Searcharxiv⌕ Search

arXiv subjects

Xin Tong

Publications and source records attributed to Xin Tong.

At least 109 records · Page 6Linked to original sources
arXiv2024

V-Hands: Touchscreen-based Hand Tracking for Remote Whiteboard Interaction

In whiteboard-based remote communication, the seamless integration of drawn content and hand-screen interactions is essential for an immersive user experience. Previous methods either require bulky device setups for capturing hand gestures or fail to accurately track the hand poses from capacitive images. In this paper, we present a real-time method for precise tracking 3D poses of both hands from capacitive video frames. To this end, we develop a deep neural network to identify hands and infer hand joint positions from capacitive frames, and then recover 3D hand poses from the hand-joint positions via a constrained inverse kinematic solver. Additionally, we design a device setup for capturing high-quality hand-screen interaction data and obtained a more accurate synchronized capacitive video and hand pose dataset. Our method improves the accuracy and stability of 3D hand tracking for capacitive frames while maintaining a compact device setup for remote communication. We validate our scheme design and its superior performance on 3D hand pose tracking and demonstrate the effectiveness of our method in whiteboard-based remote communication. Our code, model, and dataset are available at https://V-Hands.github.io.

cs.HC↗
arXiv2024

Data-Driven Fire Modeling: Learning First Arrival Times and Model Parameters with Neural Networks

Data-driven techniques are being increasingly applied to complement physics-based models in fire science. However, the lack of sufficiently large datasets continues to hinder the application of certain machine learning techniques. In this paper, we use simulated data to investigate the ability of neural networks to parameterize dynamics in fire science. In particular, we investigate neural networks that map five key parameters in fire spread to the first arrival time, and the corresponding inverse problem. By using simulated data, we are able to characterize the error, the required dataset size, and the convergence properties of these neural networks. For the inverse problem, we quantify the network's sensitivity in estimating each of the key parameters. The findings demonstrate the potential of machine learning in fire science, highlight the challenges associated with limited dataset sizes, and quantify the sensitivity of neural networks to estimate key parameters governing fire spread dynamics.

cs.LG↗
arXiv2024

Diffusion Models are Geometry Critics: Single Image 3D Editing Using Pre-Trained Diffusion Priors

We propose a novel image editing technique that enables 3D manipulations on single images, such as object rotation and translation. Existing 3D-aware image editing approaches typically rely on synthetic multi-view datasets for training specialized models, thus constraining their effectiveness on open-domain images featuring significantly more varied layouts and styles. In contrast, our method directly leverages powerful image diffusion models trained on a broad spectrum of text-image pairs and thus retain their exceptional generalization abilities. This objective is realized through the development of an iterative novel view synthesis and geometry alignment algorithm. The algorithm harnesses diffusion models for dual purposes: they provide appearance prior by predicting novel views of the selected object using estimated depth maps, and they act as a geometry critic by correcting misalignments in 3D shapes across the sampled views. Our method can generate high-quality 3D-aware image edits with large viewpoint transformations and high appearance and shape consistency with the input image, pushing the boundaries of what is possible with single-image 3D-aware editing.

cs.CV↗
arXiv2024

A Simple Baseline for Spoken Language to Sign Language Translation with 3D Avatars

The objective of this paper is to develop a functional system for translating spoken languages into sign languages, referred to as Spoken2Sign translation. The Spoken2Sign task is orthogonal and complementary to traditional sign language to spoken language (Sign2Spoken) translation. To enable Spoken2Sign translation, we present a simple baseline consisting of three steps: 1) creating a gloss-video dictionary using existing Sign2Spoken benchmarks; 2) estimating a 3D sign for each sign video in the dictionary; 3) training a Spoken2Sign model, which is composed of a Text2Gloss translator, a sign connector, and a rendering module, with the aid of the yielded gloss-3D sign dictionary. The translation results are then displayed through a sign avatar. As far as we know, we are the first to present the Spoken2Sign task in an output format of 3D signs. In addition to its capability of Spoken2Sign translation, we also demonstrate that two by-products of our approach-3D keypoint augmentation and multi-view understanding-can assist in keypoint-based sign language understanding. Code and models are available at https://github.com/FangyunWei/SLRT.

