Proceedings of the 3rd International Conference on Vision, Image and Signal Processing最新文献_第9页

Sketch-aae: A Seq2Seq Model to Generate Sketch Drawings Sketch-aae:一个Seq2Seq模型来生成草图

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387178

Jia Lu, Xueming Li, Xianlin Zhang

{"title":"Sketch-aae: A Seq2Seq Model to Generate Sketch Drawings","authors":"Jia Lu, Xueming Li, Xianlin Zhang","doi":"10.1145/3387168.3387178","DOIUrl":"https://doi.org/10.1145/3387168.3387178","url":null,"abstract":"Sketch plays an important role in human nonverbal communication, which is a superior way to describe specific objects visually. Generating human free-hand sketches has become topical in computer graphics and vision, inspired by various applications related to sketches such as sketch object recognition. Existing methods on sketch generation failed to utilize stroke sequence information of human free-hand sketches. Especially, a recent study proposed an end-to-end variational autoencoder (VAE) model called sketch-rnn which learned to sketch with human input. However, the performance of sketch-rnn is affected by the original input seriously hence decreased its robustness. In this paper, we proposed a sequence-to-sequence model called sketch-aae to generate multiple categories of humanlike sketches of higher quality than sketch-rnn. We achieve this by introducing an adversarial autoencoder (AAE) model, which uses generative adversarial networks (GAN) to improve the robustness of VAE. To our best knowledge, for the first time, the AAE model is used to synthesize sketches. A VGGNet classification model is then formulated to prove the similarity between our generated sketches and human free-hand sketches. Extensive experiments both qualitatively and quantitatively demonstrate that the proposed model is superiority over the state-of-the-art for sketch generation and multi-class sketch classification.","PeriodicalId":346739,"journal":{"name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117102483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Robust Infrared Air Object Tracking Fusing Convolutional And Hand-Crafted Features 鲁棒红外空中目标跟踪融合卷积和手工制作的特点

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387239

Kai Zhang, Chenhui Li, Xiaotian Wang, Kai Yang, Xi Yang

{"title":"Robust Infrared Air Object Tracking Fusing Convolutional And Hand-Crafted Features","authors":"Kai Zhang, Chenhui Li, Xiaotian Wang, Kai Yang, Xi Yang","doi":"10.1145/3387168.3387239","DOIUrl":"https://doi.org/10.1145/3387168.3387239","url":null,"abstract":"The infrared objects do not have color information, and they have low resolution. Therefore, the hand-crafted features cannot robustly describe observation model of the object, and it is easy to track failure in the presence of heavy occlusion and infrared distractors. Based on the correlation filtering theory, a robust air object tracking algorithm using convolutional and hand-crafted features is proposed in this paper. Firstly, there are differences in the ability of different layer features to describe the objects. We reconstruct the foreground mask with feature map selection approach, and select the features which are sensitive to intra-class appearance variation. Then, convolutional and hand-crafted features are fused and embedded in the correlation filtering theory to estimate the object position, achieving the air object tracking. Finally, to re-capture the object when the tracking fails, the proposed algorithm introduces YOLOv3 for re-detection. We verify our algorithm with actual infrared image sequence and the simulation image sequence. The experimental results show that the proposed algorithm can accurately track air objects with high precision.","PeriodicalId":346739,"journal":{"name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","volume":"261 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115230831","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Genetically-enhanced Multi-dimensional Constellation Design for Wireless Systems 无线系统的遗传增强多维星座设计

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387193

Zefeng Lin, Song-Wen Huang, M. Jiang

引用次数: 0

A New Cryptojacking Malware Classifier Model Based on Dendritic Cell Algorithm 一种基于树突状细胞算法的加密劫持恶意软件分类器模型

