Skip to Content
You are currently on the new version of our website. Access the old version .

370 Results Found

  • Article
  • Open Access
4 Citations
6,182 Views
19 Pages

Learning Sentence-Level Representations with Predictive Coding

  • Vladimir Araujo,
  • Marie-Francine Moens and
  • Alvaro Soto

Learning sentence representations is an essential and challenging topic in the deep learning and natural language processing communities. Recent methods pre-train big models on a massive text corpus, focusing mainly on learning the representation of...

  • Article
  • Open Access
1 Citations
3,314 Views
21 Pages

Discrete Infomax Codes for Supervised Representation Learning

  • Yoonho Lee,
  • Wonjae Kim,
  • Wonpyo Park and
  • Seungjin Choi

2 April 2022

For high-dimensional data such as images, learning an encoder that can output a compact yet informative representation is a key task on its own, in addition to facilitating subsequent processing of data. We present a model that produces discrete info...

(This article belongs to the Special Issue Theory and Applications of Information Processing Algorithms)
  • Article
  • Open Access
86 Citations
11,098 Views
16 Pages

2 March 2020

Vulnerability is one of the root causes of network intrusion. An effective way to mitigate security threats is to discover and patch vulnerabilities before an attack. Traditional vulnerability detection methods rely on manual participation and incur...

(This article belongs to the Special Issue Machine Learning for Cybersecurity Threats, Challenges, and Opportunities)
  • Article
  • Open Access
6 Citations
6,525 Views
13 Pages

Hyperbolic Function Embedding: Learning Hierarchical Representation for Functions of Source Code in Hyperbolic Space

  • Mingming Lu,
  • Yan Liu,
  • Haifeng Li,
  • Dingwu Tan and ,
  • Xiaoxian He,
  • Wenjie Bi and
  • Wendbo Li
  • + 2 authors+ 0 author

18 February 2019

Recently, source code mining has received increasing attention due to the rapid increase of open-sourced code repositories and the tremendous values implied in this large dataset, which can help us understand the organization of functions or classes...

  • Article
  • Open Access
1 Citations
750 Views
17 Pages

21 January 2026

High-quality code representations are fundamental to code intelligence. Achieving such representations with parameter-efficient fine-tuning (PEFT) remains a key challenge. While code pre-trained models (CodePTMs) offer a robust foundation for general...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
2 Citations
2,937 Views
17 Pages

Statement-Grained Hierarchy Enhanced Code Summarization

  • Qianjin Zhang,
  • Dahai Jin,
  • Yawen Wang and
  • Yunzhan Gong

15 February 2024

Code summarization plays a vital role in aiding developers with program comprehension by generating corresponding textual descriptions for code snippets. While recent approaches have concentrated on encoding the textual and structural characteristics...

(This article belongs to the Special Issue Advances in Software Engineering and Programming Languages)
  • Article
  • Open Access
2 Citations
2,911 Views
20 Pages

Summarizing source code by natural language aims to help developers better understand existing code, making software development more efficient. Since source code is highly structured, recent research uses code structure information like Abstract Sem...

(This article belongs to the Special Issue Data Mining Applied in Natural Language Processing)
  • Article
  • Open Access
239 Views
30 Pages

12 October 2026

As a powerful tool for sparse signal representation, dictionary learning has gained traction in data-driven fault diagnosis. However, noise interference exists in actual industrial environments; noise as a common feature across all classes inevitably...

(This article belongs to the Special Issue AI-Driven Intelligent Perception and Diagnosis of Mechanical Equipment)
  • Article
  • Open Access
4 Citations
4,499 Views
18 Pages

A Good View for Graph Contrastive Learning

  • Xueyuan Chen and
  • Shangzhe Li

27 February 2024

Due to the success observed in deep neural networks with contrastive learning, there has been a notable surge in research interest in graph contrastive learning, primarily attributed to its superior performance in graphs with limited labeled data. Wi...

(This article belongs to the Special Issue Entropy in Machine Learning Applications)
  • Article
  • Open Access
12 Citations
4,029 Views
27 Pages

Software vulnerability detection aims to proactively reduce the risk to software security and reliability. Despite advancements in deep-learning-based detection, a semantic gap still remains between learned features and human-understandable vulnerabi...

