Haixia Wang, Huan Zhang, Xiuling Wang, Xule Xin, Zhiguo Zhang^*

CMC-Computers, Materials & Continua, Vol.86, No.1, pp. 1-20, 2026, DOI:10.32604/cmc.2025.069340 - 10 November 2025

Abstract Accurately counting dense objects in complex and diverse backgrounds is a significant challenge in computer vision, with applications ranging from crowd counting to various other object counting tasks. To address this, we propose HUANNet (High-Resolution Unified Attention Network), a convolutional neural network designed to capture both local features and rich semantic information through a high-resolution representation learning framework, while optimizing computational distribution across parallel branches. HUANNet introduces three core modules: the High-Resolution Attention Module (HRAM), which enhances feature extraction by optimizing multi-resolution feature fusion; the Unified Multi-Scale Attention Module (UMAM), which integrates spatial, channel, and More >

Yanting Zhang¹, Qiyue Liu^1,2, Chuanzhao Tian^1,2,*, Xuewen Li¹, Na Yang¹, Feng Zhang¹, Hongyue Zhang³

CMC-Computers, Materials & Continua, Vol.86, No.1, pp. 1-25, 2026, DOI:10.32604/cmc.2025.068403 - 10 November 2025

Abstract High-resolution remote sensing images (HRSIs) are now an essential data source for gathering surface information due to advancements in remote sensing data capture technologies. However, their significant scale changes and wealth of spatial details pose challenges for semantic segmentation. While convolutional neural networks (CNNs) excel at capturing local features, they are limited in modeling long-range dependencies. Conversely, transformers utilize multihead self-attention to integrate global context effectively, but this approach often incurs a high computational cost. This paper proposes a global-local multiscale context network (GLMCNet) to extract both global and local multiscale contextual information from HRSIs.… More >

R. Rajeev^a,b,*, C. M. S. Negi^a

Chalcogenide Letters, Vol.22, No.5, pp. 469-480, 2025, DOI:10.15251/CL.2025.225.469

Abstract Cobalt-doped cadmium sulphide nanoparticles of semiconductors (CDs: Co NPs) were synthesised using various cobalt concentrations utilising a microwave-assisted approach. Debye-Scherer equation revealed the nanoparticles' size range to be between 2 and 4 nm. Diffraction from X-rays revealed a zinc mix structure. According to the structure in the optical bandgap energies indicates that, doping has systematically raised the bandgap energy as the doping concentration raises. The composition of the nanoparticles which was verified by EDAX, validated the effective integration of cobalt into the CdS structure. The detection of different functional and vibrational groups was performed at More >

Haoyang Tang^1,2, Kai Zeng^1,2,*

CMC-Computers, Materials & Continua, Vol.84, No.1, pp. 1485-1506, 2025, DOI:10.32604/cmc.2025.064441 - 09 June 2025

Abstract Semantic segmentation provides important technical support for Land cover/land use (LCLU) research. By calculating the cosine similarity between feature vectors, transformer-based models can effectively capture the global information of high-resolution remote sensing images. However, the diversity of detailed and edge features within the same class of ground objects in high-resolution remote sensing images leads to a dispersed embedding distribution. The dispersed feature distribution enlarges feature vector angles and reduces cosine similarity, weakening the attention mechanism’s ability to identify the same class of ground objects. To address this challenge, remote sensing image information granulation transformer for… More >

Yue Chen¹, Xiaoman Liang^1,2,*, Mugang Lin^1,2, Fachao Zhang¹, Huihuang Zhao^1,2

CMC-Computers, Materials & Continua, Vol.82, No.2, pp. 2753-2768, 2025, DOI:10.32604/cmc.2024.059530 - 17 February 2025

Abstract The objective of image-based virtual try-on is to seamlessly integrate clothing onto a target image, generating a realistic representation of the character in the specified attire. However, existing virtual try-on methods frequently encounter challenges, including misalignment between the body and clothing, noticeable artifacts, and the loss of intricate garment details. To overcome these challenges, we introduce a two-stage high-resolution virtual try-on framework that integrates an attention mechanism, comprising a garment warping stage and an image generation stage. During the garment warping stage, we incorporate a channel attention mechanism to effectively retain the critical features of… More >

