Qiming Ma, Fanliang Bu^*, Rong Wang, Lingbin Bu, Yifan Wang, Zhiyuan Li

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 5169-5184, 2025, DOI:10.32604/cmc.2025.061187 - 06 March 2025

Abstract Speech-face association aims to achieve identity matching between facial images and voice segments by aligning cross-modal features. Existing research primarily focuses on learning shared-space representations and computing one-to-one similarities between cross-modal sample pairs to establish their correlation. However, these approaches do not fully account for intra-class variations between the modalities or the many-to-many relationships among cross-modal samples, which are crucial for robust association modeling. To address these challenges, we propose a novel framework that leverages global information to align voice and face embeddings while effectively correlating identity information embedded in both modalities. First, we jointly… More >

Xin Wen^*, Xiao Zheng, Yu He

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 4371-4388, 2025, DOI:10.32604/cmc.2025.060661 - 06 March 2025

Abstract Detecting surface defects on unused rails is crucial for evaluating rail quality and durability to ensure the safety of rail transportation. However, existing detection methods often struggle with challenges such as complex defect morphology, texture similarity, and fuzzy edges, leading to poor accuracy and missed detections. In order to resolve these problems, we propose MSCM-Net (Multi-Scale Cross-Modal Network), a multiscale cross-modal framework focused on detecting rail surface defects. MSCM-Net introduces an attention mechanism to dynamically weight the fusion of RGB and depth maps, effectively capturing and enhancing features at different scales for each modality. To… More >

Jingjing Yan¹, Xuyang Zhuang^2,*, Xuezhuan Zhao^1,2, Xiaoyan Shao^1,*, Jiaqi Han¹

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 5363-5386, 2025, DOI:10.32604/cmc.2025.059709 - 06 March 2025

Abstract The key to the success of few-shot semantic segmentation (FSS) depends on the efficient use of limited annotated support set to accurately segment novel classes in the query set. Due to the few samples in the support set, FSS faces challenges such as intra-class differences, background (BG) mismatches between query and support sets, and ambiguous segmentation between the foreground (FG) and BG in the query set. To address these issues, The paper propose a multi-module network called CAMSNet, which includes four modules: the General Information Module (GIM), the Class Activation Map Aggregation (CAMA) module, the… More >

Hongliang Tian, Zuoqing Li^*

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 3983-4002, 2025, DOI:10.32604/cmc.2025.059103 - 06 March 2025

Abstract Low data encryption efficiency and inadequate security are two issues with the current blockchain cross-chain transaction protection schemes. To address these issues, a blockchain cross-chain transaction protection scheme based on Fully Homomorphic Encryption (FHE) is proposed. In the proposed scheme, the functional relationship is established by Box-Muller, Discrete Gaussian Distribution Function (DGDF) and Uniform Random Distribution Function (URDF) are used to improve the security and efficiency of key generation. Subsequently, the data preprocessing function is introduced to perform cleaning, deduplication, and normalization operations on the transaction data of multi-key signature, and it is classified into… More >

Cheng Sun^1,3, Chen Zhao^2,3, Guohua Wang^2,3, Qianwen Mao^2,3, Rong Han^2,3,*

Phyton-International Journal of Experimental Botany, Vol.94, No.2, pp. 455-479, 2025, DOI:10.32604/phyton.2025.061462 - 06 March 2025

Abstract Enhanced UV-B radiation represents a major environmental factor impacting global cereal production. Researchers have explored various approaches to reduce the detrimental impact of UV-B radiation on crops. Recently, engineered nanoparticles, particularly cerium oxide nanoparticles (CeO₂-NPs), have attracted widespread interest for their ability to boost plant tolerance to a range of abiotic stresses. This study investigates how CeO₂-NPs application affects the morphology, physiology, biochemistry, and transcriptomics profiles of wheat seedling roots subjected to enhanced UV-B stress. The findings demonstrate that CeO₂-NPs notably promoted root length, fresh and dry weights, and root activity (p < 0.05) under enhanced UV-B… More >

Josef Walek^*, Petr Lichý

CMES-Computer Modeling in Engineering & Sciences, Vol.142, No.3, pp. 3135-3153, 2025, DOI:10.32604/cmes.2025.059889 - 03 March 2025