cs.CV↗
arXiv2024

Individual-centered partial information in social networks

In statistical network analysis, we often assume either the full network is available or multiple subgraphs can be sampled to estimate various global properties of the network. However, in a real social network, people frequently make decisions based on their local view of the network alone. Here, we consider a partial information framework that characterizes the local network centered at a given individual by path length $L$ and gives rise to a partial adjacency matrix. Under $L=2$, we focus on the problem of (global) community detection using the popular stochastic block model (SBM) and its degree-corrected variant (DCSBM). We derive theoretical properties of the eigenvalues and eigenvectors from the signal term of the partial adjacency matrix and propose new spectral-based community detection algorithms that achieve consistency under appropriate conditions. Our analysis also allows us to propose a new centrality measure that assesses the importance of an individual's partial information in determining global community structure. Using simulated and real networks, we demonstrate the performance of our algorithms and compare our centrality measure with other popular alternatives to show it captures unique nodal information. Our results illustrate that the partial information framework enables us to compare the viewpoints of different individuals regarding the global structure.

stat.ME↗
arXiv2024

Evaluation of Missing Data Analytical Techniques in Longitudinal Research: Traditional and Machine Learning Approaches

Missing Not at Random (MNAR) and nonnormal data are challenging to handle. Traditional missing data analytical techniques such as full information maximum likelihood estimation (FIML) may fail with nonnormal data as they are built on normal distribution assumptions. Two-Stage Robust Estimation (TSRE) does manage nonnormal data, but both FIML and TSRE are less explored in longitudinal studies under MNAR conditions with nonnormal distributions. Unlike traditional statistical approaches, machine learning approaches do not require distributional assumptions about the data. More importantly, they have shown promise for MNAR data; however, their application in longitudinal studies, addressing both Missing at Random (MAR) and MNAR scenarios, is also underexplored. This study utilizes Monte Carlo simulations to assess and compare the effectiveness of six analytical techniques for missing data within the growth curve modeling framework. These techniques include traditional approaches like FIML and TSRE, machine learning approaches by single imputation (K-Nearest Neighbors and missForest), and machine learning approaches by multiple imputation (micecart and miceForest). We investigate the influence of sample size, missing data rate, missing data mechanism, and data distribution on the accuracy and efficiency of model estimation. Our findings indicate that FIML is most effective for MNAR data among the tested approaches. TSRE excels in handling MAR data, while missForest is only advantageous in limited conditions with a combination of very skewed distributions, very large sample sizes (e.g., n larger than 1000), and low missing data rates.

stat.AP↗
arXiv2024

DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generation

This paper presents a novel method for exerting fine-grained lighting control during text-driven diffusion-based image generation. While existing diffusion models already have the ability to generate images under any lighting condition, without additional guidance these models tend to correlate image content and lighting. Moreover, text prompts lack the necessary expressional power to describe detailed lighting setups. To provide the content creator with fine-grained control over the lighting during image generation, we augment the text-prompt with detailed lighting information in the form of radiance hints, i.e., visualizations of the scene geometry with a homogeneous canonical material under the target lighting. However, the scene geometry needed to produce the radiance hints is unknown. Our key observation is that we only need to guide the diffusion process, hence exact radiance hints are not necessary; we only need to point the diffusion model in the right direction. Based on this observation, we introduce a three stage method for controlling the lighting during image generation. In the first stage, we leverage a standard pretrained diffusion model to generate a provisional image under uncontrolled lighting. Next, in the second stage, we resynthesize and refine the foreground object in the generated image by passing the target lighting to a refined diffusion model, named DiLightNet, using radiance hints computed on a coarse shape of the foreground object inferred from the provisional image. To retain the texture details, we multiply the radiance hints with a neural encoding of the provisional synthesized image before passing it to DiLightNet. Finally, in the third stage, we resynthesize the background to be consistent with the lighting on the foreground object. We demonstrate and validate our lighting controlled diffusion model on a variety of text prompts and lighting conditions.

