arXiv subjects

Jie Chang

Publications and source records attributed to Jie Chang.

16 recordsLinked to original sources

arXiv2026

Rail Track Extraction from Rasterized Classified Point Clouds Using a Full-Resolution, Fully Convolutional Recurrent Neural Network

Rail track extraction is essential for effective railway asset management and maintenance, especially in automated inspection and mapping workflows. This paper introduces a novel method for extracting rail tracks from classified 3D point clouds using a fully convolutional recurrent neural network that preserves full spatial resolution and is trained exclusively on synthetically generated data. This approach enhances per-pixel quality and is particularly suited for rail track extraction. The proposed method begins by rasterizing points corresponding to railroad tracks, then applies the neural network to reduce noise and yield a cleaner track representation suitable for vectorization [1]. Subsequent morphological operations further refine the resultant data, enabling accurate track centerline extraction. Next, the extracted centerlines undergo smoothing to eliminate residual irregularities [2, 3]. Finally, the algorithm transfers 3D information from lidar points onto 2D polylines and applies additional vertical smoothing. A single centerline for both tracks is found using the Dynamic Time Warping (DTW) algorithm [4]. The final outcome consists of rail top centerlines and track centerlines derived for rail pairs, with minimal manual intervention. Experimental validation confirms the effectiveness of this method in yielding high-quality rail track extraction.

cs.CV↗

arXiv2025

Confidence Intervals Using Turing's Estimator: Simulations and Applications

Turing's estimator allows one to estimate the probabilities of outcomes that either do not appear or only rarely appear in a given random sample. We perform a simulation study to understand the finite sample performance of several related confidence intervals (CIs) and introduce an approach for selecting the appropriate CI for a given sample. We give an application to the problem of authorship attribution and apply it to a dataset comprised of tweets from users on X (Twitter). Further, we derive several theoretical results about asymptotic normality and asymptotic Poissonity of Turing's estimator for two important discrete distributions.

math.ST↗

arXiv2024

Minimizing information loss reduces spiking neuronal networks to differential equations

Spiking neuronal networks (SNNs) are widely used in computational neuroscience, from biologically realistic modeling of local cortical networks to phenomenological modeling of the whole brain. Despite their prevalence, a systematic mathematical theory for finite-sized SNNs remains elusive, even for idealized homogeneous networks. The primary challenges are twofold: 1) the rich, parameter-sensitive SNN dynamics, and 2) the singularity and irreversibility of spikes. These challenges pose significant difficulties when relating SNNs to systems of differential equations, leading previous studies to impose additional assumptions or to focus on individual dynamic regimes. In this study, we introduce a Markov approximation of homogeneous SNN dynamics to minimize information loss when translating SNNs into ordinary differential equations. Our only assumption for the Markov approximation is the fast self-decorrelation of synaptic conductances. The system of ordinary differential equations derived from the Markov model effectively captures high-frequency partial synchrony and the metastability of finite-neuron networks produced by interacting excitatory and inhibitory populations. Besides accurately predicting dynamical statistics, such as firing rates, our theory also quantitatively captures the geometry of attractors and bifurcation structures of SNNs. Thus, our work provides a comprehensive mathematical framework that can systematically map parameters of single-neuron physiology, network coupling, and external stimuli to homogeneous SNN dynamics.

q-bio.NC↗

arXiv2024

CDSE-UNet: Enhancing COVID-19 CT Image Segmentation with Canny Edge Detection and Dual-Path SENet Feature Fusion

Accurate segmentation of COVID-19 CT images is crucial for reducing the severity and mortality rates associated with COVID-19 infections. In response to blurred boundaries and high variability characteristic of lesion areas in COVID-19 CT images, we introduce CDSE-UNet: a novel UNet-based segmentation model that integrates Canny operator edge detection and a dual-path SENet feature fusion mechanism. This model enhances the standard UNet architecture by employing the Canny operator for edge detection in sample images, paralleling this with a similar network structure for semantic feature extraction. A key innovation is the Double SENet Feature Fusion Block, applied across corresponding network layers to effectively combine features from both image paths. Moreover, we have developed a Multiscale Convolution approach, replacing the standard Convolution in UNet, to adapt to the varied lesion sizes and shapes. This addition not only aids in accurately classifying lesion edge pixels but also significantly improves channel differentiation and expands the capacity of the model. Our evaluations on public datasets demonstrate CDSE-UNet's superior performance over other leading models, particularly in segmenting large and small lesion areas, accurately delineating lesion edges, and effectively suppressing noise

eess.IV↗

arXiv2024

Tracking sustainability: co-evolution of economic and ecological activities in the industrialization of the United Kingdom and China

