arXiv subjects

Yiran Shen

Publications and source records attributed to Yiran Shen.

31 records · Page 2Linked to original sources

arXiv2025

A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models

Personalized preference alignment for large language models (LLMs), the process of tailoring LLMs to individual users' preferences, is an emerging research direction spanning the area of NLP and personalization. In this survey, we present an analysis of works on personalized alignment and modeling for LLMs. We introduce a taxonomy of preference alignment techniques, including training time, inference time, and additionally, user-modeling based methods. We provide analysis and discussion on the strengths and limitations of each group of techniques and then cover evaluation, benchmarks, as well as open problems in the field.

cs.CL↗

arXiv2025

Ev-Layout: A Large-scale Event-based Multi-modal Dataset for Indoor Layout Estimation and Tracking

This paper presents Ev-Layout, a novel large-scale event-based multi-modal dataset designed for indoor layout estimation and tracking. Ev-Layout makes key contributions to the community by: Utilizing a hybrid data collection platform (with a head-mounted display and VR interface) that integrates both RGB and bio-inspired event cameras to capture indoor layouts in motion. Incorporating time-series data from inertial measurement units (IMUs) and ambient lighting conditions recorded during data collection to highlight the potential impact of motion speed and lighting on layout estimation accuracy. The dataset consists of 2.5K sequences, including over 771.3K RGB images and 10 billion event data points. Of these, 39K images are annotated with indoor layouts, enabling research in both event-based and video-based indoor layout estimation. Based on the dataset, we propose an event-based layout estimation pipeline with a novel event-temporal distribution feature module to effectively aggregate the spatio-temporal information from events. Additionally, we introduce a spatio-temporal feature fusion module that can be easily integrated into a transformer module for fusion purposes. Finally, we conduct benchmarking and extensive experiments on the Ev-Layout dataset, demonstrating that our approach significantly improves the accuracy of dynamic indoor layout estimation compared to existing event-based methods.

cs.GR↗

arXiv2024

NeRF-NQA: No-Reference Quality Assessment for Scenes Generated by NeRF and Neural View Synthesis Methods

Neural View Synthesis (NVS) has demonstrated efficacy in generating high-fidelity dense viewpoint videos using a image set with sparse views. However, existing quality assessment methods like PSNR, SSIM, and LPIPS are not tailored for the scenes with dense viewpoints synthesized by NVS and NeRF variants, thus, they often fall short in capturing the perceptual quality, including spatial and angular aspects of NVS-synthesized scenes. Furthermore, the lack of dense ground truth views makes the full reference quality assessment on NVS-synthesized scenes challenging. For instance, datasets such as LLFF provide only sparse images, insufficient for complete full-reference assessments. To address the issues above, we propose NeRF-NQA, the first no-reference quality assessment method for densely-observed scenes synthesized from the NVS and NeRF variants. NeRF-NQA employs a joint quality assessment strategy, integrating both viewwise and pointwise approaches, to evaluate the quality of NVS-generated scenes. The viewwise approach assesses the spatial quality of each individual synthesized view and the overall inter-views consistency, while the pointwise approach focuses on the angular qualities of scene surface points and their compound inter-point quality. Extensive evaluations are conducted to compare NeRF-NQA with 23 mainstream visual quality assessment methods (from fields of image, video, and light-field assessment). The results demonstrate NeRF-NQA outperforms the existing assessment methods significantly and it shows substantial superiority on assessing NVS-synthesized scenes without references. An implementation of this paper are available at https://github.com/VincentQQu/NeRF-NQA.

cs.CV↗

arXiv2024

EvRepSL: Event-Stream Representation via Self-Supervised Learning for Event-Based Vision

Event-stream representation is the first step for many computer vision tasks using event cameras. It converts the asynchronous event-streams into a formatted structure so that conventional machine learning models can be applied easily. However, most of the state-of-the-art event-stream representations are manually designed and the quality of these representations cannot be guaranteed due to the noisy nature of event-streams. In this paper, we introduce a data-driven approach aiming at enhancing the quality of event-stream representations. Our approach commences with the introduction of a new event-stream representation based on spatial-temporal statistics, denoted as EvRep. Subsequently, we theoretically derive the intrinsic relationship between asynchronous event-streams and synchronous video frames. Building upon this theoretical relationship, we train a representation generator, RepGen, in a self-supervised learning manner accepting EvRep as input. Finally, the event-streams are converted to high-quality representations, termed as EvRepSL, by going through the learned RepGen (without the need of fine-tuning or retraining). Our methodology is rigorously validated through extensive evaluations on a variety of mainstream event-based classification and optical flow datasets (captured with various types of event cameras). The experimental results highlight not only our approach's superior performance over existing event-stream representations but also its versatility, being agnostic to different event cameras and tasks.

