Searcharxiv⌕ Search

arXiv subjects

Hao Xing

Publications and source records attributed to Hao Xing.

At least 19 recordsLinked to original sources
arXiv2026

Latent Fragility and Clustered Withdrawals in Dynamic Banks Runs

Using a mean-field game framework, we study a dynamic model of bank runs in which more withdrawals raise the risk of bank failure. Even though depositors receive gradual and idiosyncratic shocks, withdrawals occur in clusters. The main mechanism is latent fragility: run-prone depositors accumulate gradually over time and may prefer to wait individually, but they withdraw together once collective exit becomes self-fulfilling. We establish equilibrium existence and characterize earliest-run and latest-run equilibria. The clustering mechanism arises whether depositor heterogeneity is discrete or continuous. A common aggregate state coordinates withdrawal timing and leads to a unique threshold equilibrium.

econ.TH↗
arXiv2026

Flexible Information Acquisition in the Kyle Model

We study an information acquisition problem in which an informed trader acquires costly information prior to trading in the Kyle equilibrium. The cost of information acquisition is represented by an entropy cost. Regardless of the prior distribution of the asset payoff, continuous signals are optimal. Moreover, any continuously distributed signal, together with an associated logit type posterior distribution of the payoff, yields the same ex-ante value for the informed trader, the same distribution of posterior expected payoff, and the same unconditional distribution of the informed trader's trading strategy. Consequently, a normally distributed signal can be adopted without loss of generality. We further show that when the information acquisition cost increases or the volatility of noise trades decreases, the variance of the posterior expected payoff declines, the profit potential from trading diminishes, meanwhile the posterior expected payoff increasingly resembles a normal distribution, and the information leakage cost from trading decreases.

econ.TH↗
arXiv2025

Minimax Analysis of Estimation Problems in Coherent Imaging

Unlike conventional imaging modalities, such as magnetic resonance imaging, which are often well described by a linear regression framework, coherent imaging systems follow a significantly more complex model. In these systems, the task is to estimate the unknown image ${\boldsymbol x}_o \in \mathbb{R}^n$ from observations ${\boldsymbol y}_1, \ldots, {\boldsymbol y}_L \in \mathbb{R}^m$ of the form \[ {\boldsymbol y}_l = A_l X_o {\boldsymbol w}_l + {\boldsymbol z}_l, \quad l = 1, \ldots, L, \] where $X_o = \mathrm{diag}({\boldsymbol x}_o)$ is an $n \times n$ diagonal matrix, ${\boldsymbol w}_1, \ldots, {\boldsymbol w}_L \stackrel{\text{i.i.d.}}{\sim} \mathcal{N}(0,I_n)$ represent speckle noise, and ${\boldsymbol z}_1, \ldots, {\boldsymbol z}_L \stackrel{\text{i.i.d.}}{\sim} \mathcal{N}(0,\sigma_z^2 I_m)$ denote additive noise. The matrices $A_1, \ldots, A_L$ are known forward operators determined by the imaging system. The fundamental limits of conventional imaging systems have been extensively studied through sparse linear regression models. However, the limits of coherent imaging systems remain largely unexplored. Our goal is to close this gap by characterizing the minimax risk of estimating ${\boldsymbol x}_o$ in high-dimensional settings. Motivated by insights from sparse regression, we observe that the structure of ${\boldsymbol x}_o$ plays a crucial role in determining the estimation error. In this work, we adopt a general notion of structure based on the covering numbers, which is more appropriate for coherent imaging systems. We show that the minimax mean squared error (MSE) scales as \[ \frac{\max\{\sigma_z^4,\, m^2,\, n^2\}\, k \log n}{m^2 n L}, \] where $k$ is a parameter that quantifies the effective complexity of the class of images.

math.ST↗
arXiv2025

Multi-Modal Graph Convolutional Network with Sinusoidal Encoding for Robust Human Action Segmentation

