Filters








150 Hits in 2.9 sec

A Deep Neural Network-Based Approach to Finding Similar Code Segments

Dong Kwan KIM
2020 IEICE transactions on information and systems  
Experimental results demonstrate that CNN-based feature extraction is effective in detecting code clones at source code or bytecode levels. key words: code clone detection, Siamese architecture, convolutional  ...  This paper presents a Siamese architecture model with two identical Convolutional Neural Networks (CNNs) to identify code clones; two code fragments are represented as Abstract Syntax Trees (ASTs), CNN-based  ...  Siamese neural networks can be used to find similar code fragments.  ... 
doi:10.1587/transinf.2019edl8195 fatcat:qr6f2k7dgjh2rc3s4kh77rh544

Deep Just-In-Time Inconsistency Detection Between Comments and Source Code [article]

Sheena Panthaplackel, Junyi Jessy Li, Milos Gligoric, Raymond J. Mooney
2020 arXiv   pre-print
resolve inconsistent comments based on code changes.  ...  In this paper, we aim to detect whether a comment becomes inconsistent as a result of changes to the corresponding body of code, in order to catch potential inconsistencies just-in-time, i.e., before they  ...  Detecting Code Comment Inconsistency Using Siamese Recurrent Network. In International Conference on Program Comprehension -Early Research Achievements, 371-375.  ... 
arXiv:2010.01625v2 fatcat:u6eagow32vcvflbjfga4ayhniq

An Effective Semantic Code Clone Detection Framework using Pairwise Feature Fusion

Abdullah Sheneamer, Swarup Roy, Jugal Kalita
2021 IEEE Access  
[40] presented an approach to detect plagiarism in source-codes using deep learning features and character-level Recurrent Neural Network (char-RNN).  ...  [32] used a so-called Siamese twin neural network architecture, whose inputs are obtained by computing features of code blocks.  ...  His research interests include data mining, machine learning and its application to computational biology, social network analysis, smartphone security, and code clone detection.  ... 
doi:10.1109/access.2021.3079156 fatcat:35kta7bkabgtjmgs2zbwo77t2q

A Comprehensive Review of Deep-Learning-Based Methods for Image Forensics

Ivan Castillo Castillo Camacho, Kai Wang
2021 Journal of Imaging  
For these reasons, it is important to have tools that can help us discern the truth.  ...  of computer graphics images and detection of emerging Deepfake images.  ...  [163] made use of a so-called Common Fake Feature Network (CFFN) consisting of several dense units and a Siamese network for Deepfake detection.  ... 
doi:10.3390/jimaging7040069 pmid:34460519 pmcid:PMC8321383 fatcat:72zd7nyaifhvlgcxv22zztpm4y

Towards Egocentric Person Re-identification and Social Pattern Analysis [article]

Estefania Talavera, Alexandre Cola, Nicolai Petkov, Petia Radeva
2019 arXiv   pre-print
Recurrence of detected faces within photostreams allows us to shape an idea of the social pattern of behaviour of the user.  ...  Our findings indicate that social profiles are potentially useful for social behaviour interpretation.  ...  Later, we use the OpenFace tool [3] , a trained deep neural network that extracts 128-D feature vectors from the detected faces.  ... 
arXiv:1905.04073v1 fatcat:or6bzqexo5ffplgkb5g7f7scpa

Deep Learning for Enterprise Systems Implementation Lifecycle Challenges: Research Directions

Hossam El-Din Hassanien, Ahmed Elragal
2021 Informatics  
Lastly, recurrent neural networks (RNNs) and long short-term memory networks (LSTMs) did also see many applications empowering text mining and NLP-based use cases.  ...  - cles) 16% 4% 39% 65% 14% 4% 12% 82% 35% 7% Table 6 . 6 A record count of the free-text comments being used to train the Siamese LSTM architecture.  ... 
doi:10.3390/informatics8010011 fatcat:4ck54axcgnhnvjnwsnlgfh25my

2021 Index IEEE Transactions on Image Processing Vol. 30

2021 IEEE Transactions on Image Processing  
-that appeared in this periodical during 2021, and items from previous years that were commented upon or corrected in 2021.  ...  Zhao, Z., +, TIP 2021 6544-6556 Learning Deep Lucas-Kanade Siamese Network for Visual Tracking. Progressive Self-Guided Loss for Salient Object Detection.  ...  ., +, TIP 2021 6142-6155 Structure-Texture Image Decomposition Using Discriminative Patch Recurrence.  ... 
doi:10.1109/tip.2022.3142569 fatcat:z26yhwuecbgrnb2czhwjlf73qu

Peak Alignment of Gas Chromatography-Mass Spectrometry Data with Deep Learning [article]

Mike Li, X. Rosalind Wang
2019 arXiv   pre-print
We present a solution to GC-MS alignment using deep learning neural networks, which are more adept at complex, fuzzy data sets.  ...  The source code is written in Python and available online.  ...  Acknowledgement We would like to thank the CSIRO Scientific Computing team for the use of their supercomputer clusters in performing the experiments for this paper.  ... 
arXiv:1904.01205v3 fatcat:tbdzmbdcofajvlcp5ycci6pbia

