检索结果-南通市图书馆

visual Semantic Segmentation Based on Few/Zero-Shot Learning:An Overview

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第5期11卷 1106-1126页

作者： Wenqi Ren Yang Tang Qiyu Sun Chaoqiang Zhao Qing-Long Han Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of EducationEast China University of Science and TechnologyShanghai 200237China National Key Laboratory of Air-Based Information Perception and Fusion Aviation Industry Corporation of ChinaLuoyang 471000China School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyMelbourne VIC 3122Australia

visual semantic segmentation aims at separating a visual sample into diverse blocks with specific semantic attributes and identifying the category for each block,and it plays a crucial role in environmental *** learning-based visual semantic segmentation approaches count heavily on largescale training data with dense annotations and consistently fail to estimate accurate semantic labels for unseen *** obstruction spurs a craze for studying visual semantic segmentation with the assistance of few/zero-shot *** emergence and rapid progress of few/zero-shot visual semantic segmentation make it possible to learn unseen categories from a few labeled or even zero-labeled samples,which advances the extension to practical ***,this paper focuses on the recently published few/zero-shot visual semantic segmentation methods varying from 2D to 3D space and explores the commonalities and discrepancies of technical settlements under different segmentation ***,the preliminaries on few/zeroshot visual semantic segmentation,including the problem definitions,typical datasets,and technical remedies,are briefly reviewed and ***,three typical instantiations are involved to uncover the interactions of few/zero-shot learning with visual semantic segmentation,including image semantic segmentation,video object segmentation,and 3D ***,the future challenges of few/zero-shot visual semantic segmentation are discussed.

关键词： visual segmentation separating

visual exploration of Internet news via sentiment score and topic models

在线全文

学校读者我要写书评

暂无评论

Computational visual Media 2020年第3期6卷 333-347页

作者： Songye Han Shaojie Ye Hongxin Zhang Zhejiang University HangzhouChina

Analyzing and understanding Internet news are important for many applications, such as market sentiment investigation and crisis ***, it is challenging for users to interpret a massive amount of unstructured text, to dig out its accurate meaning, and to spot noteworthy news *** overcome these challenges, we propose a novel visualization-driven approach for analyzing news *** first collect Internet news from different sources and encode sentences into a vector representation suitable for input to a neural network, which calculates a sentiment score, to help detect news event patterns. A subsequent interactive visualization framework allows the user to explore the development of and relationships between Internet news *** addition, a method for detecting news events enables users and domain experts to interactively explore the correlations between market sentiment, topic distribution, and event patterns. We use this framework to provide a web-based interactive visualization *** demonstrate the applicability and effectiveness of our proposed system using case studies involving blockchain news.

关键词： interactive visual overcome

visual tracking using discriminative representation with l2 regularization

在线全文

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2019年第1期13卷 199-211页

作者： Haijun WANG Hongjuan GE College of Civil Aviation Nanjing University of Aeronautics and AstronauticsNanjing 211106China Aviation Information Technology Research and Development Center Binzhou UniversityBinzhou 256603China

In this paper,we propose a novel visual tracking method using a discriminative representation under a Bayesian ***,we exploit the histogram of gradient (HOG)to generate the texture features of the target templates and ***,we introduce a novel discriminative representation and l2-regularized least squares method to solve the proposed representation *** proposed model has a closed-form solution and very high computational ***,a novel likelihood function and an update scheme considering the occlusion factor are adopted to improve the tracking performance of our proposed method. Both qualitative and quantitative evaluations on 15 challenging video sequences demonstrate that our method can achieve more robust tracking results in terms of the overlap rate and center location error.

关键词： visual tracking discriminative representation Bayesian framework closed-form solution

visual Feedback Disturbance Rejection Control for an Amphibious Bionic Stingray Under Actuator Saturation

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2023年第2期10卷 566-568页

作者： Haiyan Cheng Bin Fang Qing Liu Jinhua Zhang Jun Hong the Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System Xi’an Jiaotong UniversityXi’an 710049China the School of Automation and Information Engineering Xi’an University of TechnologyXi’an 710048China

Dear Editor,This letter is concerned with visual feedback disturbance rejection control for an amphibious bionic stingray subject to actuator saturation with internal and external disturbances. A visual feedback control method is designed for a dynamic nonlinear system on yaw angle of the amphibious bionic stingray via a finite-time extended-stateobserver,which is proved to achieve finite-time stability via a Lyapunov method. Finally, simulation results verify the effectiveness on the visual feedback control method.

