Hui Luo, Wenqing Li^*, Wei Zeng

CMC-Computers, Materials & Continua, Vol.84, No.1, pp. 1567-1580, 2025, DOI:10.32604/cmc.2025.062949 - 09 June 2025

Abstract Rail surface damage is a critical component of high-speed railway infrastructure, directly affecting train operational stability and safety. Existing methods face limitations in accuracy and speed for small-sample, multi-category, and multi-scale target segmentation tasks. To address these challenges, this paper proposes Pyramid-MixNet, an intelligent segmentation model for high-speed rail surface damage, leveraging dataset construction and expansion alongside a feature pyramid-based encoder-decoder network with multi-attention mechanisms. The encoding network integrates Spatial Reduction Masked Multi-Head Attention (SRMMHA) to enhance global feature extraction while reducing trainable parameters. The decoding network incorporates Mix-Attention (MA), enabling multi-scale structural understanding and 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 >

Jianuo Huang^1,2, Bohan Lai², Weiye Qiu³, Caixu Xu⁴, Jie He^1,5,*

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 4841-4862, 2025, DOI:10.32604/cmc.2025.059733 - 06 March 2025

Abstract The self-attention mechanism of Transformers, which captures long-range contextual information, has demonstrated significant potential in image segmentation. However, their ability to learn local, contextual relationships between pixels requires further improvement. Previous methods face challenges in efficiently managing multi-scale features of different granularities from the encoder backbone, leaving room for improvement in their global representation and feature extraction capabilities. To address these challenges, we propose a novel Decoder with Multi-Head Feature Receptors (DMHFR), which receives multi-scale features from the encoder backbone and organizes them into three feature groups with different granularities: coarse, fine-grained, and full set.… More >

Wenju Wang¹, Zehua Gu^1,*, Bang Tang¹, Sen Wang², Jianfei Hao²

CMC-Computers, Materials & Continua, Vol.82, No.2, pp. 2389-2414, 2025, DOI:10.32604/cmc.2024.057392 - 17 February 2025

Abstract Current spatio-temporal action detection methods lack sufficient capabilities in extracting and comprehending spatio-temporal information. This paper introduces an end-to-end Adaptive Cross-Scale Fusion Encoder-Decoder (ACSF-ED) network to predict the action and locate the object efficiently. In the Adaptive Cross-Scale Fusion Spatio-Temporal Encoder (ACSF ST-Encoder), the Asymptotic Cross-scale Feature-fusion Module (ACCFM) is designed to address the issue of information degradation caused by the propagation of high-level semantic information, thereby extracting high-quality multi-scale features to provide superior features for subsequent spatio-temporal information modeling. Within the Shared-Head Decoder structure, a shared classification and regression detection head is constructed. A More >

Rihem Farkh^1,*, Ghislain Oudinet¹, Yasser Foued²

CMC-Computers, Materials & Continua, Vol.81, No.3, pp. 3951-3968, 2024, DOI:10.32604/cmc.2024.053245 - 19 December 2024

Abstract The process of generating descriptive captions for images has witnessed significant advancements in last years, owing to the progress in deep learning techniques. Despite significant advancements, the task of thoroughly grasping image content and producing coherent, contextually relevant captions continues to pose a substantial challenge. In this paper, we introduce a novel multimodal method for image captioning by integrating three powerful deep learning architectures: YOLOv8 (You Only Look Once) for robust object detection, EfficientNetB7 for efficient feature extraction, and Transformers for effective sequence modeling. Our proposed model combines the strengths of YOLOv8 in detecting objects,… More >

Ou Ye, Xinli Wei, Zhenhua Yu^*, Yan Fu, Ying Yang

CMC-Computers, Materials & Continua, Vol.78, No.1, pp. 1071-1093, 2024, DOI:10.32604/cmc.2023.046418 - 30 January 2024

Abstract In the video captioning methods based on an encoder-decoder, limited visual features are extracted by an encoder, and a natural sentence of the video content is generated using a decoder. However, this kind of method is dependent on a single video input source and few visual labels, and there is a problem with semantic alignment between video contents and generated natural sentences, which are not suitable for accurately comprehending and describing the video contents. To address this issue, this paper proposes a video captioning method by semantic topic-guided generation. First, a 3D convolutional neural network… More >

Ngoc-Khuong Nguyen^1,2, Dac-Nhuong Le¹, Viet-Ha Nguyen², Anh-Cuong Le^3,*

Intelligent Automation & Soft Computing, Vol.38, No.1, pp. 1-18, 2023, DOI:10.32604/iasc.2023.037083 - 26 January 2024

Abstract Text summarization aims to generate a concise version of the original text. The longer the summary text is, the more detailed it will be from the original text, and this depends on the intended use. Therefore, the problem of generating summary texts with desired lengths is a vital task to put the research into practice. To solve this problem, in this paper, we propose a new method to integrate the desired length of the summarized text into the encoder-decoder model for the abstractive text summarization problem. This length parameter is integrated into the encoding phase More >

Abdul Qadir Khan¹, Guangmin Sun^1,*, Yu Li¹, Anas Bilal², Malik Abdul Manan¹

CMC-Computers, Materials & Continua, Vol.77, No.2, pp. 2481-2504, 2023, DOI:10.32604/cmc.2023.043239 - 29 November 2023

Abstract In the emerging field of image segmentation, Fully Convolutional Networks (FCNs) have recently become prominent. However, their effectiveness is intimately linked with the correct selection and fine-tuning of hyperparameters, which can often be a cumbersome manual task. The main aim of this study is to propose a more efficient, less labour-intensive approach to hyperparameter optimization in FCNs for segmenting fundus images. To this end, our research introduces a hyperparameter-optimized Fully Convolutional Encoder-Decoder Network (FCEDN). The optimization is handled by a novel Genetic Grey Wolf Optimization (G-GWO) algorithm. This algorithm employs the Genetic Algorithm (GA) to… More >

Dehai Zhang^*, Yu Ma, Qing Liu, Haoxing Wang, Anquan Ren, Jiashu Liang

CMC-Computers, Materials & Continua, Vol.76, No.3, pp. 2901-2920, 2023, DOI:10.32604/cmc.2023.038264 - 08 October 2023

Abstract Traffic scene captioning technology automatically generates one or more sentences to describe the content of traffic scenes by analyzing the content of the input traffic scene images, ensuring road safety while providing an important decision-making function for sustainable transportation. In order to provide a comprehensive and reasonable description of complex traffic scenes, a traffic scene semantic captioning model with multi-stage feature enhancement is proposed in this paper. In general, the model follows an encoder-decoder structure. First, multi-level granularity visual features are used for feature enhancement during the encoding process, which enables the model to learn… More >

Ou Ye^1,2, Mimi Wang¹, Zhenhua Yu^1,*, Yan Fu¹, Shun Yi¹, Jun Deng²

CMC-Computers, Materials & Continua, Vol.75, No.3, pp. 5675-5696, 2023, DOI:10.32604/cmc.2023.037503 - 29 April 2023

Abstract Currently, the video captioning models based on an encoder-decoder mainly rely on a single video input source. The contents of video captioning are limited since few studies employed external corpus information to guide the generation of video captioning, which is not conducive to the accurate description and understanding of video content. To address this issue, a novel video captioning method guided by a sentence retrieval generation network (ED-SRG) is proposed in this paper. First, a ResNeXt network model, an efficient convolutional network for online video understanding (ECO) model, and a long short-term memory (LSTM) network… More >