(This article belongs to the Special Issue Advances in Explainable Artificial Intelligence (XAI): 2nd Edition)
  • Article
  • Open Access
1 Citations
1,373 Views
16 Pages

24 May 2024

To enhance the security of vehicular software systems, inversely identifying the underlying function types of binary files plays a key role in threat discovery. However, existing function-type inference (FTI) methods can only provide a suboptimal per...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
48 Views
39 Pages

12 November 2026

In programming education, learning problems such as code tracing require intelligent tutoring systems (ITSs) to verify multi-step solutions and provide precise feedback. To do this, ITSs need formal representations that capture program entities, thei...

(This article belongs to the Section Information Processes)
  • Article
  • Open Access
1 Citations
877 Views
29 Pages

LRCFuse: Infrared and Visible Image Fusion Based on Low-Rank Representation and Convolutional Sparse Learning

  • Jingjing Liu,
  • Yujie Zhu,
  • Yuhao Zhang,
  • Aiying Guo and ,
  • Mengjiao Li and
  • Jianhua Zhang
  • + 1 author+ 0 author

11 March 2026

With the development of cross-modal image fusion in multi-sensor systems, current fusion technologies have made significant progress in feature extraction, facilitating more effective image analysis. However, insufficient fusion information may degra...

(This article belongs to the Special Issue Machine Learning in Image/Video Processing and Sensing)
  • Article
  • Open Access
9 Citations
3,508 Views
20 Pages

The explosive growth of vulnerabilities poses a significant threat to the security of software systems. While various deep-learning-based vulnerability detection methods have emerged, they primarily rely on semantic features extracted from a single c...

(This article belongs to the Special Issue Software Analysis, Quality, and Security)
  • Article
  • Open Access
8 Citations
2,738 Views
25 Pages

The aim of this work is to introduce a computer science solution to manage emotions and affections and connect them to the causes as in humans. The scientific foundation of this work lies in the ability to model the affective and emotional states of...

(This article belongs to the Special Issue New Challenges of Decision Support Systems)
  • Article
  • Open Access
13 Citations
4,887 Views
18 Pages

14 September 2021

Most Human–Computer Interfaces are built on the paradigm of manipulating abstract representations. This can be limiting when computers are used in artistic performance or as mediators of social connection, where we rely on qualities of embodied think...

(This article belongs to the Special Issue Advances in Computer Music)
  • Article
  • Open Access
545 Views
18 Pages

19 September 2026

Background/Objectives: An important challenge in long non-coding RNA (lncRNA)–disease association prediction is prioritizing candidates when neither target node has association records in the training data, even though content features are avai...

(This article belongs to the Special Issue Bioinformatics Analysis of RNA for Human Health and Disease—2nd Edition)
  • Article
  • Open Access
39 Citations
8,279 Views
26 Pages

Deep Learning-Based Software Defect Prediction via Semantic Key Features of Source Code—Systematic Survey

  • Ahmed Abdu,
  • Zhengjun Zhai,
  • Redhwan Algabri,
  • Hakim A. Abdo and ,
  • Kotiba Hamad and
  • Mugahed A. Al-antari
  • + 1 author+ 0 author

31 August 2022

Software defect prediction (SDP) methodology could enhance software’s reliability through predicting any suspicious defects in its source code. However, developing defect prediction models is a difficult task, as has been demonstrated recently....

(This article belongs to the Special Issue Computational Intelligence in Computer Vision and Software Engineering)
  • Article
  • Open Access
3 Citations
3,755 Views
29 Pages

Classification of Obfuscation Techniques in LLVM IR: Machine Learning on Vector Representations

  • Sebastian Raubitzek,
  • Patrick Felbauer,
  • Kevin Mallinger and
  • Sebastian Schrittwieser

We present a novel methodology for classifying code obfuscation techniques in LLVM IR program embeddings. We apply isolated and layered code obfuscations to C source code using the Tigress obfuscator, compile them to LLVM IR, and convert each IR code...

  • Review
  • Open Access
690 Views
29 Pages

Graph Neural Networks for Software Vulnerability Mining: A Review

  • Yuan He,
  • Haikun Lv,
  • Xing Li,
  • Lulu Zeng and ,
  • Lina Zhang,
  • Dengqi Yang and
  • Xiaowei Li
  • + 2 authors+ 0 author

28 July 2026

Software vulnerability mining is important for improving software reliability and security. Compared with sequence-based models, graph neural networks (GNNs) can explicitly model program structures such as syntax, control flow, data flow, call relati...

(This article belongs to the Special Issue Recent Advances in Graph Neural Networks and Their Applications)
  • Article
  • Open Access
1 Citations
802 Views
19 Pages

8 April 2026

Code smells are indicators of potential design problems in software systems and are commonly used to guide refactoring activities. Recent advances in representation learning have enabled the use of embedding-based models for analyzing source code, of...