关键词： visual concerned saturation

visual salience guided feature-aware shape simplification

在线全文

学校读者我要写书评

暂无评论

Journal of Zhejiang University-Science C(Computers and Electronics) 2014年第9期15卷 744-753页

作者： Yong-wei MIAO Fei-xia HU Min-yan CHEN Zhen LIU Hua-hao SHOU College of Computer Science and Technology Zhejiang University of Technology College of Science Zhejiang University of Technology

In the area of 3D digital engineering and 3D digital geometry processing, shape simplification is an important task to reduce their requirement of large memory and high time complexity. By incorporating the content-aware visual salience measure of a polygonal mesh into simplification operation, a novel feature-aware shape simplification approach is presented in this paper. Owing to the robust extraction of relief heights on 3D highly detailed meshes, our visual salience measure is defined by a center-surround operator on Gaussian-weighted relief heights in a scale-dependent manner. Guided by our visual salience map, the feature-aware shape simplification algorithm can be performed by weighting the high-dimensional feature space quadric error metric of vertex pair contractions with the weight map derived from our visual salience map. The weighted quadric error metric is calculated in a six-dimensional feature space by combining the position and normal information of mesh vertices. Experimental results demonstrate that our visual salience guided shape simplification scheme can adaptively and effectively re-sample the underlying models in a feature-aware manner, which can account for the visually salient features of the complex shapes and thus yield better visual fidelity.

关键词： visual salience Shape simplification Content-aware Weighted quadric error metric Feature-aware

Discerning Weld Seam Pro les from Strong Arc Background for the Robotic Automated Welding Process via visual Attention Features

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Mechanical Engineering 2020年第1期33卷 170-181页

作者： Yinshui He Zhuohua Yu Jian Li Lesheng Yu Guohong Ma School of Environment and Chemical Engineering Nanchang UniversityNanchang 330031China School of Mechanical Engineering Key Laboratory of Lightweight and High Strength Structural Materials of Jiangxi ProvinceNanchang UniversityNanchang 330031China Institute of Technology.East China Jiao Tong University Nanchang 330100China

In the robotic welding process with thick steel plates,laser vision sensors are widely used to profile the weld seam to implement automatic seam *** weld seam profile extraction(WSPE)result is a crucial step for identifying the feature points of the extracted profile to guide the welding torch in real *** visual information processing system may collapse when interference data points in the image survive during the phase of feature point identification,which results in low tracking accuracy and poor welding *** paper presents a visual attention featurebased method to extract the weld seam profile(WSP)from the strong arc background using clustering ***,a binary image is obtained through the preprocessing ***,all data points with a gray value 255 are clustered with the nearest neighborhood clustering ***,a strategy is developed to discern one cluster belonging to the WSP from the appointed candidate clusters in each loop,and a scheme is proposed to extract the entire WSP using visual *** with the previous methods the proposed method in this paper can extract more useful details of the WSP and has better stability in terms of removing the interference *** WSPE tests with butt joints and T-joints show the anti-interference ability of the proposed method,which contributes to smoothing the welding process and shows its practical value in robotic automated welding with thick steel plates.

关键词： Weld seam profile extraction visual attention features Clustering Robotic welding

Perovskite-based color camera inspired by human visual cells

在线全文

学校读者我要写书评

暂无评论

Light(Science & Applications) 2023年第2期12卷 294-303页

作者： Yujin Lu Zhong Ji Guobiao Cen Hengchao Sun Haibao Wang Chuanxi Zhao Zhong Lin Wang Wenjie Mai Siyuan Laboratory Guangzhou Key Laboratory of Vacuum Coating Technologies and New Energy MaterialsGuangdong Provincial Key Laboratory of Optical Fiber Sensing and CommunicationsGuangdong Provincial Engineering Technology Research Center of Vacuum Coating Technologies and New Energy MaterialsDepartment of PhysicsJinan UniversityGuangzhouGuangdong 510632China Guangzhou Institute of Technology Xidian UniversityGuangzhouGuangdong 510555China Bejing Smart-Chip Microelectronics Technology Co. Ltd.Bejing 100192China CAS Center for Excellence in Nanoscience Beijing Key Laboratory of Micro-Nano Energy and SensorBeijing Institute of Nanoenergy and NanosystemsChinese Academy of SciencesBejing 100083China School of Materials Science and Engineering Georgia Institute of TechnologyAtlantaGA 30332USA