Accurate temporal segmentation of human actions is critical for intelligent robots in collaborative settings, where a precise understanding of sub-activity labels and their temporal structure is essential. However, the inherent noise in both human pose estimation and object detection often leads to over-segmentation errors, disrupting the coherence of action sequences. To address this, we propose a Multi-Modal Graph Convolutional Network (MMGCN) that integrates low-frame-rate (e.g., 1 fps) visual data with high-frame-rate (e.g., 30 fps) motion data (skeleton and object detections) to mitigate fragmentation. Our framework introduces three key contributions. First, a sinusoidal encoding strategy that maps 3D skeleton coordinates into a continuous sin-cos space to enhance spatial representation robustness. Second, a temporal graph fusion module that aligns multi-modal inputs with differing resolutions via hierarchical feature aggregation, Third, inspired by the smooth transitions inherent to human actions, we design SmoothLabelMix, a data augmentation technique that mixes input sequences and labels to generate synthetic training examples with gradual action transitions, enhancing temporal consistency in predictions and reducing over-segmentation artifacts. Extensive experiments on the Bimanual Actions Dataset, a public benchmark for human-object interaction understanding, demonstrate that our approach outperforms state-of-the-art methods, especially in action segmentation accuracy, achieving F1@10: 94.5% and F1@25: 92.8%.

cs.CV↗
arXiv2025

Towards Open-World Human Action Segmentation Using Graph Convolutional Networks

Human-object interaction segmentation is a fundamental task of daily activity understanding, which plays a crucial role in applications such as assistive robotics, healthcare, and autonomous systems. Most existing learning-based methods excel in closed-world action segmentation, they struggle to generalize to open-world scenarios where novel actions emerge. Collecting exhaustive action categories for training is impractical due to the dynamic diversity of human activities, necessitating models that detect and segment out-of-distribution actions without manual annotation. To address this issue, we formally define the open-world action segmentation problem and propose a structured framework for detecting and segmenting unseen actions. Our framework introduces three key innovations: 1) an Enhanced Pyramid Graph Convolutional Network (EPGCN) with a novel decoder module for robust spatiotemporal feature upsampling. 2) Mixup-based training to synthesize out-of-distribution data, eliminating reliance on manual annotations. 3) A novel Temporal Clustering loss that groups in-distribution actions while distancing out-of-distribution samples. We evaluate our framework on two challenging human-object interaction recognition datasets: Bimanual Actions and 2 Hands and Object (H2O) datasets. Experimental results demonstrate significant improvements over state-of-the-art action segmentation models across multiple open-set evaluation metrics, achieving 16.9% and 34.6% relative gains in open-set segmentation (F1@50) and out-of-distribution detection performances (AUROC), respectively. Additionally, we conduct an in-depth ablation study to assess the impact of each proposed component, identifying the optimal framework configuration for open-world action segmentation.

cs.CV↗
arXiv2024

Understanding Spatio-Temporal Relations in Human-Object Interaction using Pyramid Graph Convolutional Network

Human activities recognition is an important task for an intelligent robot, especially in the field of human-robot collaboration, it requires not only the label of sub-activities but also the temporal structure of the activity. In order to automatically recognize both the label and the temporal structure in sequence of human-object interaction, we propose a novel Pyramid Graph Convolutional Network (PGCN), which employs a pyramidal encoder-decoder architecture consisting of an attention based graph convolution network and a temporal pyramid pooling module for downsampling and upsampling interaction sequence on the temporal axis, respectively. The system represents the 2D or 3D spatial relation of human and objects from the detection results in video data as a graph. To learn the human-object relations, a new attention graph convolutional network is trained to extract condensed information from the graph representation. To segment action into sub-actions, a novel temporal pyramid pooling module is proposed, which upsamples compressed features back to the original time scale and classifies actions per frame. We explore various attention layers, namely spatial attention, temporal attention and channel attention, and combine different upsampling decoders to test the performance on action recognition and segmentation. We evaluate our model on two challenging datasets in the field of human-object interaction recognition, i.e. Bimanual Actions and IKEA Assembly datasets. We demonstrate that our classifier significantly improves both framewise action recognition and segmentation, e.g., F1 micro and F1@50 scores on Bimanual Actions dataset are improved by $4.3\%$ and $8.5\%$ respectively.

cs.CV↗
arXiv2024

Understanding Human Activity with Uncertainty Measure for Novelty in Graph Convolutional Networks