The co-evolution of economic and ecological activities represents one of the fundamental challenges in the realm of sustainable development. This study on the word trends in mainstream newspapers from the UK and China reveals that both early-industrialised countries and latecomers follow three modes of economic and ecological co-evolution. First, both economic and ecological words demonstrate an S-shaped growth trajectory, and the mode underscores the importance of information propagation, whilst also highlighting the crucial role of self-organisation in the accept society. Second, the co-occurrence of these two type words exhibits a Z-shaped relationship: for two-thirds of the observed period, they display synergistic interactions, while the remaining time shows trade-offs. Lastly, the words related to ecological degradation follow M-shaped trajectories in parallel with economic growth, suggesting periodic disruptions and reconstructions in their interrelationships. Our findings contribute to a more nuanced understanding of the co-evolutionary mechanisms that govern collective behaviours in human society.

physics.soc-ph↗

arXiv2020

A gradient model for the spatial patterns of cities

The dynamics of city's spatial structures are determined by the coupling of functional components (such as restaurants and shops) and human beings within the city. Yet, there still lacks mechanism models to quantify the spatial distribution of functional components. Here, we establish a gradient model to simulate the density curves of multiple types of components based on the equilibria of gravitational and repulsive forces along the urban-rural gradient. The forces from city center to components are determined by both the city's attributes (land rent, population and people's environmental preferences) and the components attributes (supply capacity, product transportability and environmental impacts). The simulation for the distribution curves of 22 types of components on the urban-rural gradient are a good fit for the real-world data in cities. Based on the 4 typical types of components, the model reveals a bottom-up self-organizing mechanism that is, the patterns in city development are determined by the economic, ecological, and social attributes of both cities and components. Based on the mechanism, we predict the distribution curves of many types of components along with the development of cities. The model provides a general tool for analyzing the distribution of objects on the gradients.

physics.soc-ph↗

arXiv2020

Prime-Aware Adaptive Distillation

Knowledge distillation(KD) aims to improve the performance of a student network by mimicing the knowledge from a powerful teacher network. Existing methods focus on studying what knowledge should be transferred and treat all samples equally during training. This paper introduces the adaptive sample weighting to KD. We discover that previous effective hard mining methods are not appropriate for distillation. Furthermore, we propose Prime-Aware Adaptive Distillation (PAD) by the incorporation of uncertainty learning. PAD perceives the prime samples in distillation and then emphasizes their effect adaptively. PAD is fundamentally different from and would refine existing methods with the innovative view of unequal training. For this reason, PAD is versatile and has been applied in various tasks including classification, metric learning, and object detection. With ten teacher-student combinations on six datasets, PAD promotes the performance of existing distillation methods and outperforms recent state-of-the-art methods.

cs.CV↗

arXiv2020

Data Uncertainty Learning in Face Recognition

Modeling data uncertainty is important for noisy images, but seldom explored for face recognition. The pioneer work, PFE, considers uncertainty by modeling each face image embedding as a Gaussian distribution. It is quite effective. However, it uses fixed feature (mean of the Gaussian) from an existing model. It only estimates the variance and relies on an ad-hoc and costly metric. Thus, it is not easy to use. It is unclear how uncertainty affects feature learning. This work applies data uncertainty learning to face recognition, such that the feature (mean) and uncertainty (variance) are learnt simultaneously, for the first time. Two learning methods are proposed. They are easy to use and outperform existing deterministic methods as well as PFE on challenging unconstrained scenarios. We also provide insightful analysis on how incorporating uncertainty estimation helps reducing the adverse effects of noisy samples and affects the feature learning.

cs.CV↗

arXiv2020

Modern cities emerge as 'super-cells' where enclosed industrial systems are hotspots of goods and services