  • Article
  • Open Access
79 Citations
9,493 Views
24 Pages

High-Resolution Remote Sensing Image Retrieval Based on CNNs from a Dimensional Perspective

  • Zhifeng Xiao,
  • Yang Long,
  • Deren Li,
  • Chunshan Wei and ,
  • Gefu Tang and
  • Junyi Liu
  • + 1 author+ 0 author

14 July 2017

Because of recent advances in Convolutional Neural Networks (CNNs), traditional CNNs have been employed to extract thousands of codes as feature representations for image retrieval. In this paper, we propose that more powerful features for high-resol...

  • Article
  • Open Access
3,416 Views
23 Pages

29 May 2025

Recent advances in prompt learning have opened new avenues for enhancing natural language understanding in domain-specific tasks, including code vulnerability detection. Motivated by the limitations of conventional binary classification methods in ca...

  • Article
  • Open Access
5 Citations
2,566 Views
15 Pages

Code review as an effective software quality assurance practice has been widely applied in many open-source software communities. However, finding a suitable reviewer for certain codes can be very challenging in open-source communities due to the dif...

(This article belongs to the Special Issue Recommender Systems and Data Mining)
  • Article
  • Open Access
12 Citations
4,570 Views
13 Pages

16 September 2019

The formation of structure in the visual system, that is, of the connections between cells within neural populations, is by and large an unsupervised learning process. In the primary visual cortex of mammals, for example, one can observe during devel...

  • Article
  • Open Access
10 Citations
4,620 Views
22 Pages

TCCCD: Triplet-Based Cross-Language Code Clone Detection

  • Yong Fang,
  • Fangzheng Zhou,
  • Yijia Xu and
  • Zhonglin Liu

6 November 2023

Code cloning is a common practice in software development, where developers reuse existing code to accelerate programming speed and enhance work efficiency. Existing clone-detection methods mainly focus on code clones within a single programming lang...

(This article belongs to the Topic Software Engineering and Applications)
  • Article
  • Open Access
804 Views
19 Pages

Leveraging Code Language Models for Code Smells Detection

  • Soumia Zellagui,
  • Abderrezak Kenniche,
  • Samiha Fadloun and
  • Souham Meshoul

13 July 2026

Improving software quality remains a major challenge in modern software engineering. Among the different techniques used to address this issue, code smell detection plays an important role, as code smells may negatively affect software maintainabilit...

  • Article
  • Open Access
2 Citations
3,050 Views
22 Pages

A Novel Source Code Representation Approach Based on Multi-Head Attention

  • Lei Xiao,
  • Hao Zhong,
  • Jianjian Liu,
  • Kaiyu Zhang and ,
  • Qizhen Xu and
  • Le Chang
  • + 1 author+ 0 author

Code classification and code clone detection are crucial for understanding and maintaining large software systems. Although deep learning surpasses traditional techniques in capturing the features of source code, existing models suffer from low proce...

(This article belongs to the Special Issue Advanced Machine Learning, Pattern Recognition, and Deep Learning Technologies: Methodologies and Applications)
  • Article
  • Open Access
2 Citations
2,684 Views
14 Pages

Transfer Learning Improving Predictive Mortality Models for Patients in End-Stage Renal Disease

  • Edwar Macias,
  • Jose Lopez Vicario,
  • Javier Serrano,
  • Jose Ibeas and
  • Antoni Morell

Deep learning is becoming a fundamental piece in the paradigm shift from evidence-based to data-based medicine. However, its learning capacity is rarely exploited when working with small data sets. Through transfer learning (TL), information from a s...

(This article belongs to the Special Issue Feature Papers in Computer Science & Engineering)
  • Article
  • Open Access
50 Citations
7,227 Views
17 Pages

Hierarchical Coding Vectors for Scene Level Land-Use Classification

  • Hang Wu,
  • Baozhen Liu,
  • Weihua Su,
  • Wenchang Zhang and
  • Jinggong Sun

23 May 2016

Land-use classification from remote sensing images has become an important but challenging task. This paper proposes Hierarchical Coding Vectors (HCV), a novel representation based on hierarchically coding structures, for scene level land-use classif...

  • Article
  • Open Access
6 Citations
5,876 Views
18 Pages

Diffusion-Based Causal Representation Learning

  • Amir Mohammad Karimi Mamaghan,
  • Andrea Dittadi,
  • Stefan Bauer,
  • Karl Henrik Johansson and
  • Francesco Quinzan

28 June 2024

Causal reasoning can be considered a cornerstone of intelligent systems. Having access to an underlying causal graph comes with the promise of cause–effect estimation and the identification of efficient and safe interventions. However, learning...

