Previous multi-view contrastive learning methods typically operate at two scales: instance-level and cluster-level. The former generally constructs positive and negative pairs based on the correspondence between samples and view instances. These methods aim to bring positive pairs closer and push negative pairs further apart in the latent space. This kind of approaches has the drawback of inevitably introducing false negatives in an unsupervised setting, leading to reduced model discriminability. The latter usually involves calculating cluster assignments for samples under each view and maximizing view consensus by reducing distribution discrepancies through methods like optimizing the KL divergence between different view distributions or maximizing mutual information. However, clusters represent a macro structure that overlooks the local structure within the sample set, and the relationships between clusters across different views cannot be explicitly measured. To overcome the shortcomings of these two types of methods, we propose a method named Multi-view Granular-ball Contrastive Clustering (MGBCC). This method segments the sample set into coarse-grained granular balls, and establishes associations between intra-view and cross-view granular balls. These associations are reinforced in a shared latent space, thereby achieving multi-granularity contrastive learning. Granular balls lie between instances and clusters, naturally preserving the local topological structure of the sample set. We conduct extensive experiments to validate the effectiveness of the proposed method.

Train control systems are critical for ensuring railway operational safety. With the advancement of railway intelligentization strategies and the rapid development of information technology, the train control system is evolving from closed to open systems. In this context, the security of the key management system(KMS) has become a core research direction, as the train-ground communication faces the risk of unauthorized access due to the use of open channels. Currently deployed KMS in industrial settings predominantly adopt offline architectures, which exhibit vulnerabilities to physical tampering during key storage and computation processes. Meanwhile, there is a general lack of research on the adaptation of mainstream online key management technologies (such as Hardware Security Modules (HSM), quantum key distribution(QKD), and Trusted Computing(TC)) in the context of rail train control systems. To address these challenges, this paper proposes an enhanced scheme based on an online key management mechanism. By integrating TC technology and optimizing the key distribution strategy, the scheme provides high-security protection throughout the full key lifecycle (generation, distribution, storage, and destruction). Experimental results demonstrate that, compared to traditional offline systems, the proposed solution significantly improves overall system security, resilience against attacks, and key update efficiency, thereby establishing a robust foundation for constructing highly secure modern railway train control systems.

As one of the typical Industrial Control System (ICS), railway control systems nowadays are faced with many security risks during its digital transformation empowered by various Information and Communications Technology (ICT), e.g., AI, 5G/6G. In addition to ensuring safety, the fundamental property of railway control system, it is important to conduct comprehensive security assessment during their design, development, deployment, and maintenance. But how to select and apply the most appropriate and efficient assessment methods is not straightforward and deserves careful studies. This paper firstly provides an in-depth analysis of the existing standards•1 for secure design and security assessment of railway control systems, in order to clarify the relationship between safety and security. It then comparatively studies the qualitative, quantitative, and simulation-based security assessment methods, along with their application scenarios, with an objective to obtaining an effective combination of these methods for railway control systems. By taking into account the specific security requirements and system characteristics of rail control systems, we finally propose a comprehensive security assessment framework for rail control systems.

All tables can be represented as grids. Based on this observation, we propose GridFormer, a novel approach for interpreting unconstrained table structures by predicting the vertex and edge of a grid. First, we propose a flexible table representation in the form of an M X N grid. In this representation, the vertexes and edges of the grid store the localization and adjacency information of the table. Then, we introduce a DETR-style table structure recognizer to efficiently predict this multi-objective information of the grid in a single shot. Specifically, given a set of learned row and column queries, the recognizer directly outputs the vertexes and edges information of the corresponding rows and columns. Extensive experiments on five challenging benchmarks which include wired, wireless, multi-merge-cell, oriented, and distorted tables demonstrate the competitive performance of our model over other methods.

Online and offline handwritten Chinese text recognition (HTCR) has been studied for decades. Early methods adopted oversegmentation-based strategies but suffered from low speed, insufficient accuracy, and high cost of character segmentation annotations. Recently, segmentation-free methods based on connectionist temporal classification (CTC) and attention mechanism, have dominated the field of HCTR. However, people actually read text character by character, especially for ideograms such as Chinese. This raises the question: are segmentation-free strategies really the best solution to HCTR? To explore this issue, we propose a new segmentation-based method for recognizing handwritten Chinese text that is implemented using a simple yet efficient fully convolutional network. A novel weakly supervised learning method is proposed to enable the network to be trained using only transcript annotations; thus, the expensive character segmentation annotations required by previous segmentation-based methods can be avoided. Owing to the lack of context modeling in fully convolutional networks, we propose a contextual regularization method to integrate contextual information into the network during the training stage, which can further improve the recognition performance. Extensive experiments conducted on four widely used benchmarks, namely CASIA-HWDB, CASIA-OLHWDB, ICDAR2013, and SCUT-HCCDoc, show that our method significantly surpasses existing methods on both online and offline HCTR, and exhibits a considerably higher inference speed than CTC/attention-based approaches.

Automatic font generation remains a challenging research issue due to the large amounts of characters with complicated structures. Typically, only a few samples can serve as the style/content reference (termed few-shot learning), which further increases the difficulty to preserve local style patterns or detailed glyph structures. We investigate the drawbacks of previous studies and find that a coarsegrained discriminator is insufficient for supervising a font generator. To this end, we propose a novel Component-Aware Module (CAM), which supervises the generator to decouple content and style at a more fine-grained level, i.e., the component level. Different from previous studies struggling to increase the complexity of generators, we aim to perform more effective supervision for a relatively simple generator to achieve its full potential, which is a brand new perspective for font generation. The whole framework achieves remarkable results by coupling component-level supervision with adversarial learning, hence we call it Component-Guided GAN, shortly CG-GAN. Extensive experiments show that our approach outperforms state-of-the-art one-shot font generation methods. Furthermore, it can be applied to handwritten word synthesis and scene text image editing, suggesting the generalization of our approach.

Visual information extraction (VIE) has attracted increasing attention in recent years. The existing methods usually first organized optical character recognition (OCR) results in plain texts and then utilized token-level category annotations as supervision to train a sequence tagging model. However, it expends great annotation costs and may be exposed to label confusion, the OCR errors will also significantly affect the final performance. In this paper, we propose a unified weakly-supervised learning framework called TCPNet (Tag, Copy or Predict Network), which introduces 1) an efficient encoder to simultaneously model the semantic and layout information in 2D OCR results, 2) a weakly-supervised training method that utilizes only sequence-level supervision; and 3) a flexible and switchable decoder which contains two inference modes: one (Copy or Predict Mode) is to output key information sequences of different categories by copying a token from the input or predicting one in each time step, and the other (Tag Mode) is to directly tag the input sequence in a single forward pass. Our method shows new state-of-the-art performance on several public benchmarks, which fully proves its effectiveness.

In this paper, we propose an end-to-end trainable framework for restoring historical documents content that follows the correct reading order. In this framework, two branches named character branch and layout branch are added behind the feature extraction network. The character branch localizes individual characters in a document image and recognizes them simultaneously. Then we adopt a post-processing method to group them into text lines. The layout branch based on fully convolutional network outputs a binary mask. We then use Hough transform for line detection on the binary mask and combine character results with the layout information to restore document content. These two branches can be trained in parallel and are easy to train. Furthermore, we propose a re-score mechanism to minimize recognition error. Experiment results on the extended Chinese historical document MTHv2 dataset demonstrate the effectiveness of the proposed framework.