Prevailing hypotheses recognize cities as 'super-organisms' which both provides organizing principles for cities and fills the scalar gap in the hierarchical living system between ecosystems and the entire planet. However, most analogies between the traits of organisms and cities are inappropriate making the super-organism model impractical as a means to acquire new knowledge. Using a cluster analysis of 15 traits of cities and other living systems, we found that modern cities are more similar to eukaryotic cells than to multicellular organisms. Enclosed industrial systems, such as factories and greenhouses, dominate modern cities and are analogous to organelles as hotspots that provide high-flux goods and services. Therefore, we propose a 'super-cell city model' as more appropriate than the super-organism model. In addition to the theoretical significance, our model also recognizes enclosed industrial systems as functional components that improve the vitality and sustainability of cities.

physics.soc-ph↗

arXiv2019

Handwritten Chinese Font Generation with Collaborative Stroke Refinement

Automatic character generation is an appealing solution for new typeface design, especially for Chinese typefaces including over 3700 most commonly-used characters. This task has two main pain points: (i) handwritten characters are usually associated with thin strokes of few information and complex structure which are error prone during deformation; (ii) thousands of characters with various shapes are needed to synthesize based on a few manually designed characters. To solve those issues, we propose a novel convolutional-neural-network-based model with three main techniques: collaborative stroke refinement, using collaborative training strategy to recover the missing or broken strokes; online zoom-augmentation, taking the advantage of the content-reuse phenomenon to reduce the size of training set; and adaptive pre-deformation, standardizing and aligning the characters. The proposed model needs only 750 paired training samples; no pre-trained network, extra dataset resource or labels is needed. Experimental results show that the proposed method significantly outperforms the state-of-the-art methods under the practical restriction on handwritten font synthesis.

cs.CV↗

arXiv2018

An Element Sensitive Saliency Model with Position Prior Learning for Web Pages

Understanding human visual attention is important for multimedia applications. Many studies have attempted to learn from eye-tracking data and build computational saliency prediction models. However, limited efforts have been devoted to saliency prediction for Web pages, which are characterized by more diverse content elements and spatial layouts. In this paper, we propose a novel end-to-end deep generative saliency model for Web pages. To capture position biases introduced by page layouts, a Position Prior Learning sub-network is proposed, which models position biases as multivariate Gaussian distribution using variational auto-encoder. To model different elements of a Web page, a Multi Discriminative Region Detection (MDRD) branch and a Text Region Detection(TRD) branch are introduced, which target to extract discriminative localizations and "prominent" text regions likely to correspond to human attention, respectively. We validate the proposed model with FiWI, a public Web-page dataset, and shows that the proposed model outperforms the state-of-art models for Web-page saliency prediction.

cs.CV↗

arXiv2018

Separating Style and Content for Generalized Style Transfer

Neural style transfer has drawn broad attention in recent years. However, most existing methods aim to explicitly model the transformation between different styles, and the learned model is thus not generalizable to new styles. We here attempt to separate the representations for styles and contents, and propose a generalized style transfer network consisting of style encoder, content encoder, mixer and decoder. The style encoder and content encoder are used to extract the style and content factors from the style reference images and content reference images, respectively. The mixer employs a bilinear model to integrate the above two factors and finally feeds it into a decoder to generate images with target style and content. To separate the style features and content features, we leverage the conditional dependence of styles and contents given an image. During training, the encoder network learns to extract styles and contents from two sets of reference images in limited size, one with shared style and the other with shared content. This learning framework allows simultaneous style transfer among multiple styles and can be deemed as a special `multi-task' learning scenario. The encoders are expected to capture the underlying features for different styles and contents which is generalizable to new styles and contents. For validation, we applied the proposed algorithm to the Chinese Typeface transfer problem. Extensive experiment results on character generation have demonstrated the effectiveness and robustness of our method.

