Chuang-Chieh Lin¹, Yung-Shen Huang², Shih-Yeh Chen^2,*

CMC-Computers, Materials & Continua, Vol.86, No.2, pp. 1-19, 2026, DOI:10.32604/cmc.2025.072890 - 09 December 2025

Abstract With the rapid development of generative artificial intelligence (GenAI), the task of story visualization, which transforms natural language narratives into coherent and consistent image sequences, has attracted growing research attention. However, existing methods still face limitations in balancing multi-frame character consistency and generation efficiency, which restricts their feasibility for large-scale practical applications. To address this issue, this study proposes a modular cloud-based distributed system built on Stable Diffusion. By separating the character generation and story generation processes, and integrating multi-feature control techniques, a caching mechanism, and an asynchronous task queue architecture, the system enhances generation… More >

Jiqiang Xia¹, Qi Zhan¹, Le Tian^1,2,3,*, Yuxiang Hu^1,2,3, Jianhua Peng⁴

CMC-Computers, Materials & Continua, Vol.86, No.1, pp. 1-19, 2026, DOI:10.32604/cmc.2025.069533 - 10 November 2025

Abstract The rapid growth of distributed data-centric applications and AI workloads increases demand for low-latency, high-throughput communication, necessitating frequent and flexible updates to network routing configurations. However, maintaining consistent forwarding states during these updates is challenging, particularly when rerouting multiple flows simultaneously. Existing approaches pay little attention to multi-flow update, where improper update sequences across data plane nodes may construct deadlock dependencies. Moreover, these methods typically involve excessive control-data plane interactions, incurring significant resource overhead and performance degradation. This paper presents P4LoF, an efficient loop-free update approach that enables the controller to reroute multiple flows through More >

Wei Lin, Yi Sun^*

CMC-Computers, Materials & Continua, Vol.85, No.3, pp. 5117-5134, 2025, DOI:10.32604/cmc.2025.067968 - 23 October 2025

Abstract To enable efficient sharing of unbounded streaming data, this paper introduces blockchain technology into traditional cloud data, proposing a hybrid on-chain/off-chain storage model. We design a real-time verifiable data structure that is more suitable for streaming data to achieve efficient real-time verifiability for streaming data. Based on the notch gate hash function and vector commitment, an adaptive notch gate hash tree structure is constructed, and an efficient real-time verifiable data structure for on-chain and off-chain stream data is proposed. The structure binds dynamic root nodes sequentially to ordered leaf nodes in its child nodes. Only… More >

Tian Tian^1,2, Boyue Wang^1,2, Xiaxia He^1,2,*, Wentong Wang³, Meng Wang¹

CMC-Computers, Materials & Continua, Vol.85, No.3, pp. 4885-4898, 2025, DOI:10.32604/cmc.2025.067795 - 23 October 2025

Abstract Attribute-graph clustering aims to divide the graph nodes into distinct clusters in an unsupervised manner, which usually encodes the node attribute feature and the corresponding graph structure into a latent feature space. However, traditional attribute-graph clustering methods often neglect the effect of neighbor information on clustering, leading to suboptimal clustering results as they fail to fully leverage the rich contextual information provided by neighboring nodes, which is crucial for capturing the intrinsic relationships between nodes and improving clustering performance. In this paper, we propose a novel Neighbor Dual-Consistency Constrained Attribute-Graph Clustering that leverages information from… More >

Xiaoliang Zhu, Hao Chen, Xin Yang, Zhicheng Dai, Liang Zhao^*

CMC-Computers, Materials & Continua, Vol.85, No.1, pp. 1585-1602, 2025, DOI:10.32604/cmc.2025.066147 - 29 August 2025

Abstract Facial expression datasets commonly exhibit imbalances between various categories or between difficult and simple samples. This imbalance introduces bias into feature extraction within facial expression recognition (FER) models, which hinders the algorithm’s comprehension of emotional states and reduces the overall recognition accuracy. A novel FER model is introduced to address these issues. It integrates rebalancing mechanisms to regulate attention consistency and focus, offering enhanced efficacy. Our approach proposes the following improvements: (i) rebalancing weights are used to enhance the consistency between the heatmaps of an original face sample and its horizontally flipped counterpart; (ii) coefficient More >

