Vision Pub Date : 2022-05-20 DOI: 10.1109/cvidliccea56201.2022.9824311

Shiwen Li

{"title":"Trans-CycleGAN: Image-to-Image Style Transfer with Transformer-based Unsupervised GAN","authors":"Shiwen Li","doi":"10.1109/cvidliccea56201.2022.9824311","DOIUrl":"https://doi.org/10.1109/cvidliccea56201.2022.9824311","url":null,"abstract":"The field of computer image generation is developing rapidly, and more and more personalized image-to-image style transfer software is produced. Image translation can convert two different styles of data to generate realistic pictures, which can not only meet the individual needs of users, but also meet the problem of insufficient data for a certain style of pictures. Transformers not only have always occupied an important position in the NLP field. In recent years, due to its model interpretability and strong multimodal fusion ability, it has also performed well in the field of computer vision. This paper studies the application of Transformers in the field of image-to-image style transfer. Replace the traditional CNN structure with the improved Transformer of the discriminator and generator model of CycleGAN, and a comparative experiment is carried out with the traditional CycleGAN. The test dataset uses the public datasets Maps and CelebA, and the results are comparable to those of the traditional CycleGAN. This paper shows that Transformer can perform the task of image-to-image style transfer on unsupervised GAN, which expands the application of Transformer in the CV filed, and can be used as a general architecture applied to more vision tasks in the future.","PeriodicalId":23649,"journal":{"name":"Vision","volume":"178 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2022-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72704033","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: 1

Analysis of nonlinear deformation relationship between steel-plastic grid and membrane structure based on Abaqus software 基于Abaqus软件的钢塑网格与膜结构非线性变形关系分析

Vision Pub Date : 2022-05-20 DOI: 10.1109/cvidliccea56201.2022.9824844

Yuanyuan Tian, Hongyue You, Zhongying Li, Haixiang Nie, Xiang Ren

引用次数: 0

CSNet-PGNet: Algorithm for Scene Text Detection and Recognition 场景文本检测与识别算法

Vision Pub Date : 2022-05-20 DOI: 10.1109/cvidliccea56201.2022.9824815

Guanjing Li

{"title":"CSNet-PGNet: Algorithm for Scene Text Detection and Recognition","authors":"Guanjing Li","doi":"10.1109/cvidliccea56201.2022.9824815","DOIUrl":"https://doi.org/10.1109/cvidliccea56201.2022.9824815","url":null,"abstract":"In recent years, the detection and recognition of scene text have developed rapidly, but two difficult challenges have not been well solved. First, semantic analysis based on convolutional neural networks and powerful ImageNet pre-training incur high computational costs. Second, scene text detection with irregular shapes and irregular word order is inaccurate. Aiming at the above problems, this paper proposes a novel and lightweight network module (CSNet-PGNet) for real-time reading of a text of arbitrary shape and orientation. CSNet (Cross-Stage Cross-Scale network) is an extremely lightweight overall cross-stage and cross-scale network, which abandons the cumbersome CNN skeleton network (semantic classification) and can be trained from scratch. PGNet (Point Gathering Network) is a text detection recognizer that can detect and recognize the text of any shape, without the operation of Non-maximum Suppression (NMS) and Region of Interest (RoI), and has the advantages of end-to-end simplicity and efficiency. performance. This paper proposes the CSNet-PGNet scene curve text detection and recognition method, which is a development to more efficient and precise scene text detection of any shapes.","PeriodicalId":23649,"journal":{"name":"Vision","volume":"3 1","pages":"1217-1224"},"PeriodicalIF":0.0,"publicationDate":"2022-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75119597","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: 1

A low-cost and simple on-chip cell counting device based on lensless imaging technology 一种基于无透镜成像技术的低成本、简单的片上细胞计数装置

Vision Pub Date : 2022-05-20 DOI: 10.1109/cvidliccea56201.2022.9825217

Yongliang Wang, Xiaoliang Guo

引用次数: 0

Pointer Network Solution Pool : Combining Pointer Networks and Heuristics to Solve TSP Problems 指针网络解池:结合指针网络和启发式算法求解TSP问题

Vision Pub Date : 2022-05-20 DOI: 10.1109/cvidliccea56201.2022.9824787

Chen Shi

引用次数: 2

A Novel Graph-Based Structural Dissimilarity Measure for Video Summarization 一种基于图的视频摘要结构不相似度度量方法

Vision Pub Date : 2022-05-20 DOI: 10.1109/cvidliccea56201.2022.9824208

Caixia Ma, Lei Lyu, Chen Lyu

引用次数: 0

Strawberry Disease and Pest Identification and Control Based on SE-ResNeXt50 Model 基于SE-ResNeXt50模型的草莓病虫害鉴定与防治