(This article belongs to the Special Issue Deep Generative Modeling: Theory and Applications)
  • Article
  • Open Access
10 Citations
4,433 Views
18 Pages

Source code clone detection, which can identify code fragments with similar functions, plays a significant role in software development and quality assurance. Existing methods either extract single syntactic or semantic information, or ignore the ass...

(This article belongs to the Special Issue Machine Learning Methods in Software Engineering)
  • Article
  • Open Access
1 Citations
2,522 Views
20 Pages

Locality Preserving and Label-Aware Constraint-Based Hybrid Dictionary Learning for Image Classification

  • Jianqiang Song,
  • Lin Wang,
  • Zuozhi Liu,
  • Muhua Liu and ,
  • Mingchuan Zhang and
  • Qingtao Wu
  • + 1 author+ 0 author

21 August 2021

Dictionary learning has been an important role in the success of data representation. As a complete view of data representation, hybrid dictionary learning (HDL) is still in its infant stage. In previous HDL approaches, the scheme of how to learn an...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
520 Views
19 Pages

Systematic Benchmarking of DNA Sequence Encoding Strategies for Predicting Regulatory Effects of Non-Coding SNPs

  • Hui Jin,
  • Yihang Bao,
  • Wenhao Li,
  • Chengyi Yang and ,
  • Weidi Wang,
  • Wenxiang Cai,
  • Zhe Liu and
  • Guan Ning Lin
  • + 3 authors+ 0 author

Non-coding single nucleotide polymorphisms (SNPs) are key modulators of gene regulation and have been implicated in diverse complex traits and diseases. With the growing demand for accurate functional interpretation of non-coding variants, the choice...

(This article belongs to the Special Issue Mathematical Calculation and Modeling in Biology)
  • Article
  • Open Access
5 Citations
2,895 Views
18 Pages

12 October 2022

Nowadays, the facial expression recognition (FER) task has transitioned from a laboratory-controlled scenario to in-the-wild conditions. However, recognizing facial expressions in the wild is challenging due to factors such as variant backgrounds, lo...

  • Article
  • Open Access
7,199 Views
13 Pages

15 February 2024

Self-supervised learning (SSL) has emerged as a promising paradigm for learning flexible speech representations from unlabeled data. By designing pretext tasks that exploit statistical regularities, SSL models can capture useful representations that...

(This article belongs to the Topic Advances in Artificial Neural Networks)
  • Article
  • Open Access
13 Citations
8,991 Views
14 Pages

5 November 2021

Code generation, as a very hot application area of deep learning models for text, consists of two different fields: code-to-code and text-to-code. A recent approach, GraphCodeBERT uses code graph, which is called data flow, and showed good performanc...

(This article belongs to the Special Issue Advances in Data Mining and Knowledge Discovery)
  • Article
  • Open Access
2 Citations
725 Views
25 Pages

Adaptive Bit Selection via Deep Reinforcement Learning for Large-Scale Image Hashing

  • Mitra Rezaei,
  • Mohammed Ayoub Alaoui Mhamdi and
  • Madjid Allili

Image hashing enables efficient large-scale image retrieval by encoding high-dimensional visual data into compact binary representations. However, existing deep hashing methods typically learn fixed-length hash codes in a fully supervised manner, oft...

(This article belongs to the Special Issue Advanced Machine Learning Technologies and Their Applications in Intelligent Imaging and Image Processing)
  • Article
  • Open Access
18 Citations
6,434 Views
20 Pages

17 November 2021

Exploitable vulnerabilities in software systems are major security concerns. To date, machine learning (ML) based solutions have been proposed to automate and accelerate the detection of vulnerabilities. Most ML techniques aim to isolate a unit of so...

(This article belongs to the Special Issue Interpretability, Accountability and Robustness in Machine Learning)
  • Article
  • Open Access
3 Citations
3,244 Views
13 Pages

DFSGraph: Data Flow Semantic Model for Intermediate Representation Programs Based on Graph Network

  • Ke Tang,
  • Zheng Shan,
  • Chunyan Zhang,
  • Lianqiu Xu and ,
  • Meng Qiao and
  • Fudong Liu
  • + 1 author+ 0 author

8 October 2022

With the improvement of software copyright protection awareness, code obfuscation technology plays a crucial role in protecting key code segments. As the obfuscation technology becomes more and more complex and diverse, it has spawned a large number...