Understanding human activity is a crucial aspect of developing intelligent robots, particularly in the domain of human-robot collaboration. Nevertheless, existing systems encounter challenges such as over-segmentation, attributed to errors in the up-sampling process of the decoder. In response, we introduce a promising solution: the Temporal Fusion Graph Convolutional Network. This innovative approach aims to rectify the inadequate boundary estimation of individual actions within an activity stream and mitigate the issue of over-segmentation in the temporal dimension. Moreover, systems leveraging human activity recognition frameworks for decision-making necessitate more than just the identification of actions. They require a confidence value indicative of the certainty regarding the correspondence between observations and training examples. This is crucial to prevent overly confident responses to unforeseen scenarios that were not part of the training data and may have resulted in mismatches due to weak similarity measures within the system. To address this, we propose the incorporation of a Spectral Normalized Residual connection aimed at enhancing efficient estimation of novelty in observations. This innovative approach ensures the preservation of input distance within the feature space by imposing constraints on the maximum gradients of weight updates. By limiting these gradients, we promote a more robust handling of novel situations, thereby mitigating the risks associated with overconfidence. Our methodology involves the use of a Gaussian process to quantify the distance in feature space.

cs.RO↗
arXiv2024

Is speckle noise more challenging to mitigate than additive noise?

We study the problem of estimating a function in the presence of both speckle and additive noises, commonly referred to as the de-speckling problem. Although additive noise has been thoroughly explored in nonparametric estimation, speckle noise, prevalent in applications such as synthetic aperture radar, ultrasound imaging, and digital holography, has not received as much attention. Consequently, there is a lack of theoretical investigations into the fundamental limits of mitigating the speckle noise.This paper is the first step in filling this gap. Our focus is on investigating the minimax estimation error for estimating a $\beta$-H\"older continuous function and determining the rate of the minimax risk. Specifically, if $n$ represents the number of data points, $f$ denotes the underlying function to be estimated, $\hat{\nu}_n$ is an estimate of $f$, and $\sigma_n$ is the standard deviation of the additive Gaussian noise, then $\inf_{\hat{\nu}_n} \sup_f \mathbb{E}_f\| \hat{\nu}_n - f \|^2_2$ decays at the rate $(\max(1,\sigma_n^4)/n)^{\frac{2\beta}{2\beta+1}}$. Note that the rate achieved under purely additive noise is $({\sigma_n^2/n})^{\frac{2\beta}{2\beta+1}}$. We will provide a detailed comparison of this rate with the one obtained in the presence of both noise types across different regimes of their relative magnitudes, and discuss the insights that emerge from these comparisons.

math.ST↗
arXiv2024

Equidistribution of polynomially bounded o-minimal curves in homogeneous spaces

We extend Ratner's theorem on equidistribution of individual orbits of unipotent flows on finite volume homogeneous spaces of Lie groups to trajectories of non-contracting curves definable in polynomially bounded o-minimal structures. To be precise, let $\varphi:[0,\infty)\to \text{SL}(n,\mathbb R)$ be a continuous map whose coordinate functions are definable in a polynomially bounded o-minimal structure; for example, rational functions. Suppose that $\varphi$ is non-contracting; that is, for any linearly independent vectors $v_1,\ldots,v_k$ in $\mathbb R^n$, $\varphi(t).(v_1\wedge\cdots\wedge v_k)\not\to0$ as $t\to\infty$. Then, there exists a unique smallest subgroup $H_\varphi$ of $\text{SL}(n,\mathbb R)$ generated by unipotent one-parameter subgroups such that $\varphi(t)H_\varphi\to g_0H_\varphi$ in $\text{SL}(n,\mathbb R)/H_\varphi$ as $t\to\infty$ for some $g_0\in \text{SL}(n,\mathbb R)$. Let $G$ be a closed subgroup of $\text{SL}(n,\mathbb R)$ and $\Gamma$ be a lattice in $G$. Suppose that $\varphi([0,\infty))\subset G$. Then $H_\varphi\subset G$, and for any $x\in G/\Gamma$, the trajectory $\{\varphi(t)x:t\in [0,T]\}$ gets equidistributed with respect to the measure $g_0\mu_{Lx}$ as $T\to\infty$, where $L$ is a closed subgroup of $G$ such that $\overline{Hx}=Lx$ and $Lx$ admits a unique $L$-invariant probability measure, denoted by $\mu_{Lx}$. A crucial new ingredient in this work is proving that for any finite-dimensional representation $V$ of $\text{SL}(n,\mathbb R)$, there exist $T_0>0$, $C>0$, and $\alpha>0$ such that for any $v\in G$, the map $t\mapsto \|\varphi(t)v\|$ is $(C,\alpha)$-good on $[T_0,\infty)$.