cs.CV↗

arXiv2024

Towards High-Speed Passive Visible Light Communication with Event Cameras and Digital Micro-Mirrors

Passive visible light communication (VLC) modulates light propagation or reflection to transmit data without directly modulating the light source. Thus, passive VLC provides an alternative to conventional VLC, enabling communication where the light source cannot be directly controlled. There have been ongoing efforts to explore new methods and devices for modulating light propagation or reflection. The state-of-the-art has broken the 100 kbps data rate barrier for passive VLC by using a digital micro-mirror device (DMD) as the light modulating platform, or transmitter, and a photo-diode as the receiver. We significantly extend this work by proposing a massive spatial data channel framework for DMDs, where individual channels can be decoded in parallel using an event camera at the receiver. For the event camera, we introduce event processing algorithms to detect numerous channels and decode bits from individual channels with high reliability. Our prototype, built with off-the-shelf event cameras and DMDs, can decode up to $\sim$2,000 parallel channels, achieving a data transmission rate of 1.6 Mbps, markedly surpassing current benchmarks by 16x.

cs.NI↗

arXiv2024

PDSR: A Privacy-Preserving Diversified Service Recommendation Method on Distributed Data

The last decade has witnessed a tremendous growth of service computing, while efficient service recommendation methods are desired to recommend high-quality services to users. It is well known that collaborative filtering is one of the most popular methods for service recommendation based on QoS, and many existing proposals focus on improving recommendation accuracy, i.e., recommending high-quality redundant services. Nevertheless, users may have different requirements on QoS, and hence diversified recommendation has been attracting increasing attention in recent years to fulfill users' diverse demands and to explore potential services. Unfortunately, the recommendation performances relies on a large volume of data (e.g., QoS data), whereas the data may be distributed across multiple platforms. Therefore, to enable data sharing across the different platforms for diversified service recommendation, we propose a Privacy-preserving Diversified Service Recommendation (PDSR) method. Specifically, we innovate in leveraging the Locality-Sensitive Hashing (LSH) mechanism such that privacy-preserved data sharing across different platforms is enabled to construct a service similarity graph. Based on the similarity graph, we propose a novel accuracy-diversity metric and design a $2$-approximation algorithm to select $K$ services to recommend by maximizing the accuracy-diversity measure. Extensive experiments on real datasets are conducted to verify the efficacy of our PDSR method.

cs.IR↗

arXiv2024

E2HQV: High-Quality Video Generation from Event Camera via Theory-Inspired Model-Aided Deep Learning

The bio-inspired event cameras or dynamic vision sensors are capable of asynchronously capturing per-pixel brightness changes (called event-streams) in high temporal resolution and high dynamic range. However, the non-structural spatial-temporal event-streams make it challenging for providing intuitive visualization with rich semantic information for human vision. It calls for events-to-video (E2V) solutions which take event-streams as input and generate high quality video frames for intuitive visualization. However, current solutions are predominantly data-driven without considering the prior knowledge of the underlying statistics relating event-streams and video frames. It highly relies on the non-linearity and generalization capability of the deep neural networks, thus, is struggling on reconstructing detailed textures when the scenes are complex. In this work, we propose \textbf{E2HQV}, a novel E2V paradigm designed to produce high-quality video frames from events. This approach leverages a model-aided deep learning framework, underpinned by a theory-inspired E2V model, which is meticulously derived from the fundamental imaging principles of event cameras. To deal with the issue of state-reset in the recurrent components of E2HQV, we also design a temporal shift embedding module to further improve the quality of the video frames. Comprehensive evaluations on the real world event camera datasets validate our approach, with E2HQV, notably outperforming state-of-the-art approaches, e.g., surpassing the second best by over 40\% for some evaluation metrics.

