Lirong Yin¹, Lei Wang¹, Siyu Lu^2,*, Ruiyang Wang², Youshuai Yang², Bo Yang², Shan Liu², Ahmed AlSanad³, Salman A. AlQahtani³, Zhengtong Yin⁴, Xiaolu Li⁵, Xiaobing Chen⁶, Wenfeng Zheng^3,*

CMES-Computer Modeling in Engineering & Sciences, Vol.141, No.1, pp. 87-106, 2024, DOI:10.32604/cmes.2024.051083 - 20 August 2024

Abstract This study addresses the limitations of Transformer models in image feature extraction, particularly their lack of inductive bias for visual structures. Compared to Convolutional Neural Networks (CNNs), the Transformers are more sensitive to different hyperparameters of optimizers, which leads to a lack of stability and slow convergence. To tackle these challenges, we propose the Convolution-based Efficient Transformer Image Feature Extraction Network (CEFormer) as an enhancement of the Transformer architecture. Our model incorporates E-Attention, depthwise separable convolution, and dilated convolution to introduce crucial inductive biases, such as translation invariance, locality, and scale invariance, into the Transformer… More >

Raheem Ogla^1,*, Eman Shakar Mahmood¹, Rasha I. Ahmed¹, Abdul Monem S. Rahma²

CMC-Computers, Materials & Continua, Vol.76, No.3, pp. 3075-3096, 2023, DOI:10.32604/cmc.2023.039818 - 08 October 2023

Abstract The transmission of video content over a network raises various issues relating to copyright authenticity, ethics, legality, and privacy. The protection of copyrighted video content is a significant issue in the video industry, and it is essential to find effective solutions to prevent tampering and modification of digital video content during its transmission through digital media. However, there are still many unresolved challenges. This paper aims to address those challenges by proposing a new technique for detecting moving objects in digital videos, which can help prove the credibility of video content by detecting any fake… More >

Siyu Lu¹, Yueming Ding¹, Zhengtong Yin², Mingzhe Liu^3,*, Xuan Liu⁴, Wenfeng Zheng^1,*, Lirong Yin⁵

Computer Systems Science and Engineering, Vol.47, No.1, pp. 1149-1161, 2023, DOI:10.32604/csse.2023.038598 - 26 May 2023

Abstract Visual question answering (VQA) has attracted more and more attention in computer vision and natural language processing. Scholars are committed to studying how to better integrate image features and text features to achieve better results in VQA tasks. Analysis of all features may cause information redundancy and heavy computational burden. Attention mechanism is a wise way to solve this problem. However, using single attention mechanism may cause incomplete concern of features. This paper improves the attention mechanism method and proposes a hybrid attention mechanism that combines the spatial attention mechanism method and the channel attention More >

Vidit Kumar^1,*, Hemant Petwal², Ajay Krishan Gairola¹, Pareshwar Prasad Barmola¹

Computer Systems Science and Engineering, Vol.46, No.3, pp. 2711-2724, 2023, DOI:10.32604/csse.2023.032047 - 03 April 2023

Abstract Fine-grained image search is one of the most challenging tasks in computer vision that aims to retrieve similar images at the fine-grained level for a given query image. The key objective is to learn discriminative fine-grained features by training deep models such that similar images are clustered, and dissimilar images are separated in the low embedding space. Previous works primarily focused on defining local structure loss functions like triplet loss, pairwise loss, etc. However, training via these approaches takes a long training time, and they have poor accuracy. Additionally, representations learned through it tend to… More >

Le Duc Thuan^1,2,*, Pham Van Huong², Hoang Van Hiep¹, Nguyen Kim Khanh¹

Computer Systems Science and Engineering, Vol.45, No.3, pp. 2741-2759, 2023, DOI:10.32604/csse.2023.033420 - 21 December 2022

Abstract Android malware has exploded in popularity in recent years, due to the platform’s dominance of the mobile market. With the advancement of deep learning technology, numerous deep learning-based works have been proposed for the classification of Android malware. Deep learning technology is designed to handle a large amount of raw and continuous data, such as image content data. However, it is incompatible with discrete features, i.e., features gathered from multiple sources. Furthermore, if the feature set is already well-extracted and sparsely distributed, this technology is less effective than traditional machine learning. On the other hand,… More >

Muhammad Alyas Khan¹, Mushtaq Ali¹, Mohsin Shah², Toqeer Mahmood³, Muneer Ahmad⁴, NZ Jhanjhi⁵, Mohammad Arif Sobhan Bhuiyan^6,*, Emad Sami Jaha⁷

Intelligent Automation & Soft Computing, Vol.30, No.3, pp. 771-785, 2021, DOI:10.32604/iasc.2021.018039 - 20 August 2021

Abstract Fungi disease affects walnut trees worldwide because it damages the canopies of the trees and can easily spread to neighboring trees, resulting in low quality and less yield. The fungal disease can be treated relatively easily, and the main goal is preventing its spread by automatic early-detection systems. Recently, machine learning techniques have achieved promising results in many applications in the agricultural field, including plant disease detection. In this paper, an automatic machine learning-based detection method for identifying walnut diseases is proposed. The proposed method first resizes a leaf’s input image and pre-processes it using… More >

Lei Feng^1,2, Haibin Li^1,*, Yakun Gao¹, Yakun Zhang¹

Intelligent Automation & Soft Computing, Vol.26, No.4, pp. 831-839, 2020, DOI:10.32604/iasc.2020.010117

Abstract In the paper, we apply the sparse reconstruction algorithm of improved background dictionary to saliency detection. Firstly, after super-pixel segmentation, two bottom features are extracted: the color information of LAB and the texture features of the image by Gabor filter. Secondly, the convex hull theory is used to remove object region in boundary region, and K-means clustering algorithm is used to continue to simplify the background dictionary. Finally, the saliency map is obtained by calculating the reconstruction error. Compared with the mainstream algorithms, the accuracy and efficiency of this algorithm are better than those of More >

Xiangshu Ou¹, Mingfang Jiang^2,*, Shuai Li¹, Yao Bai¹

Journal of Cyber Security, Vol.2, No.3, pp. 123-130, 2020, DOI:10.32604/jcs.2020.09703 - 14 September 2020

Abstract In smart environments, more and more teaching data sources are uploaded to remote cloud centers which promote the development of the smart campus. The outsourcing of massive teaching data can reduce storage burden and computational cost, but causes some privacy concerns because those teaching data (especially personal image data) may contain personal private information. In this paper, a privacy-preserving image feature extraction algorithm is proposed by using mean value features. Clients use block scrambling and chaotic map to encrypt original images before uploading to the remote servers. Cloud servers can directly extract image mean value More >