arXiv subjects

Yuxiang Guo

Publications and source records attributed to Yuxiang Guo.

At least 37 records · Page 2Linked to original sources

arXiv2025

DASKT: A Dynamic Affect Simulation Method for Knowledge Tracing

Knowledge Tracing (KT) predicts future performance by modeling students' historical interactions, and understanding students' affective states can enhance the effectiveness of KT, thereby improving the quality of education. Although traditional KT values students' cognition and learning behaviors, efficient evaluation of students' affective states and their application in KT still require further exploration due to the non-affect-oriented nature of the data and budget constraints. To address this issue, we propose a computation-driven approach, Dynamic Affect Simulation Knowledge Tracing (DASKT), to explore the impact of various student affective states (such as frustration, concentration, boredom, and confusion) on their knowledge states. In this model, we first extract affective factors from students' non-affect-oriented behavioral data, then use clustering and spatiotemporal sequence modeling to accurately simulate students' dynamic affect changes when dealing with different problems. Subsequently, {\color{blue}we incorporate affect with time-series analysis to improve the model's ability to infer knowledge states over time and space.} Extensive experimental results on two public real-world educational datasets show that DASKT can achieve more reasonable knowledge states under the effect of students' affective states. Moreover, DASKT outperforms the most advanced KT methods in predicting student performance. Our research highlights a promising avenue for future KT studies, focusing on achieving high interpretability and accuracy.

cs.CY↗

arXiv2024

An Immersive Multi-Elevation Multi-Seasonal Dataset for 3D Reconstruction and Visualization

Significant progress has been made in photo-realistic scene reconstruction over recent years. Various disparate efforts have enabled capabilities such as multi-appearance or large-scale modeling; however, there lacks a welldesigned dataset that can evaluate the holistic progress of scene reconstruction. We introduce a collection of imagery of the Johns Hopkins Homewood Campus, acquired at different seasons, times of day, in multiple elevations, and across a large scale. We perform a multi-stage calibration process, which efficiently recover camera parameters from phone and drone cameras. This dataset can enable researchers to rigorously explore challenges in unconstrained settings, including effects of inconsistent illumination, reconstruction from large scale and from significantly different perspectives, etc.

cs.CV↗

arXiv2024

Studies of Cherenkov Photon Production in PbF$_2$ Crystals using Proton Beams at Fermilab

Future lepton colliders such as the FCC-ee, CEPC, ILC, or a muon collider will collect large data samples that allow precision physics studies with unprecedented accuracy, especially when the data is collected by innovative state-of-the-art detectors. An electromagnetic calorimeter based on scintillating crystals, designed to separately record Cherenkov and scintillation light, can achieve precision measurements of electrons and photons without sacrificing jet energy resolution, given adequate light collection efficiency and separation. This paper presents initial measurements from a program aimed at developing such a calorimeter system for future colliders. We focus on using PbF2 crystals to enhance the understanding of Cherenkov light collection, marking the first step in this endeavor.

physics.ins-det↗

arXiv2024

SPARS3R: Semantic Prior Alignment and Regularization for Sparse 3D Reconstruction

Recent efforts in Gaussian-Splat-based Novel View Synthesis can achieve photorealistic rendering; however, such capability is limited in sparse-view scenarios due to sparse initialization and over-fitting floaters. Recent progress in depth estimation and alignment can provide dense point cloud with few views; however, the resulting pose accuracy is suboptimal. In this work, we present SPARS3R, which combines the advantages of accurate pose estimation from Structure-from-Motion and dense point cloud from depth estimation. To this end, SPARS3R first performs a Global Fusion Alignment process that maps a prior dense point cloud to a sparse point cloud from Structure-from-Motion based on triangulated correspondences. RANSAC is applied during this process to distinguish inliers and outliers. SPARS3R then performs a second, Semantic Outlier Alignment step, which extracts semantically coherent regions around the outliers and performs local alignment in these regions. Along with several improvements in the evaluation process, we demonstrate that SPARS3R can achieve photorealistic rendering with sparse images and significantly outperforms existing approaches.