Xian Yu, Jianxun Zhang^*, Siran Tian, Xiaobao He

CMC-Computers, Materials & Continua, Vol.85, No.1, pp. 1883-1897, 2025, DOI:10.32604/cmc.2025.065529 - 29 August 2025

Abstract In recent years, diffusion models have achieved remarkable progress in image generation. However, extending them to text-to-video (T2V) generation remains challenging, particularly in maintaining semantic consistency and visual quality across frames. Existing approaches often overlook the synergy between high-level semantics and low-level texture information, resulting in blurry or temporally inconsistent outputs. To address these issues, we propose Dual Consistency Training (DCT), a novel framework designed to jointly optimize semantic and texture consistency in video generation. Specifically, we introduce a multi-scale spatial adapter to enhance spatial feature extraction, and leverage the complementary strengths of CLIP and More >

Yi Zhang¹, Diju Gao^1,*, Yide Wang², Zhaoxia Huang³

Energy Engineering, Vol.122, No.9, pp. 3681-3702, 2025, DOI:10.32604/ee.2025.068656 - 26 August 2025

Abstract Hydrogen fuel cell ships are one of the key solutions to achieving zero carbon emissions in shipping. Multi-fuel cell stacks (MFCS) systems are frequently employed to fulfill the power requirements of high-load power equipment on ships. Compared to single-stack system, MFCS may be difficult to apply traditional energy management strategies (EMS) due to their complex structure. In this paper, a two-layer power allocation strategy for MFCS of a hydrogen fuel cell ship is proposed to reduce the complexity of the allocation task by splitting it into each layer of the EMS. The first layer of… More > Graphic Abstract

Amani Baazeem¹, Muhammad Shoaib Arif^2,*, Yasir Nawaz³, Kamaleldin Abodayeh²

CMES-Computer Modeling in Engineering & Sciences, Vol.143, No.3, pp. 3463-3489, 2025, DOI:10.32604/cmes.2025.066299 - 30 June 2025

Abstract The numerical approximation of stochastic partial differential equations (SPDEs), particularly those including q-diffusion, poses considerable challenges due to the requirements for high-order precision, stability amongst random perturbations, and processing efficiency. Because of their simplicity, conventional numerical techniques like the Euler-Maruyama method are frequently employed to solve stochastic differential equations; nonetheless, they may have low-order accuracy and lower stability in stiff or high-resolution situations. This study proposes a novel computational scheme for solving SPDEs arising from a stochastic SEIR model with q-diffusion and a general incidence rate function. A proposed computational scheme can be used to… More >

Zichen Li^1,#, Jukui Ma^2,#, Minjun Liu³, Guowei Geng^1,*, Hongxia Zhang^1,*

Phyton-International Journal of Experimental Botany, Vol.94, No.6, pp. 1841-1856, 2025, DOI:10.32604/phyton.2025.066148 - 27 June 2025

Abstract Sweet potatoes are significant cash crops, however, their yield and quality are greatly compromised by viral diseases. In this study, the complete genomic sequences of two Sweet Potato Virus 2 (SPV2) isolates from infected sweet potato leaves in the Shandong (designated as SPV2-SDYT, GenBank No. PQ855660.1) and Jiangsu (designated as SPV2-JSXZ, GenBank No. PQ855661.1) provinces in China were obtained using 5^′ RACE and RT-PCR amplification. Consistency, phylogeny, codon usage bias, recombination, and selection pressure analyses were conducted using the SPV2-SDYT and SPV2-JSXZ genome sequences. The complete genome sequences of SPV2-SDYT and SPV2-JSXZ were 10561 nucleotides (nt)… More >

Chunming Tang^*, Yu Wang

CMC-Computers, Materials & Continua, Vol.83, No.3, pp. 5115-5128, 2025, DOI:10.32604/cmc.2025.062328 - 19 May 2025

Abstract Image dehazing aims to generate clear images critical for subsequent visual tasks. CNNs have made significant progress in the field of image dehazing. However, due to the inherent limitations of convolution operations, it is challenging to effectively model global context and long-range spatial dependencies effectively. Although the Transformer can address this issue, it faces the challenge of excessive computational requirements. Therefore, we propose the FS-MSFormer network, an asymmetric encoder-decoder architecture that combines the advantages of CNNs and Transformers to improve dehazing performance. Specifically, the encoding process employs two branches for multi-scale feature extraction. One branch… More >