Yahia Said^1,*, Yahya Alassaf², Taoufik Saidani³, Refka Ghodhbani³, Olfa Ben Rhaiem⁴, Ali Ahmad Alalawi¹

CMC-Computers, Materials & Continua, Vol.81, No.3, pp. 4349-4370, 2024, DOI:10.32604/cmc.2024.058903 - 19 December 2024

Abstract The integration of Unmanned Aerial Vehicles (UAVs) into Intelligent Transportation Systems (ITS) holds transformative potential for real-time traffic monitoring, a critical component of emerging smart city infrastructure. UAVs offer unique advantages over stationary traffic cameras, including greater flexibility in monitoring large and dynamic urban areas. However, detecting small, densely packed vehicles in UAV imagery remains a significant challenge due to occlusion, variations in lighting, and the complexity of urban landscapes. Conventional models often struggle with these issues, leading to inaccurate detections and reduced performance in practical applications. To address these challenges, this paper introduces CFEMNet,… More >

Beng-Loon Aw^1,*

The International Conference on Computational & Experimental Engineering and Sciences, Vol.32, No.1, pp. 1-1, 2024, DOI:10.32604/icces.2024.011990

Abstract This study introduces a novel method that combines Binder Jet Printing (BJP) and Selective Laser Melting (SLM) techniques to achieve unprecedented high-speed and high-resolution 3D printing of fine metal powders in Laser Powder Bed Fusion (LPBF). Our approach comfortably attains a resolution of 0.2 mm, enabling the selective deposition of fine powder (D50: 30 µm) made from multiple materials within a single print layer. We demonstrate the capability of this technique through the printing of a composite structure composed of copper alloy and 18Ni300 Maraging tool steel, showcasing its potential for fast-cooling tooling applications. The More >

Xiayun Zhao^1,*, Yue Zhang¹, Heyang Zhang¹, Yousra Bensouda¹, Md Jahangir Alam¹, Haolin Zhang¹, Yiquan Wang¹

The International Conference on Computational & Experimental Engineering and Sciences, Vol.31, No.2, pp. 1-2, 2024, DOI:10.32604/icces.2024.011485

Abstract Vat photopolymerization (VPP) among other additive manufacturing (AM) processes have a great potential to rapidly print complex 3D components out of a matrix of photo-curable resin. Current VPP processes utilize single-wavelength light exposure, imposing limitations on print speed and throughput, especially in multi-material AM. This is attributed to delays in material switch-over mechanisms. Additionally, the resolution of conventional single-wavelength VPP is constrained by over-curing. Despite ongoing efforts and progress in VPP, there remains a need for effective approaches to address these persistent issues. In this work, we report our development of two-wavelength digital light processing-based… More >

Weixin Jiang^1,*, Zongze Li², Qing Yuan^3,*, Junhua Gong², Bo Yu⁴

The International Conference on Computational & Experimental Engineering and Sciences, Vol.30, No.1, pp. 1-3, 2024, DOI:10.32604/icces.2024.011266

Abstract High resolution flow field results are of great significance for exploring physical laws and guiding practical engineering practice. However, traditional activities based on experiments or direct numerical solutions to obtain high-resolution flow fields typically require a significant amount of computational time or resources. In response to this challenge, this study proposes an efficient and robust high-resolution flow field reconstruction method by embedding graph theory into neural networks, to adapt to low data volume situations. In the high resolution flow field reconstruction problem of an NS equation, the proposed model has a lower mean squared error More >

Jing Wang^1,2,*, Chen Zhang¹, Tianwen Lin¹

CMC-Computers, Materials & Continua, Vol.80, No.2, pp. 1907-1925, 2024, DOI:10.32604/cmc.2024.052597 - 15 August 2024

Abstract When existing deep learning models are used for road extraction tasks from high-resolution images, they are easily affected by noise factors such as tree and building occlusion and complex backgrounds, resulting in incomplete road extraction and low accuracy. We propose the introduction of spatial and channel attention modules to the convolutional neural network ConvNeXt. Then, ConvNeXt is used as the backbone network, which cooperates with the perceptual analysis network UPerNet, retains the detection head of the semantic segmentation, and builds a new model ConvNeXt-UPerNet to suppress noise interference. Training on the open-source DeepGlobe and CHN6-CUG… More >