Vision Pub Date : 2022-05-20 DOI: 10.1109/cvidliccea56201.2022.9825283

G. Gan, Xu Xiao, Chuntao Jiang, Yingxi Ye, Yuhao He, Yushen Xu, Chunhai Luo

{"title":"Strawberry Disease and Pest Identification and Control Based on SE-ResNeXt50 Model","authors":"G. Gan, Xu Xiao, Chuntao Jiang, Yingxi Ye, Yuhao He, Yushen Xu, Chunhai Luo","doi":"10.1109/cvidliccea56201.2022.9825283","DOIUrl":"https://doi.org/10.1109/cvidliccea56201.2022.9825283","url":null,"abstract":"Strawberry disease and pest identification and control were rarely studied, with few high-quality open image datasets to date. In view of this situation, firstly, the images of common strawberry pests and diseases of 13 categories were collected both online and offline independently to be constructed into datasets. Secondly, the SE-ResNeXt50 model was created, which had better usability than the residual network model ResNet50. To be specific, the Inception was combined with the ResNet50 model to widen the network, 32 branches were set, and the attention mechanism, the squeeze and excitation module (SE), was also imported, which solved the problems of the complex image background and information interference and improved the identification efficiency and accuracy of the model. The results showed that the accuracy of the SE-ResNeXt50 model, reaching 89.3%, was 8% higher than that of the ResNet50 model. The SEResNeXt50 model had plateaued after iterating 15 times, indicating its good identification performance. Besides, the SEResNeXt50 model, which was developed based on the data obtained in real life, had good generalization ability and robustness, better meeting the demands of strawberry growers. A WeChat mini-program for strawberry disease and pest identification based on the SE-ResNeXt50 model was developed, enabling the fruit growers to identify the strawberry pests and diseases easily and get prevention suggestions, promoting the development of the strawberry industry.","PeriodicalId":23649,"journal":{"name":"Vision","volume":"59 1","pages":"237-243"},"PeriodicalIF":0.0,"publicationDate":"2022-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86047177","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: 1

EEG data augmentation for Personal Identification Using SF-GAN 基于SF-GAN的个人识别EEG数据增强

Vision Pub Date : 2022-05-20 DOI: 10.1109/cvidliccea56201.2022.9824276

Shuai Zhang, Xiuqing Mao, Lei Sun, Yu Yang

{"title":"EEG data augmentation for Personal Identification Using SF-GAN","authors":"Shuai Zhang, Xiuqing Mao, Lei Sun, Yu Yang","doi":"10.1109/cvidliccea56201.2022.9824276","DOIUrl":"https://doi.org/10.1109/cvidliccea56201.2022.9824276","url":null,"abstract":"Because EEG-based identity requires a large amount of training data when training a classification model, and the collection of EEG signals requires a lot of time and effort. Therefore, we hope to perform data augmentation on the EEG data used for identity. Generative adversarial networks have achieved great success in image generation, but the raw EEG signals are not in the form of images. Therefore, we process the EEG signal into an EEG topomap with stronger spatial feature representation, and use a spatial feature-based generative adversarial network image augmentation method (SF-GAN). To verify the generality of our proposed method, we use real EEG topomap samples processed from two different EEG datasets, BCI Competition IV 1 and BCI Competition IV 2a, to train SF-GAN to generate augmented samples for training identity classification model. The proposed method can use smaller real samples to expand the training set of identity, reduce the data dependence on real samples, and reduce the time of data collection to a certain extent. And it is proved by experiments that the data generated by this method can further improve the training effect of the classification model.","PeriodicalId":23649,"journal":{"name":"Vision","volume":"6 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2022-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77065359","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: 1

Research on Multi-scale Network Computer Modeling based on Mobile Vendor Management 基于移动厂商管理的多尺度网络计算机建模研究

Vision Pub Date : 2022-05-20 DOI: 10.1109/cvidliccea56201.2022.9824717

Yufan Yang, Xingchen Dong, Yingjun Li, Huaiyang Zhang

引用次数: 0

Research on Binary Program Dynamic Slicing Technology for Cause Analysis of Vulnerability 面向漏洞原因分析的二进制程序动态切片技术研究

Vision Pub Date : 2022-05-20 DOI: 10.1109/cvidliccea56201.2022.9825448

Peiyu Lu, Chao Feng, Chaojing Tang

{"title":"Research on Binary Program Dynamic Slicing Technology for Cause Analysis of Vulnerability","authors":"Peiyu Lu, Chao Feng, Chaojing Tang","doi":"10.1109/cvidliccea56201.2022.9825448","DOIUrl":"https://doi.org/10.1109/cvidliccea56201.2022.9825448","url":null,"abstract":"In cause analysis of vulnerability, multi-level dereference of pointer and array element index analysis are often encountered at the code level, which is reflected in the case of indirect addressing at the assembly level. At present, the program slicing technology commonly used for cause analysis of vulnerability can not completely analyze the data flow and control flow of indirect addressing. In order to solve this problem, this paper proposes a binary program dynamic slicing technology for cause analysis of vulnerability. This technology uses the information related to the reading and writing of registers and memory addresses in the program execution trace to find the relationship of the data flow and control flow between the two instructions, which can more completely retain the information related to the instructions to be sliced, improve the automation component in cause analysis of vulnerability and reduce the cost of manual analysis. In addition, using the static characteristics of execution trace, this paper can meet the needs of researchers for repeated debugging and analysis of a program execution at different time points in the process of program execution.","PeriodicalId":23649,"journal":{"name":"Vision","volume":"4 1","pages":"783-788"},"PeriodicalIF":0.0,"publicationDate":"2022-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87729741","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

Vision最新文献