There are two primary types of photoreceptor cells in the human eye:cone cells and rod cells that enable color vision and night vision,***,inspired by the function of human visual cells,we develop a high-resolution perovskite-based color camera using a set of narrowband red,green,blue,and broadband white perovskite photodetectors as imaging *** narrowband red,green,and blue perovskite photodetectors with color perceptions mimic long-,medium-,and short-wavelength cones cells to achieve color imaging ***,the broadband white perovskite photodetector with better detectivity mimics rod cells to improve weak-light imaging *** perovskite-based camera,combined with predesigned pattern illumination and image reconstruction technology,is demonstrated with high-resolution color images(up to 256 x 256 pixels)in diffuse *** is far beyond previously reported advanced perovskite array image sensors that only work in monochrome transmission *** work shows a new approach to bio-inspired cameras and their great potential to strongly mimic the ability of the natural eve.

关键词： visual perovskite image

Pd films on soft substrates:a visual,high-contrast and low-cost optical hydrogen sensor

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Light(Science & Applications) 2019年第1期8卷 1151-1160页

作者： Xiaoyi She Yang Shen Jianfang Wang Chongjun Jin State Key Laboratory of Optoelectronic Materials and Technologies School of Materials Science and EngineeringSun Yat-sen UniversityGuangzhou 510275China School of Electronics and Information Technology Sun Yat-sen UniversityGuangzhou 510275China Department of Physics the Chinese University of Hong KongShatinHong Kong SARChina

For the rapid development of the hydrogen economy,a reliable and low-cost hydrogen sensor appears to be extremely ***,we first show that a palladium film deposited on polydimethylsiloxane(PDMS)can obtain an exceedingly high-reflectance contrast of 25.78 over the entire visible band upon exposure to 4 vol% hydrogen gas(H2)mixed with nitrogen *** high-reflectance contrast results from the surface deformation induced by the volume inflation after exposure to H2,leading to the transition of the near-specular surface to a diffusing *** addition,a change in brightness is readable by naked eye upon exposure to H2 with various concentrations from 0.6 to 1 vol% under the illumination of a fluorescent ***,this sensor possesses an excellent recyclability and quick response time of a few *** with Pd nanostructure-based hydrogen sensors,this visual,high-contrast and low-cost sensor is of great potential for practical hydrogen sensing.

关键词： deformation cost visual

A novel visual attention method for target detection from SAR images

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2019年第8期32卷 1946-1958页

作者： Fei GAO Aidong LIU Kai LIU Erfu YANG Amir HUSSAIN School of Electronic and Information Engineering Beihang UniversityBeijing 100083China Space Mechatronic Systems Technology Laboratory Department of DesignManufacture and Engineering ManagementUniversity of StrathclydeGlasgow G1 1XJUK Cognitive Big Data and Cyber-Informatics(CogBID)Laboratory School of ComputingEdinburgh Napier UniversityEdinburgh EH10 5DTScotlandUK

Synthetic Aperture Radar(SAR) imaging systems have been widely used in civil and military fields due to their all-weather and all-day abilities and various other advantages. However, due to image data exponentially increasing, there is a need for novel automatic target detection and recognition technologies. In recent years, the visual attention mechanism in the visual system has helped humans effectively deal with complex visual signals. In particular, biologically inspired top-down attention models have garnered much attention recently. This paper presents a visual attention model for SAR target detection, comprising a bottom-up stage and top-down *** the bottom-up step, the Itti model is improved based on the difference between SAR and optical images. The top-down step fully utilizes prior information to further detect targets. Extensive detection experiments carried out on the benchmark Moving and Stationary Target Acquisition and Recognition(MSTAR) dataset show that, compared with typical visual models and other popular detection methods, our model has increased ability and robustness for SAR target detection, under a range of Signal to Clutter Ratio(SCR) conditions and scenes. In addition, results obtained using only the bottom-up stage are inferior to those of the proposed method, further demonstrating the effectiveness and rationality of a top-down strategy. In summary, our proposed visual attention method can be considered a potential benchmark resource for the SAR research community.

关键词： Learning strategy Synthetic Aperture Radar(SAR) images Target detection Top-down visual attention mechanism