math.DS↗
arXiv2023

Equidistribution of lattice orbits in the space of homothety classes of rank $2$ sublattices in $\mathbb R^3$

We study the distribution of orbits of a lattice $Γ\leq\text{SL}(3,\mathbb R)$ in the moduli space $X_{2,3}$ of covolume one rank-two discrete subgroups in $\mathbb R^3$. Each orbit is dense, and our main result is the limiting distribution of these orbits with respect to norm balls, where the norm is given by the sum of squares. Specifically, we consider $Γ_T=\{γ\inΓ:\|γ\|\leq T\}$ and show that, for any fixed $x_0\in X_{2,3}$ and $φ\in C_c(X_{2,3})$, $$\lim_{T\to\infty}\frac{1}{\#Γ_T}\sum_{γ\inΓ_T}φ(x_0\cdotγ)=\int_{X_{2,3}}φ(x)d \tildeν_{x_0}(x),$$ where $\tildeν_{x_0}$ is an explicit probability measure on $X_{2,3}$ depending on $x_0$. To prove our result, we use the duality principle developed by Gorodnik and Weiss which recasts the above problem into the problem of computation of certain volume estimates of growing skewed balls in $H$ and proving ergodic theorems of the left action of the skewed balls on $\text{SL}(3,\mathbb{R})/Γ$. The ergodic theorems are proven by applying theorems of Shah building on the linearisation technique. The main contribution of the paper is the application of the duality principle in the case where $H$ has infinitely many non-compact connected components.

math.DS↗
arXiv2023

Limiting distribution of dense orbits in a moduli space of rank $m$ discrete subgroups in $(m+1)$-space

We study the limiting distribution of dense orbits of a lattice subgroup $\Gamma\le \text{SL}(m+1,\mathbb{R})$ acting on $H\backslash\text{SL}(m+1,\mathbb{R})$, with respect to a filtration of growing norm balls. The novelty of our work is that the groups $H$ we consider have infinitely many non-trivial connected components. For a specific such $H$, the homogeneous space $H\backslash G$ identifies with $X_{m,m+1}$, a moduli space of rank $m$-discrete subgroups in $\mathbb{R}^{m+1}$. This study is motivated by the work of Shapira-Sargent who studied random walks on $X_{2,3}$.

math.DS↗
arXiv2022

RCRN: Real-world Character Image Restoration Network via Skeleton Extraction

Constructing high-quality character image datasets is challenging because real-world images are often affected by image degradation. There are limitations when applying current image restoration methods to such real-world character images, since (i) the categories of noise in character images are different from those in general images; (ii) real-world character images usually contain more complex image degradation, e.g., mixed noise at different noise levels. To address these problems, we propose a real-world character restoration network (RCRN) to effectively restore degraded character images, where character skeleton information and scale-ensemble feature extraction are utilized to obtain better restoration performance. The proposed method consists of a skeleton extractor (SENet) and a character image restorer (CiRNet). SENet aims to preserve the structural consistency of the character and normalize complex noise. Then, CiRNet reconstructs clean images from degraded character images and their skeletons. Due to the lack of benchmarks for real-world character image restoration, we constructed a dataset containing 1,606 character images with real-world degradation to evaluate the validity of the proposed method. The experimental results demonstrate that RCRN outperforms state-of-the-art methods quantitatively and qualitatively.

cs.CV↗
arXiv2022

Joint Prediction of Monocular Depth and Structure using Planar and Parallax Geometry