cs.CV↗

arXiv2017

Chinese Typeface Transformation with Hierarchical Adversarial Network

In this paper, we explore automated typeface generation through image style transfer which has shown great promise in natural image generation. Existing style transfer methods for natural images generally assume that the source and target images share similar high-frequency features. However, this assumption is no longer true in typeface transformation. Inspired by the recent advancement in Generative Adversarial Networks (GANs), we propose a Hierarchical Adversarial Network (HAN) for typeface transformation. The proposed HAN consists of two sub-networks: a transfer network and a hierarchical adversarial discriminator. The transfer network maps characters from one typeface to another. A unique characteristic of typefaces is that the same radicals may have quite different appearances in different characters even under the same typeface. Hence, a stage-decoder is employed by the transfer network to leverage multiple feature layers, aiming to capture both the global and local features. The hierarchical adversarial discriminator implicitly measures data discrepancy between the generated domain and the target domain. To leverage the complementary discriminating capability of different feature layers, a hierarchical structure is proposed for the discriminator. We have experimentally demonstrated that HAN is an effective framework for typeface transfer and characters restoration.

cs.CV↗

arXiv2017

Chinese Typography Transfer

In this paper, we propose a new network architecture for Chinese typography transformation based on deep learning. The architecture consists of two sub-networks: (1)a fully convolutional network(FCN) aiming at transferring specified typography style to another in condition of preserving structure information; (2)an adversarial network aiming at generating more realistic strokes in some details. Unlike models proposed before 2012 relying on the complex segmentation of Chinese components or strokes, our model treats every Chinese character as an inseparable image, so pre-processing or post-preprocessing are abandoned. Besides, our model adopts end-to-end training without pre-trained used in other deep models. The experiments demonstrates that our model can synthesize realistic-looking target typography from any source typography both on printed style and handwriting style.

cs.CV↗

arXiv2012

Cooperating epidemics of foodborne diseases with diverse trade networks

The frequent outbreak of severe foodborne diseases warns of a potential threat that the global trade networks could spread fatal pathogens. The global trade network is a typical overlay network, which compounds multiple standalone trade networks representing the transmission of a single product and connecting the same set of countries and territories through their own set of trade interactions. Although the epidemic dynamic implications of overlay networks have been debated in recent studies, some general answers for the overlay of multiple and diverse standalone networks remain elusive, especially the relationship between the heterogeneity and diversity of a set of standalone networks and the behavior of the overlay network. In this paper, we establish a general analysis framework for multiple overlay networks based on diversity theory. The framework could reveal the critical epidemic mechanisms beyond overlay processes. Applying the framework to global trade networks, we found that, although the distribution of connectivity of standalone trade networks was highly heterogeneous, epidemic behavior on overlay networks is more dependent on cooperation among standalone trade networks rather than on a few high-connectivity networks as the general property of complex systems with heterogeneous distribution. Moreover, the analysis of overlay trade networks related to 7 real pathogens also suggested that epidemic behavior is not controlled by high-connectivity goods but that the actual compound mode of overlay trade networks plays a critical role in spreading pathogens. Finally, we study the influence of cooperation mechanisms on the stability of overlay networks and on the control of global epidemics. The framework provides a general tool to study different problems on overlay networks.

physics.soc-ph↗

arXiv2011

The role of vegetables trade network in global epidemics

The outbreak of enterohemorrhagic Escherichia coli (EHEC) in May 2011 warns the potential threats of the world vegetables trade network (VTN) in spreading fatal infectious diseases. The heterogeneous weight distribution and multi-scale activity of intermediary networks affects the diffusion, proliferation and extinction of epidemics. Here, we constructed a dual-weighted VTN with 118 major countries and territories from FAO 2008 statistic data about global vegetation production and trade, and develop a reaction-diffusion model to simulate the epidemic behaviors in through VTN. We found an emerged asymmetric threshold of epidemic on VTN, in which local proliferation within nodes plays a more critical role than global diffusion in spreading of EHEC-like diseases, i.e. sufficient local proliferation is the precondition for global diffusion. We also found that a strong modularity on VTN structure, which restricts the spreading of EHEC-like diseases; however, within the communities, the diffusion is quick and easy. There is, moreover, a critical "epidemic stem", in which a serial of positive feedback loop for amplifying the proliferation and diffusion pathogens has been identified from entire VTN. Surprisingly, statistical analysis shows a well consistency between theoretical composition of stem and actual pattern of EHEC. The results provide a chance to design gradient control strategies for controlling disease global diffusion. Our analysis provided the first inspect of global epidemics mediated by trade networks for improved control and immunity strategies in the future.

q-bio.PE↗