cs.CV↗

arXiv2023

VibHead: An Authentication Scheme for Smart Headsets through Vibration

Recent years have witnessed the fast penetration of Virtual Reality (VR) and Augmented Reality (AR) systems into our daily life, the security and privacy issues of the VR/AR applications have been attracting considerable attention. Most VR/AR systems adopt head-mounted devices (i.e., smart headsets) to interact with users and the devices usually store the users' private data. Hence, authentication schemes are desired for the head-mounted devices. Traditional knowledge-based authentication schemes for general personal devices have been proved vulnerable to shoulder-surfing attacks, especially considering the headsets may block the sight of the users. Although the robustness of the knowledge-based authentication can be improved by designing complicated secret codes in virtual space, this approach induces a compromise of usability. Another choice is to leverage the users' biometrics; however, it either relies on highly advanced equipments which may not always be available in commercial headsets or introduce heavy cognitive load to users. In this paper, we propose a vibration-based authentication scheme, VibHead, for smart headsets. Since the propagation of vibration signals through human heads presents unique patterns for different individuals, VibHead employs a CNN-based model to classify registered legitimate users based the features extracted from the vibration signals. We also design a two-step authentication scheme where the above user classifiers are utilized to distinguish the legitimate user from illegitimate ones. We implement VibHead on a Microsoft HoloLens equipped with a linear motor and an IMU sensor which are commonly used in off-the-shelf personal smart devices. According to the results of our extensive experiments, with short vibration signals ($\leq 1s$), VibHead has an outstanding authentication accuracy; both FAR and FRR are around 5%.

cs.CR↗

arXiv2022

High Speed Rotation Estimation with Dynamic Vision Sensors

Rotational speed is one of the important metrics to be measured for calibrating the electric motors in manufacturing, monitoring engine during car repairing, faults detection on electrical appliance and etc. However, existing measurement techniques either require prohibitive hardware (e.g., high-speed camera) or are inconvenient to use in real-world application scenarios. In this paper, we propose, EV-Tach, an event-based tachometer via efficient dynamic vision sensing on mobile devices. EV-Tach is designed as a high-fidelity and convenient tachometer by introducing dynamic vision sensor as a new sensing modality to capture the high-speed rotation precisely under various real-world scenarios. By designing a series of signal processing algorithms bespoke for dynamic vision sensing on mobile devices, EV-Tach is able to extract the rotational speed accurately from the event stream produced by dynamic vision sensing on rotary targets. According to our extensive evaluations, the Relative Mean Absolute Error (RMAE) of EV-Tach is as low as 0.03% which is comparable to the state-of-the-art laser tachometer under fixed measurement mode. Moreover, EV-Tach is robust to subtle movement of user's hand, therefore, can be used as a handheld device, where the laser tachometer fails to produce reasonable results.

cs.CV↗

arXiv2021

Investigating Steady Unconfined Groundwater Flow using Physics Informed Neural Networks

A novel deep learning technique called Physics Informed Neural Networks (PINNs) is adapted to study steady groundwater flow in unconfined aquifers. This technique utilizes information from underlying physics represented in the form of partial differential equations (PDEs) alongside data obtained from physical observations. In this work, we consider the Dupuit-Boussinesq equation, which is based on the Dupuit-Forchheimer approximation, as well as a recent more complete model derived by Di Nucci (2018) as underlying models. We then train PINNs on data obtained from steady-state analytical solutions and laboratory based experiments. Using PINNs, we predict phreatic surface profiles given different input flow conditions and recover estimates for the hydraulic conductivity from the experimental observations. We show that PINNs can eliminate the inherent inability of the Dupuit-Boussinesq equation to predict flows with seepage faces. Moreover, the inclusion of physics information from the Di Nucci and Dupuit-Boussinesq models constrains the solution space and produces better predictions than solely the training data. PINNs based predictions are very robust and show little effect from added noise in the training data. Further, we compare the PINNs obtained using the two different flow models to examine the effects of higher order flow terms, which are neglected by the Dupuit Forchheimer approximation. We found a dimensionless parameter $Π$, which is the ratio of vertical to horizontal flow effects. For $Π\leq 0.1$, Dupuit-Boussinesq approximation is found to be applicable but not otherwise. Lastly, we discuss the effectiveness of using PINNs for examining groundwater flow.