Supervised learning depth estimation methods can achieve good performance when trained on high-quality ground-truth, like LiDAR data. However, LiDAR can only generate sparse 3D maps which causes losing information. Obtaining high-quality ground-truth depth data per pixel is difficult to acquire. In order to overcome this limitation, we propose a novel approach combining structure information from a promising Plane and Parallax geometry pipeline with depth information into a U-Net supervised learning network, which results in quantitative and qualitative improvement compared to existing popular learning-based methods. In particular, the model is evaluated on two large-scale and challenging datasets: KITTI Vision Benchmark and Cityscapes dataset and achieve the best performance in terms of relative error. Compared with pure depth supervision models, our model has impressive performance on depth prediction of thin objects and edges, and compared to structure prediction baseline, our model performs more robustly.

cs.CV↗
arXiv2022

Skeletal Human Action Recognition using Hybrid Attention based Graph Convolutional Network

In skeleton-based action recognition, Graph Convolutional Networks model human skeletal joints as vertices and connect them through an adjacency matrix, which can be seen as a local attention mask. However, in most existing Graph Convolutional Networks, the local attention mask is defined based on natural connections of human skeleton joints and ignores the dynamic relations for example between head, hands and feet joints. In addition, the attention mechanism has been proven effective in Natural Language Processing and image description, which is rarely investigated in existing methods. In this work, we proposed a new adaptive spatial attention layer that extends local attention map to global based on relative distance and relative angle information. Moreover, we design a new initial graph adjacency matrix that connects head, hands and feet, which shows visible improvement in terms of action recognition accuracy. The proposed model is evaluated on two large-scale and challenging datasets in the field of human activities in daily life: NTU-RGB+D and Kinetics skeleton. The results demonstrate that our model has strong performance on both dataset.

cs.CV↗
arXiv2021

Knowledge-aware Coupled Graph Neural Network for Social Recommendation

Social recommendation task aims to predict users' preferences over items with the incorporation of social connections among users, so as to alleviate the sparse issue of collaborative filtering. While many recent efforts show the effectiveness of neural network-based social recommender systems, several important challenges have not been well addressed yet: (i) The majority of models only consider users' social connections, while ignoring the inter-dependent knowledge across items; (ii) Most of existing solutions are designed for singular type of user-item interactions, making them infeasible to capture the interaction heterogeneity; (iii) The dynamic nature of user-item interactions has been less explored in many social-aware recommendation techniques. To tackle the above challenges, this work proposes a Knowledge-aware Coupled Graph Neural Network (KCGN) that jointly injects the inter-dependent knowledge across items and users into the recommendation framework. KCGN enables the high-order user- and item-wise relation encoding by exploiting the mutual information for global graph structure awareness. Additionally, we further augment KCGN with the capability of capturing dynamic multi-typed user-item interactive patterns. Experimental studies on real-world datasets show the effectiveness of our method against many strong baselines in a variety of settings. Source codes are available at: https://github.com/xhcdream/KCGN.

cs.IR↗
arXiv2021

Global Context Enhanced Social Recommendation with Hierarchical Graph Neural Networks

Social recommendation which aims to leverage social connections among users to enhance the recommendation performance. With the revival of deep learning techniques, many efforts have been devoted to developing various neural network-based social recommender systems, such as attention mechanisms and graph-based message passing frameworks. However, two important challenges have not been well addressed yet: (i) Most of existing social recommendation models fail to fully explore the multi-type user-item interactive behavior as well as the underlying cross-relational inter-dependencies. (ii) While the learned social state vector is able to model pair-wise user dependencies, it still has limited representation capacity in capturing the global social context across users. To tackle these limitations, we propose a new Social Recommendation framework with Hierarchical Graph Neural Networks (SR-HGNN). In particular, we first design a relation-aware reconstructed graph neural network to inject the cross-type collaborative semantics into the recommendation framework. In addition, we further augment SR-HGNN with a social relation encoder based on the mutual information learning paradigm between low-level user embeddings and high-level global representation, which endows SR-HGNN with the capability of capturing the global social contextual signals. Empirical results on three public benchmarks demonstrate that SR-HGNN significantly outperforms state-of-the-art recommendation methods. Source codes are available at: https://github.com/xhcdream/SR-HGNN.

cs.IR↗