Abstract Plastometric experiments, supplemented with numerical simulations using the finite element method (FEM), can be advantageously used to characterize the deformation behavior of metallic materials. The accuracy of such simulations predicting deformation behaviors of materials is, however, primarily affected by the applied rheology law. The presented study focuses on the characterization of the deformation behavior of AISI 1045 type carbon steel, widely used e.g., in automotive and power engineering, under extreme conditions (i.e., high temperatures, strain rates). The study consists of two main parts: experimentally analyzing the flow stress development of the steel under different thermomechanical… More >

RAZIEH MOMEN-MESGIN¹, JAFAR REZAIE^2,*, VAHID NEJATI¹, PEYMAN NAJAFI MOGHADAM³

Oncology Research, Vol.33, No.3, pp. 665-674, 2025, DOI:10.32604/or.2024.054487 - 28 February 2025

Abstract Objectives: Due to systematic side effects, there is a growing interest in nanoparticle formulation of anticancer drugs. Here, we aimed to synthesize poly (styrene-alt-maleic anhydride) cross-linked by melamine (PSMA/Me) and coated with magnetite nanoparticles (MNPs) PSMA/Me/Fe₃O₄. In addition, we aimed to load paclitaxel (PTX) into PSMA/Me/Fe₃O₄ for drug delivery and anticancer investigations. Methods: Novel PSMA/Me was synthesized via free radical copolymerization, coated with Fe₃O₄, and then used as a transporter for PTX delivery. Fabricated copolymer was characterized using SEM, TGA, and XRD techniques. Drug release rate and loading efficiency were investigated. Human ovarian cancer cells (Skov-3) and… More >

YONG RAO^1,3,4, XIAO CHEN^5,6, KAIYU LI^1,3,4, MINHAI NIE^1,3,4, XUQIAN LIU^2,3,4,*

Oncology Research, Vol.33, No.3, pp. 577-590, 2025, DOI:10.32604/or.2024.053119 - 28 February 2025

Abstract Decorin (DCN) is primarily found in the connective tissues of various parts of the body, including the lungs, kidneys, bone tissue, aorta, and tendons. It is an important component of the extracellular matrix (ECM) and belongs to the class I small leucine-rich proteoglycans family. DCN is increasingly attracting attention due to its significant role in tumors, fibrotic diseases, and the regulation of vascular formation. Moreover, its anti-tumor properties have positioned it as a promising biomarker in the fight against cancer. Numerous studies have confirmed that DCN can exert inhibitory effects in various solid tumors, particularly… More >

Yujiao Tang¹, Yadong Wu^1,*, Yuanmei He², Jilin Liu¹, Weihan Zhang¹

CMC-Computers, Materials & Continua, Vol.82, No.2, pp. 2331-2352, 2025, DOI:10.32604/cmc.2024.059115 - 17 February 2025

Abstract Emotion recognition plays a crucial role in various fields and is a key task in natural language processing (NLP). The objective is to identify and interpret emotional expressions in text. However, traditional emotion recognition approaches often struggle in few-shot cross-domain scenarios due to their limited capacity to generalize semantic features across different domains. Additionally, these methods face challenges in accurately capturing complex emotional states, particularly those that are subtle or implicit. To overcome these limitations, we introduce a novel approach called Dual-Task Contrastive Meta-Learning (DTCML). This method combines meta-learning and contrastive learning to improve emotion… More >

Lihua Xie¹, Ni Tang¹, Qing Chen^1,*, Jun Li^2,*

CMC-Computers, Materials & Continua, Vol.82, No.2, pp. 3381-3397, 2025, DOI:10.32604/cmc.2024.058950 - 17 February 2025

Abstract In the age of information explosion and artificial intelligence, sentiment analysis tailored for the tobacco industry has emerged as a pivotal avenue for cigarette manufacturers to enhance their tobacco products. Existing solutions have primarily focused on intrinsic features within consumer reviews and achieved significant progress through deep feature extraction models. However, they still face these two key limitations: (1) neglecting the influence of fundamental tobacco information on analyzing the sentiment inclination of consumer reviews, resulting in a lack of consistent sentiment assessment criteria across thousands of tobacco brands; (2) overlooking the syntactic dependencies between Chinese… More >