(This article belongs to the Special Issue AI in Cybersecurity)
  • Article
  • Open Access
17 Citations
4,822 Views
20 Pages

Hyperspectral Image Classification via Deep Structure Dictionary Learning

  • Wenzheng Wang,
  • Yuqi Han,
  • Chenwei Deng and
  • Zhen Li

8 May 2022

The construction of diverse dictionaries for sparse representation of hyperspectral image (HSI) classification has been a hot topic over the past few years. However, compared with convolutional neural network (CNN) models, dictionary-based models can...

(This article belongs to the Special Issue Signal Processing Theory and Methods in Remote Sensing)
  • Article
  • Open Access
577 Views
18 Pages

DCANet: Diffusion-Coded Attention Network for Cross-Domain Semantic Noise Mitigation and Multi-Scale Context Fusion

  • Xiao Han,
  • Chunhua Wang,
  • Weijian Fan,
  • Zishuo Niu and ,
  • Jing Gui and
  • Shijia Yu
  • + 1 author+ 0 author

Neural language models have achieved remarkable progress in semantic representation learning. However, cross-domain representation learning still suffers from prominent semantic noise propagation issues. Existing methods still face challenges in cros...

(This article belongs to the Section Artificial Intelligence)
  • Article
  • Open Access
21 Citations
8,313 Views
18 Pages

11 November 2016

The multi-focus image fusion method is used in image processing to generate all-focus images that have large depth of field (DOF) based on original multi-focus images. Different approaches have been used in the spatial and transform domain to fuse mu...

(This article belongs to the Special Issue Future Intelligent Systems and Networks)
  • Article
  • Open Access
3 Citations
3,967 Views
25 Pages

Spatio-Temporal Scale Coded Bag-of-Words

  • Divina Govender and
  • Jules-Raymond Tapamo

9 November 2020

The Bag-of-Words (BoW) framework has been widely used in action recognition tasks due to its compact and efficient feature representation. Various modifications have been made to this framework to increase its classification power. This often results...

(This article belongs to the Special Issue Data Processing of Intelligent Sensors)
  • Article
  • Open Access
1 Citations
1,218 Views
21 Pages

Adaptive Feature Representation Learning for Privacy-Fairness Joint Optimization

  • Chao Ma,
  • Mingkai Dai,
  • Zhibo Guan,
  • Zi Ye and ,
  • Yikai Hou,
  • Xiaoyu Wang and
  • Hai Huang
  • + 2 authors+ 0 author

10 December 2025

Coded text representations often contain a large amount of personal sensitive information, which can easily lead to problems such as privacy leakage and model prediction bias. Most of the existing methods focus on optimizing a single objective, makin...

(This article belongs to the Special Issue Advances in Cyber Security)
  • Article
  • Open Access
4 Citations
2,272 Views
14 Pages

26 March 2025

Automated program repair (APR) plays a vital role in enhancing software quality and reducing developer maintenance efforts. Neural Machine Translation (NMT)-based methods demonstrate notable potential by learning translation patterns from bug-fix cod...

  • Article
  • Open Access
7 Citations
4,019 Views
13 Pages

6 July 2023

Contrastive learning, as an unsupervised technique, has emerged as a prominent method in time series representation learning tasks, serving as a viable solution to the scarcity of annotated data. However, the application of data augmentation methods...

(This article belongs to the Special Issue Deep Learning for Electroencephalography(EEG) Data Analysis)
  • Article
  • Open Access
3 Citations
21 Views

RGB-D (Red, Green and Blue-Depth) cameras are novel sensing systems that can improve image recognition by providing high quality color and depth information in computer vision. In this paper we propose a model to study feature representation of combi...

  • Article
  • Open Access
5 Citations
1,906 Views
25 Pages

New Gait Representation Maps for Enhanced Recognition in Clinical Gait Analysis

  • Nagwan Abdel Samee,
  • Mohammed A. Al-masni,
  • Eman N. Marzban,
  • Abobakr Khalil Al-Shamiri and ,
  • Mugahed A. Al-antari,
  • Maali Ibrahim Alabdulhafith,
  • Noha F. Mahmoud and
  • Yasser M. Kadah
  • + 3 authors+ 0 author

Gait analysis is essential in the evaluation of neuromuscular and musculoskeletal disorders; however, traditional approaches based on expert visual observation remain subjective and often lack consistency. Accurate and objective assessment of gait im...

(This article belongs to the Special Issue AI Advancements in Healthcare: Medical Imaging and Sensing Technologies, 2nd Edition)

of 8