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387218

Azuan Ahmad, Wan Shafiuddin, M. Kama, M. Saudi

{"title":"A New Cryptojacking Malware Classifier Model Based on Dendritic Cell Algorithm","authors":"Azuan Ahmad, Wan Shafiuddin, M. Kama, M. Saudi","doi":"10.1145/3387168.3387218","DOIUrl":"https://doi.org/10.1145/3387168.3387218","url":null,"abstract":"A new threat known as \"cryptojacking\" has entered the picture where cryptojacking malware is the future trend for cyber criminals, who infect victim's device, install cryptojacking malware, and use the stolen resources for crytocurrency mining. Worse comes to worst by 2020, researchers estimate there will be 30 billion of IoT devices in the world. IoT devices are vulnerable to attacks because of their simple configuration, unpatched vulnerability and weak passwords. IoT devices also prone to be poorly monitored because of their nature. There is lack of studies that provide in depth analysis on cryptojacking malware classification using machine learning approach where the current research mostly focused on manual analysis of web-based cryptojacking attacks. As IoT devices requires small processing capability, a lightweight model are required for the cryptojacking malware detection algorithm to maintain its accuracy without sacrificing the performance of other process. As a solution, we propose a new lightweight cryptojacking classifier model based on machine learning technique that may fit in a low processing capability environment such as IoT and Cyber Physical Systems (CPS). This paper aim to disscuss a new approach based on dendritic cell algorithm in order to provide a lightweight cryptojacking classifier model. The output of this paper will be significant used in detecting cryptojacking malware attacks that benefits multiple industries including cyber security contractors, oil and gas, water, power and energy industries.","PeriodicalId":346739,"journal":{"name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121804120","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7

Confidence Intervals for Single Coefficient of Variation of Weibull Distribution 威布尔分布单变异系数的置信区间

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387253

Manussaya La-ongkaew, S. Niwitpong, Suparat Niwitpong

引用次数: 2

Existence of Latin Maps 拉丁地图的存在

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387252

Zhaoqi Zhang

引用次数: 0

The Role of ICT in Poverty Reduction in Onitsha L.G.A of Anambra State 信息通信技术在阿南布拉州奥尼沙州减贫中的作用

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387190

Wilson Obinna Igbasi

引用次数: 0

Cloud Computing Virtual Machine Migration Energy Measuring Research 云计算虚拟机迁移能量测量研究

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387192

Liu Jun, Zhang Jie, Dinghong Pu

引用次数: 1

Solving Dynamic Multi-Objective Optimization Problems Using Cultural Algorithm based on Decomposition 基于分解的文化算法求解动态多目标优化问题

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387205

Ramya Ravichandran, Ziad Kobti

引用次数: 0

Automatic Phonocardiography Analysis Using Discrete Wavelet Transform

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387172

Md Tanzil Hoque Chowdhury, K. Poudel, Yating Hu

{"title":"Automatic Phonocardiography Analysis Using Discrete Wavelet Transform","authors":"Md Tanzil Hoque Chowdhury, K. Poudel, Yating Hu","doi":"10.1145/3387168.3387172","DOIUrl":"https://doi.org/10.1145/3387168.3387172","url":null,"abstract":"This paper presents an intelligent algorithm for analyzing the heart sound signal using multi-resolution analysis based on discrete wavelet transform (DWT). This signal processing technique can not only compress and encrypt the phonocardiogram (PCG) signal but also reduces the noises and the murmurs from the PCG signal. This information can assist the cardiologists for taking appropriate actions to diagnosis for the initial stage of the cardiovascular dis- order. We have presented an efficient data compression algorithm based on DWT, energy packing efficiency (EPE), and run-length encoding (RLE) that can compress the signal about 93.70% without losing any pathological information. Further, this paper explores an end-to-end encryption technique using the compression algo-rithm to maintain patient confidentiality. After the compression of the PCG signal, the noises and the murmurs are effectively separated from the signal by reusing DWT. The performance of this algorithm has been evaluated by using 5 normal and 18 abnormal PCG signals available in the University of Michigan Heart Sound and Murmur Library. This method can be used in real time for the remote monitoring of the heart sound.","PeriodicalId":346739,"journal":{"name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","volume":"373 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131073732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4