A Survey on Deep Learning for Software Engineering [article]

Yanming Yang, Xin Xia, David Lo, John Grundy
2020 arXiv   pre-print
In 2006, Geoffrey Hinton proposed the concept of training "Deep Neural Networks (DNNs)" and an improved model training method to break the bottleneck of neural network development.  ...  We analyzed key optimization technologies used in these deep learning models, and finally describe a range of key research topics using DNNs in SE.  ...  [71] proposed an automated approach for detecting and refactoring inconsistent method names by using Paragraph Vector and a CNN. Ni et al.  ... 
arXiv:2011.14597v1 fatcat:pcyg6zbnm5bc3g4yhjomcnye3y

Automatic Assessment Of Singing Voice Pronunciation: A Case Study With Jingju Music

Rong Gong, Xavier Serra
2018 Zenodo  
Chinese tonal languages and the strict conventions in oral transmission adopted by jingju singing training pose unique challenges that have not been addressed by the current MIR research, which motivates us  ...  ., 2017) Using Siamese network word embeddings for Query-by-Example search task. (Zeghidour et al., 2016) Using Siamese network to jointly learn phoneme and speaker embeddings.  ...  Recurrent neural networks Recurrent neural networks (RNNs) is another type of deep learning architecture which is commonly used to model the symbolic or acoustic sequential data such as text, speech, and  ... 
doi:10.5281/zenodo.1490343 fatcat:f3mrhstkdff6ppmdadeasfuo7m

Combination of Recursive and Recurrent Neural Networks for Aspect-Based Sentiment Analysis Using Inter-Aspect Relations

Cem Rifki Aydin, Tunga Gungor
2020 IEEE Access  
Sentiment analysis studies in the literature mostly use either recurrent or recursive neural network models.  ...  INDEX TERMS Aspect-based sentiment classification, ensemble neural network model, recurrent neural networks, recursive neural networks, sentiment analysis.  ...  They also employ a Siamese bi-directional model to detect topic-level sentiments. The system proposed ranked first in SemEval-2017, Task 4 ''Sentiment Analysis in Twitter.'' C.  ... 
doi:10.1109/access.2020.2990306 fatcat:4biow2zv4rcqvmpmrqa2rzi67a

Going Deeper into Action Recognition: A Survey [article]

Samitha Herath, Mehrtash Harandi, Fatih Porikli
2017 arXiv   pre-print
This motivated us to provide a comprehensive review of the notable steps taken towards recognizing human actions.  ...  To this end, we start our discussion with the pioneering methods that use handcrafted representations, and then, navigate into the realm of deep learning based approaches.  ...  Basura Fernando for fruitful discussions and encouragement comments given for this work.  ... 
arXiv:1605.04988v2 fatcat:7727tjctgfffzlnig5rvicxjgq

Deep Learning for Android Malware Defenses: a Systematic Literature Review [article]

Yue Liu, Chakkrit Tantithamthavorn, Li Li, Yepang Liu
2022 arXiv   pre-print
Our investigation reveals that, while the majority of these sources mainly consider DL-based on Android malware detection, 53 primary studies (40.1 percent) design defense approaches based on other scenarios  ...  [31] employ recurrent neural networks to visualize potential risks for Android malware samples.  ...  [17] perform Android malware family classification through siamese neural networks. Ma et al. [105] adopt deep residual learning to detect sensitive behaviors.  ... 
arXiv:2103.05292v2 fatcat:qruddq4gknfq7jx5wyrk5qu2eu

Contrastive Code Representation Learning [article]

Paras Jain, Ajay Jain, Tianjun Zhang, Pieter Abbeel, Joseph E. Gonzalez, Ion Stoica
2021 arXiv   pre-print
We also propose a new zero-shot JavaScript code clone detection dataset, showing that ContraCode is both more robust and semantically meaningful.  ...  We scalably generate these variants using an automated source-to-source compiler as a form of data augmentation.  ...  Dead-code insertion (DCI): Commonly used no-ops such as comments and logging are inserted.  ... 
arXiv:2007.04973v3 fatcat:bpqzjwtoebhh3in5q7qkk4sggq

Clone-Seeker: Effective Code Clone Search Using Annotations

Muhammad Hammad, Onder Babur, Hamid Abdul Basit, Mark Van Den Brand
2022 IEEE Access  
Source code search plays an important role in software development, e.g. for exploratory development or opportunistic reuse of existing code from a code base.  ...  Searching for code clones involves a given search query to retrieve the relevant code fragments.  ...  We do not use comments as they have been reported to be non-reliable and inconsistent source for extracting natural language document [54] , [55] .  ... 
doi:10.1109/access.2022.3145686 fatcat:use6c3t2xjbyvgenvs2b3z66eu
« Previous Showing results 1 — 15 out of 150 results