cs.CV↗

arXiv2024

VILLS -- Video-Image Learning to Learn Semantics for Person Re-Identification

Person Re-identification is a research area with significant real world applications. Despite recent progress, existing methods face challenges in robust re-identification in the wild, e.g., by focusing only on a particular modality and on unreliable patterns such as clothing. A generalized method is highly desired, but remains elusive to achieve due to issues such as the trade-off between spatial and temporal resolution and imperfect feature extraction. We propose VILLS (Video-Image Learning to Learn Semantics), a self-supervised method that jointly learns spatial and temporal features from images and videos. VILLS first designs a local semantic extraction module that adaptively extracts semantically consistent and robust spatial features. Then, VILLS designs a unified feature learning and adaptation module to represent image and video modalities in a consistent feature space. By Leveraging self-supervised, large-scale pre-training, VILLS establishes a new State-of-The-Art that significantly outperforms existing image and video-based methods.

cs.CV↗

arXiv2024

Distillation-guided Representation Learning for Unconstrained Gait Recognition

Gait recognition holds the promise of robustly identifying subjects based on walking patterns instead of appearance information. While previous approaches have performed well for curated indoor data, they tend to underperform in unconstrained situations, e.g. in outdoor, long distance scenes, etc. We propose a framework, termed GAit DEtection and Recognition (GADER), for human authentication in challenging outdoor scenarios. Specifically, GADER leverages a Double Helical Signature to detect segments that contain human movement and builds discriminative features through a novel gait recognition method, where only frames containing gait information are used. To further enhance robustness, GADER encodes viewpoint information in its architecture, and distills representation from an auxiliary RGB recognition model, which enables GADER to learn from silhouette and RGB data at training time. At test time, GADER only infers from the silhouette modality. We evaluate our method on multiple State-of-The-Arts(SoTA) gait baselines and demonstrate consistent improvements on indoor and outdoor datasets, especially with a significant 25.2% improvement on unconstrained, remote gait data.

cs.CV↗

arXiv2024

GaitContour: Efficient Gait Recognition based on a Contour-Pose Representation

Gait recognition holds the promise to robustly identify subjects based on walking patterns instead of appearance information. In recent years, this field has been dominated by learning methods based on two principal input representations: dense silhouette masks or sparse pose keypoints. In this work, we propose a novel, point-based Contour-Pose representation, which compactly expresses both body shape and body parts information. We further propose a local-to-global architecture, called GaitContour, to leverage this novel representation and efficiently compute subject embedding in two stages. The first stage consists of a local transformer that extracts features from five different body regions. The second stage then aggregates the regional features to estimate a global human gait representation. Such a design significantly reduces the complexity of the attention operation and improves efficiency and performance simultaneously. Through large scale experiments, GaitContour is shown to perform significantly better than previous point-based methods, while also being significantly more efficient than silhouette-based methods. On challenging datasets with significant distractors, GaitContour can even outperform silhouette-based methods.

cs.CV↗

arXiv2024

An Empirical Study on JIT Defect Prediction Based on BERT-style Model

Previous works on Just-In-Time (JIT) defect prediction tasks have primarily applied pre-trained models directly, neglecting the configurations of their fine-tuning process. In this study, we perform a systematic empirical study to understand the impact of the settings of the fine-tuning process on BERT-style pre-trained model for JIT defect prediction. Specifically, we explore the impact of different parameter freezing settings, parameter initialization settings, and optimizer strategies on the performance of BERT-style models for JIT defect prediction. Our findings reveal the crucial role of the first encoder layer in the BERT-style model and the project sensitivity to parameter initialization settings. Another notable finding is that the addition of a weight decay strategy in the Adam optimizer can slightly improve model performance. Additionally, we compare performance using different feature extractors (FCN, CNN, LSTM, transformer) and find that a simple network can achieve great performance. These results offer new insights for fine-tuning pre-trained models for JIT defect prediction. We combine these findings to find a cost-effective fine-tuning method based on LoRA, which achieve a comparable performance with only one-third memory consumption than original fine-tuning process.

cs.SE↗

arXiv2023

SCCA: Shifted Cross Chunk Attention for long contextual semantic expansion

Sparse attention as a efficient method can significantly decrease the computation cost, but current sparse attention tend to rely on window self attention which block the global information flow. For this problem, we present Shifted Cross Chunk Attention (SCCA), using different KV shifting strategy to extend respective field in each attention layer. Except, we combine Dilated Attention(DA) and Dilated Neighborhood Attention(DNA) to present Shifted Dilated Attention(SDA). Both SCCA and SDA can accumulate attention results in multi head attention to obtain approximate respective field in full attention. In this paper, we conduct language modeling experiments using different pattern of SCCA and combination of SCCA and SDA. The proposed shifted cross chunk attention (SCCA) can effectively extend large language models (LLMs) to longer context combined with Positional interpolation(PI) and LoRA than current sparse attention. Notably, SCCA adopts LLaMA2 7B from 4k context to 8k in single V100. This attention pattern can provide a Plug-and-play fine-tuning method to extend model context while retaining their original architectures, and is compatible with most existing techniques.