cs.CV↗
arXiv2024

Analytic Geometry and Hodge-Frobenius Structure

In this paper, we study Frobenius structures in higher dimensional $p$-adic analytic geometry and the corresponding $p$-adic functional analysis. This will build up foundations for further study on some generalized cohomology of Frobenius modules and the corresponding generalized Iwasawa theory and generalized noncommutative Tamagawa number conjectures in the spirit of Burns-Flach-Fukaya-Kato and Nakamura (as well as certainly the original noncommutative Tamagawa number conjectures as observed by Pal-Zábrádi). We will work in the program proposed by Carter-Kedlaya-Zábrádi and after Pal-Zábrádi, and we will follow closely the approach from Kedlaya-Pottharst-Xiao to investigate the corresponding deformation of the generalized $p$-adic Hodge structures.

math.NT↗
arXiv2024

$\infty$-Categorical Generalized Langlands Program I: Mixed-Parity Modules and Sheaves

Mixed-parity module emerges for instance when a de Rham Galois representation is being tensored with a square root of cyclotomic character, which produces half odd integers as the corresponding Hodge-Tate weights. We build the whole foundation on the $p$-adic Hodge theory in this setting over small $v$-stacks after Scholze and we also consider certain moduli $v$-stack which parametrizes families of mixed-parity Hodge modules. Examples of the small $v$-stacks in our mind are rigid analytic spaces over $p$-adic fields and moduli $v$-stack of vector bundles over Fargues-Fontaine curves. The preparation implemented at this level will be expected to provide further essential foundationalization for generalized Langlands program after Langlands, Drinfeld, Fargues-Scholze. One side of the generalized Langlands correspondence in the geometric setting is the perverse motivic derived $\infty$-category over $\mathrm{Moduli}_G$ related to smooth representations of reductive groups, while the other side of the generalized Langlands correspondence in the geometric setting is the corresponding derived $\infty$-category over the stack of mixed-parity $L$-parametrizations (i.e. from two-fold covering of the Weil group into $\ell$-adic groups) related to the representations of Weil group in our setting into Langlands dual groups. Although after Scholze and Fargues-Scholze our generalized Langlands program can go along $\ell$-adic cohomologicalization to immediately achieve various solid derived $\infty$-categories $\mathrm{DerCat}_\text{ét}(\mathrm{Moduli}_G,\square)$, $\mathrm{DerCat}_\mathrm{lisse, \blacksquare}(\mathrm{Moduli}_G,\square)$, $\mathrm{DerCat}_{\blacksquare}(\mathrm{Moduli}_G,\square)$ and so on with well-established formalism regarding 6-functors, we already provide certain $p$-adic cohomologicalization of the story over $\mathrm{Moduli}_G$.

math.NT↗
arXiv2024

Topologization and Functional Analytification III

In this paper, we continue our study on the topologization and functional analytification in $\infty$-categorical and homotopical analytic geometry. As in our previous articles on the $\infty$-categorical extensions of certain analytic and topological contexts, we discuss the corresponding prismatic cohomological constructions after Bhatt-Lurie, Bhatt-Scholze and Drinfeld, and the corresponding Robba stacks and sheaves after Kedlaya-Liu.

math.AG↗
arXiv2024

3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining

Masked autoencoders (MAE) have recently been introduced to 3D self-supervised pretraining for point clouds due to their great success in NLP and computer vision. Unlike MAEs used in the image domain, where the pretext task is to restore features at the masked pixels, such as colors, the existing 3D MAE works reconstruct the missing geometry only, i.e, the location of the masked points. In contrast to previous studies, we advocate that point location recovery is inessential and restoring intrinsic point features is much superior. To this end, we propose to ignore point position reconstruction and recover high-order features at masked points including surface normals and surface variations, through a novel attention-based decoder which is independent of the encoder design. We validate the effectiveness of our pretext task and decoder design using different encoder structures for 3D training and demonstrate the advantages of our pretrained networks on various point cloud analysis tasks.

cs.CV↗
arXiv2024

Quaternion-Based Attitude Stabilization Using Synergistic Hybrid Feedback With Minimal Potential Functions

This paper investigates the robust global attitude stabilization problem for a rigid-body system using quaternion-based feedback. We propose a novel synergistic hybrid feedback with the following notable features: (1) It demonstrates central synergism by utilizing a minimal number of potential functions; (2) It ensures consistency with respect to the unit quaternion representation of rigid-body attitude; (3) Its state-feedback laws incorporate a shared action term that steers the system toward the desired attitude. We demonstrate that the proposed hybrid feedback method effectively solves the problem at hand and guarantees robust uniform global asymptotic stability.

