributed to Mark Roman Miller.

7 recordsLinked to original sources

arXiv2025

Cognitive State Inference from VR Motion via Motion Foundation Model

As virtual reality (VR) becomes widespread, head and hand motion data captured by consumer systems has become substantially more common. However, the extent of what can be inferred from such motion remains unclear. This paper investigates whether transient cognitive states, specifically confusion, hesitation, and readiness during different stages of decision-making, can be inferred from VR telemetry alone. We introduce a novel dataset of head and hand motion collected during structured decision-making tasks, with frame-level annotations of these states. We evaluate classical machine learning models, temporal neural networks, and motion foundation models under two protocols: (1) future-in-time prediction for the same users, and (2) cross-user generalization to unseen users. We further propose a VR-native motion adapter that maps sparse VR telemetry to representations compatible with motion foundation models pretrained on large-scale full-body motion data, enabling transfer without explicit full-body reconstruction. To our knowledge, this is the first work to adapt a motion foundation model to VR motion for a classification task. Results show that motion-only sensing captures meaningful signals of cognitive states, and that pretrained motion foundation models generalize more effectively than classical and temporal models even with a small dataset of 24 participants. Our approach achieves 82% accuracy, comparable to and sometimes surpassing human observers. These findings suggest that VR motion encodes richer behavioral information than previously assumed and highlight the potential of large-scale motion pretraining for XR applications. We will release the dataset and modeling framework to support future research.

cs.HC↗

arXiv2025

Experience Level Influences User's Criteria for Avatar Animation Realism

The sense of realism in avatar animation is a widely pursued goal in social VR applications. A common approach to enhancing realism is improving the match between avatar motion and real-world human movement. However, experience with existing VR platforms may reshape users' expectations, suggesting that matching reality is not the only path to enhancing the sense of realism. This study examines how different levels of experience with a social VR platform influence users' criteria for evaluating the realism of avatar animation. Participants were shown a set of animations varying in the degree they reflected real-world motion and motion seen on the social VR platform VRChat. Results showed that users with no VRChat experience found animations recorded on VRChat unnatural and unrealistic, but experienced users in fact rated these animations as more likely to come from a real person than the motion-capture animations. Additionally, highly experienced users recognized the intent to imitate VRChat's style and noted the differences from genuine in-platform animations. All these results suggest users' expectations of and criteria for realistic animation were shaped by their experience level. The findings support the idea that realism in avatar animation does not solely depend on mimicking real-world movement. Experience with VR platforms can shape how users expect, perceive, and evaluate animation realism. This insight can inform the design of more immersive VR environments and virtual humans in the future.

cs.HC↗

arXiv2024

Virtual Reality for Action Evaluation

Physical rehabilitation plays a crucial role in restoring functional abilities, but traditional approaches often face challenges in terms of cost, accessibility, and personalized monitoring. Asynchronous physical rehabilitation has gained traction as a cost-effective and convenient alternative, but it lacks real-time monitoring and assessment capabilities. This study investigates the feasibility of using low-cost Virtual Reality (VR) devices for action evaluation in rehabilitation exercises. We leverage state-of-the-art deep learning models and evaluate their performance on three data streams (head and hands) derived from existing rehabilitation datasets that approximate VR headset and hand data. Our results demonstrate that VR tracking data can be effectively utilized for action evaluation, paving the way for more accessible and affordable remote monitoring solutions in physical therapy. By leveraging artificial intelligence techniques and consumer-grade virtual reality technology, this study proposes an approach that could potentially address some of the challenges in asynchronous rehabilitation, such as the need for expensive motion capture systems or in-person sessions.

cs.HC↗

arXiv2024

Effect of Duration and Delay on the Identifiability of VR Motion

Social virtual reality is an emerging medium of communication. In this medium, a user's avatar (virtual representation) is controlled by the tracked motion of the user's headset and hand controllers. This tracked motion is a rich data stream that can leak characteristics of the user or can be effectively matched to previously-identified data to identify a user. To better understand the boundaries of motion data identifiability, we investigate how varying training data duration and train-test delay affects the accuracy at which a machine learning model can correctly classify user motion in a supervised learning task simulating re-identification. The dataset we use has a unique combination of a large number of participants, long duration per session, large number of sessions, and a long time span over which sessions were conducted. We find that training data duration and train-test delay affect identifiability; that minimal train-test delay leads to very high accuracy; and that train-test delay should be controlled in future experiments.

cs.CR↗

arXiv2024

Effect of Data Degradation on Motion Re-Identification

The use of virtual and augmented reality devices is increasing, but these sensor-rich devices pose risks to privacy. The ability to track a user's motion and infer the identity or characteristics of the user poses a privacy risk that has received significant attention. Existing deep-network-based defenses against this risk, however, require significant amounts of training data and have not yet been shown to generalize beyond specific applications. In this work, we study the effect of signal degradation on identifiability, specifically through added noise, reduced framerate, reduced precision, and reduced dimensionality of the data. Our experiment shows that state-of-the-art identification attacks still achieve near-perfect accuracy for each of these degradations. This negative result demonstrates the difficulty of anonymizing this motion data and gives some justification to the existing data- and compute-intensive deep-network based methods.

cs.CR↗

arXiv2023

A Large-Scale Study of Personal Identifiability of Virtual Reality Motion Over Time

In recent years, social virtual reality (VR), sometimes described as the "metaverse," has become widely available. With its potential comes risks, including risks to privacy. To understand these risks, we study the identifiability of participants' motion in VR in a dataset of 232 VR users with eight weekly sessions of about thirty minutes each, totaling 764 hours of social interaction. The sample is unique as we are able to study the effect of user, session, and time independently. We find that the number of sessions recorded greatly increases identifiability, and duration per session increases identifiability as well, but to a lesser degree. We also find that greater delay between training and testing sessions reduces identifiability. Ultimately, understanding the identifiability of VR activities will help designers, security professionals, and consumer advocates make VR safer.

cs.CR↗

arXiv2017

Rotation Blurring: Use of Artificial Blurring to Reduce Cybersickness in Virtual Reality First Person Shooters

Users of Virtual Reality (VR) systems often experience vection, the perception of self-motion in the absence of any physical movement. While vection helps to improve presence in VR, it often leads to a form of motion sickness called cybersickness. Cybersickness is a major deterrent to large scale adoption of VR. Prior work has discovered that changing vection (changing the perceived speed or moving direction) causes more severe cybersickness than steady vection (walking at a constant speed or in a constant direction). Based on this idea, we try to reduce the cybersickness caused by character movements in a First Person Shooter (FPS) game in VR. We propose Rotation Blurring (RB), uniformly blurring the screen during rotational movements to reduce cybersickness. We performed a user study to evaluate the impact of RB in reducing cybersickness. We found that the blurring technique led to an overall reduction in sickness levels of the participants and delayed its onset. Participants who experienced acute levels of cybersickness benefited significantly from this technique.

cs.HC↗