cs.CL↗

arXiv2023

Instruct2Attack: Language-Guided Semantic Adversarial Attacks

We propose Instruct2Attack (I2A), a language-guided semantic attack that generates semantically meaningful perturbations according to free-form language instructions. We make use of state-of-the-art latent diffusion models, where we adversarially guide the reverse diffusion process to search for an adversarial latent code conditioned on the input image and text instruction. Compared to existing noise-based and semantic attacks, I2A generates more natural and diverse adversarial examples while providing better controllability and interpretability. We further automate the attack process with GPT-4 to generate diverse image-specific text instructions. We show that I2A can successfully break state-of-the-art deep neural networks even under strong adversarial defenses, and demonstrate great transferability among a variety of network architectures.

cs.CV↗

arXiv2023

A study on the impact of pre-trained model on Just-In-Time defect prediction

Previous researchers conducting Just-In-Time (JIT) defect prediction tasks have primarily focused on the performance of individual pre-trained models, without exploring the relationship between different pre-trained models as backbones. In this study, we build six models: RoBERTaJIT, CodeBERTJIT, BARTJIT, PLBARTJIT, GPT2JIT, and CodeGPTJIT, each with a distinct pre-trained model as its backbone. We systematically explore the differences and connections between these models. Specifically, we investigate the performance of the models when using Commit code and Commit message as inputs, as well as the relationship between training efficiency and model distribution among these six models. Additionally, we conduct an ablation experiment to explore the sensitivity of each model to inputs. Furthermore, we investigate how the models perform in zero-shot and few-shot scenarios. Our findings indicate that each model based on different backbones shows improvements, and when the backbone's pre-training model is similar, the training resources that need to be consumed are much more closer. We also observe that Commit code plays a significant role in defect detection, and different pre-trained models demonstrate better defect detection ability with a balanced dataset under few-shot scenarios. These results provide new insights for optimizing JIT defect prediction tasks using pre-trained models and highlight the factors that require more attention when constructing such models. Additionally, CodeGPTJIT and GPT2JIT achieved better performance than DeepJIT and CC2Vec on the two datasets respectively under 2000 training samples. These findings emphasize the effectiveness of transformer-based pre-trained models in JIT defect prediction tasks, especially in scenarios with limited training data.

cs.SE↗

arXiv2022

Multi-Modal Human Authentication Using Silhouettes, Gait and RGB

Whole-body-based human authentication is a promising approach for remote biometrics scenarios. Current literature focuses on either body recognition based on RGB images or gait recognition based on body shapes and walking patterns; both have their advantages and drawbacks. In this work, we propose Dual-Modal Ensemble (DME), which combines both RGB and silhouette data to achieve more robust performances for indoor and outdoor whole-body based recognition. Within DME, we propose GaitPattern, which is inspired by the double helical gait pattern used in traditional gait analysis. The GaitPattern contributes to robust identification performance over a large range of viewing angles. Extensive experimental results on the CASIA-B dataset demonstrate that the proposed method outperforms state-of-the-art recognition systems. We also provide experimental results using the newly collected BRIAR dataset.

cs.CV↗

arXiv2022

Development and test of a mini-Data Acquisition system for the High-Luminosity LHC upgrade of the ATLAS Monitored Drift Tube detector

New front-end electronics including ASICs and FPGA boards are under development for the ATLAS Monitored Drift Tube (MDT) detector to handle the large data rates and harsh environment expected at high-luminosity LHC runs. A mobile Data Acquisition (miniDAQ) system is designed to perform integration tests of these front-end electronics. In addition, it will be used for surface commissioning of 96 small-radius MDT (sMDT) chambers and for integration and commissioning of new front-end electronics on the present ATLAS MDT chambers. Details of the miniDAQ hardware and firmware are described in this article. The miniDAQ system is also used to read out new front-end electronics on an sMDT prototype chamber using cosmic muons and results obtained are shown.

physics.ins-det↗

arXiv2021

Performance of Michigan sMDT Prototype Chambers for the HL-LHC ATLAS Muon Detector Upgrade