eess.SY↗
arXiv2024

CPSDBench: A Large Language Model Evaluation Benchmark and Baseline for Chinese Public Security Domain

Large Language Models (LLMs) have demonstrated significant potential and effectiveness across multiple application domains. To assess the performance of mainstream LLMs in public security tasks, this study aims to construct a specialized evaluation benchmark tailored to the Chinese public security domain--CPSDbench. CPSDbench integrates datasets related to public security collected from real-world scenarios, supporting a comprehensive assessment of LLMs across four key dimensions: text classification, information extraction, question answering, and text generation. Furthermore, this study introduces a set of innovative evaluation metrics designed to more precisely quantify the efficacy of LLMs in executing tasks related to public security. Through the in-depth analysis and evaluation conducted in this research, we not only enhance our understanding of the performance strengths and limitations of existing models in addressing public security issues but also provide references for the future development of more accurate and customized LLM models targeted at applications in this field.

cs.AI↗
arXiv2024

Dynamic laser ablation loading of a linear Paul trap

We present a detailed method for accumulating Ca$^{+}$ ions controllably in a linear Paul trap. The ions are generated by pulsed laser ablation and dynamically loaded into the ion trap by switching the trapping potential on and off. The loaded ions are precooled by buffer gas and then laser-cooled to form Coulomb crystals for verifying quantity. The number of ions is controlled by manipulating the trapping potential of the ion trap, partial pressure of buffer gas and turn-on time of the entrance end cap voltage. With single-pulse laser ablation, the number of trapped ions ranges from tens to ten thousand. The kinetic energy of loaded ions can be selected via the optimal turn-on time of the entrance end cap. Using multiple-pulse laser ablation, the number is further increased and reaches about $4 \times 10^{4}$. The dynamic loading method has wide application for accumulating low-yielding ions via laser ablation in the ion trap.

physics.atom-ph↗
arXiv2024

Adaptive conformal classification with noisy labels

This paper develops novel conformal prediction methods for classification tasks that can automatically adapt to random label contamination in the calibration sample, leading to more informative prediction sets with stronger coverage guarantees compared to state-of-the-art approaches. This is made possible by a precise characterization of the effective coverage inflation (or deflation) suffered by standard conformal inferences in the presence of label contamination, which is then made actionable through new calibration algorithms. Our solution is flexible and can leverage different modeling assumptions about the label contamination process, while requiring no knowledge of the underlying data distribution or of the inner workings of the machine-learning classifier. The advantages of the proposed methods are demonstrated through extensive simulations and an application to object classification with the CIFAR-10H image data set.

stat.ME↗
arXiv2024

MVD$^2$: Efficient Multiview 3D Reconstruction for Multiview Diffusion

As a promising 3D generation technique, multiview diffusion (MVD) has received a lot of attention due to its advantages in terms of generalizability, quality, and efficiency. By finetuning pretrained large image diffusion models with 3D data, the MVD methods first generate multiple views of a 3D object based on an image or text prompt and then reconstruct 3D shapes with multiview 3D reconstruction. However, the sparse views and inconsistent details in the generated images make 3D reconstruction challenging. We present MVD$^2$, an efficient 3D reconstruction method for multiview diffusion (MVD) images. MVD$^2$ aggregates image features into a 3D feature volume by projection and convolution and then decodes volumetric features into a 3D mesh. We train MVD$^2$ with 3D shape collections and MVD images prompted by rendered views of 3D shapes. To address the discrepancy between the generated multiview images and ground-truth views of the 3D shapes, we design a simple-yet-efficient view-dependent training scheme. MVD$^2$ improves the 3D generation quality of MVD and is fast and robust to various MVD methods. After training, it can efficiently decode 3D meshes from multiview images within one second. We train MVD$^2$ with Zero-123++ and ObjectVerse-LVIS 3D dataset and demonstrate its superior performance in generating 3D models from multiview images generated by different MVD methods, using both synthetic and real images as prompts.

cs.CV↗