physics.geo-ph↗

arXiv2019

Snoopy: Sniffing Your Smartwatch Passwords via Deep Sequence Learning

Demand for smartwatches has taken off in recent years with new models which can run independently from smartphones and provide more useful features, becoming first-class mobile platforms. One can access online banking or even make payments on a smartwatch without a paired phone. This makes smartwatches more attractive and vulnerable to malicious attacks, which to date have been largely overlooked. In this paper, we demonstrate Snoopy, a password extraction and inference system which is able to accurately infer passwords entered on Android/Apple watches within 20 attempts, just by eavesdropping on motion sensors. Snoopy uses a uniform framework to extract the segments of motion data when passwords are entered, and uses novel deep neural networks to infer the actual passwords. We evaluate the proposed Snoopy system in the real-world with data from 362 participants and show that our system offers a 3-fold improvement in the accuracy of inferring passwords compared to the state-of-the-art, without consuming excessive energy or computational resources. We also show that Snoopy is very resilient to user and device heterogeneity: it can be trained on crowd-sourced motion data (e.g. via Amazon Mechanical Turk), and then used to attack passwords from a new user, even if they are wearing a different model. This paper shows that, in the wrong hands, Snoopy can potentially cause serious leaks of sensitive information. By raising awareness, we invite the community and manufacturers to revisit the risks of continuous motion sensing on smart wearable devices.

cs.HC↗

arXiv2019

Design and Implementation of Secret Key Agreement for Platoon-based Vehicular Cyber-Physical Systems

In platoon-based vehicular cyber-physical system (PVCPS), a lead vehicle that is responsible for managing the platoon's moving directions and velocity periodically disseminates control messages to the vehicles that follow. Securing wireless transmissions of the messages between the vehicles is critical for privacy and confidentiality of platoon's driving pattern. However, due to the broadcast nature of radio channels, the transmissions are vulnerable to eavesdropping. In this paper, we propose a cooperative secret key agreement (CoopKey) scheme for encrypting/decrypting the control messages, where the vehicles in PVCPS generate a unified secret key based on the quantized fading channel randomness. Channel quantization intervals are optimized by dynamic programming to minimize the mismatch of keys. A platooning testbed is built with autonomous robotic vehicles, where a TelosB wireless node is used for onboard data processing and multi-hop dissemination. Extensive real-world experiments demonstrate that CoopKey achieves significantly low secret bit mismatch rate in a variety of settings. Moreover, the standard NIST test suite is employed to verify randomness of the generated keys, where the p-values of our CoopKey pass all the randomness tests. We also evaluate CoopKey with an extended platoon size via simulations to investigate the effect of system scalability on performance.

cs.NI↗

arXiv2018

Shake-n-Shack: Enabling Secure Data Exchange Between Smart Wearables via Handshakes

Since ancient Greece, handshaking has been commonly practiced between two people as a friendly gesture to express trust and respect, or form a mutual agreement. In this paper, we show that such physical contact can be used to bootstrap secure cyber contact between the smart devices worn by users. The key observation is that during handshaking, although belonged to two different users, the two hands involved in the shaking events are often rigidly connected, and therefore exhibit very similar motion patterns. We propose a novel Shake-n-Shack system, which harvests motion data during user handshaking from the wrist worn smart devices such as smartwatches or fitness bands, and exploits the matching motion patterns to generate symmetric keys on both parties. The generated keys can be then used to establish a secure communication channel for exchanging data between devices. This provides a much more natural and user-friendly alternative for many applications, e.g. exchanging/sharing contact details, friending on social networks, or even making payments, since it doesn't involve extra bespoke hardware, nor require the users to perform pre-defined gestures. We implement the proposed Shake-n-Shack system on off-the-shelf smartwatches, and extensive evaluation shows that it can reliably generate 128-bit symmetric keys just after around 1s of handshaking (with success rate >99%), and is resilient to real-time mimicking attacks: in our experiments the Equal Error Rate (EER) is only 1.6% on average. We also show that the proposed Shake-n-Shack system can be extremely lightweight, and is able to run in-situ on the resource-constrained smartwatches without incurring excessive resource consumption.

cs.CR↗