A new small-diameter Monitored Drift Tube (sMDT) chamber has been developed for the muon spectrometer of the ATLAS experiment to handle the higher collision rates expected at the CERN High Luminosity Large Hadron Collider (HL-LHC). This paper presents measurements of the tracking resolution and hit efficiency of two prototype sMDT chambers constructed at the University of Michigan. Using cosmic-ray muons the sMDT tracking resolution of 103.7$\pm8.1$ \textmu m was measured for one chamber and 101.8$\pm$7.8 \textmu m for the other, compared with a design resolution of 106 \textmu m. A further tracking resolution improvement to 83.4$\pm$7.8 \textmu m was obtained by using new high-gain readout electronics which will be added for HL-LHC. An average tracking efficiency of (98.5$\pm$0.2)\% was found for both chambers. The methodology used to determine the detector tracking resolution and efficiency, including reconstruction of sMDT data and a Geant4 simulation of the test chamber, is presented in detail.

physics.ins-det↗

arXiv2020

Design of a Time-to-Digital Converter ASIC and a mini-DAQ system for the Phase-2 Upgrade of the ATLAS Monitored Drift Tube detector

We present the second prototype of a time-to-digital (TDC) ASIC for the upgrade of the ATLAS Monitored Drift Tube (MDT) detector for High-Luminosity LHC operations. Compared to the first prototype, triple modular redundancy has been implemented for the configuration and flow control logic. The total power consumption is increased by less than 10 mW while achieving the same time resolution and channel uniformity. A mini-DAQ system has been built to verify the front-end electronics chain with the new prototype together with other ASICs and boards in triggered mode. Cosmic ray tests with a small-diameter MDT chamber indicate that the configuration and data transmission of the readout electronics perform well. It is expected that this prototype design will be used in the final production.

physics.ins-det↗

arXiv2019

A multichannel front end ASIC for PMT readout in LHAASO WCDA

Time and charge measurements over a large dynamic range from 1 Photo Electron (P.E.) to 4000 P.E. are required for the Water Cherenkov Detector Array (WCDA), which is one of the key components in the Large High Altitude Air Shower Observatory (LHAASO). To simplify the circuit structure of the readout electronics, a front end ASIC was designed. Based on the charge-to-time conversion method, the output pulse width of the ASIC corresponds to the input signal charge information while time information of the input signal is picked off through a discriminator, and thus the time and charge information can be digitized simultaneously using this ASIC and a following Time-to-Digital Converter (TDC). To address the challenge of mismatch among the channels observed in the previous prototype version, this work presents approaches for analyzing the problem and optimizing the circuits. A new version of the ASIC was designed and fabricated in the GLOBALFOUNDRIES 0.35 um CMOS technology, which integrates 6 channels (corresponding to the readout of the 3 PMTs) in each chip. The test results indicate that the mismatch between the channels is significantly reduced to less than 20% using the proposed approach. The time measurement resolution better than 300 ps is achieved, and the charge measurement resolution is better than 10% at 1 P.E., and 1% at 4000 P.E., which meets the application requirements.

physics.ins-det↗

arXiv2019

Prototype of a transient waveform recording ASIC

The paper presents the design and measurement results of a transient waveform recording ASIC based on the Switched Capacitor Array (SCA) architecture. This 0.18 μm CMOS prototype device contains two channels and each channel employs a SCA of 128 samples deep, a 12-bit Wilkinson ADC and a serial data readout. A series of tests have been conducted and the results indicate that: a full 1 V signal voltage range is available, the input analog bandwidth is approximately 450 MHz and the sampling speed is adjustable from 0.076 to 3.2 Gsps (Gigabit Samples Per Second). For precision waveform timing extraction, careful calibration of timing intervals between samples is conducted to improve the timing resolution of such chips, and the timing precision of this ASIC is proved to be better than 15 ps RMS.

physics.ins-det↗

arXiv2019

An overdetermined linear equations-based time calibration method for fast sampling ASICs

A novel time calibration method for waveform sampling application specific integrated circuits (ASICs) based on switched capacitor arrays (SCAs) is proposed in this paper. Precision timing extraction using SCA ASICs has been proved to be a promising technique in many high energy physics experiments. However, such ASICs suffer from irregular sampling intervals caused by process variations. Therefore, careful calibration is required to improve the time resolution of such systems. We evaluated the limitation of a popular method using the proportionality between voltage amplitude and sampling interval of adjacent switched-capacitor cells responding to either a sawtooth wave or a sine wave. The new time calibration method presented here utilizes the relationship between sampling intervals and the known input signal period to establish overdetermined linear equations, and the roots of these equations correspond to the actual sampling intervals. We applied this new method to a pulse timing test with an ASIC designed by our team, and the test results indicate that the new time calibration method is effective.

physics.ins-det↗