检索结果-南通市图书馆

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

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 perception.Conventional 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 categories.This obstruction spurs a craze for studying Visual semantic segmentation with the assistance of few/zero-shot learning.The 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 applications.Therefore,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 circumstances.Specifically,the preliminaries on few/zeroshot Visual semantic segmentation,including the problem definitions,typical datasets,and technical remedies,are briefly reviewed and discussed.Moreover,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 segmentation.Finally,the future challenges of few/zero-shot Visual semantic segmentation are discussed.

关键词： Visual segmentation separating

来源：

维普期刊数据库

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

A deep learning based fine-grained classification algorithm for grading of Visual impairment in cataract patients

引用

Optoelectronics Letters 2024年第1期20卷 48-57页

作者： JIANG Jiewei ZHANG Yi XIE He YANG Jingshi GONG Jiamin LI Zhongwen School of Electronic Engineering Xi'an University of Posts and TelecommunicationsXi'an 710121China School of Ophthalmology and Optometry and Eye Hospital Wenzhou Medical UniversityWenzhou 325000China Ningbo Eye Hospital Wenzhou Medical UniversityNingbo 315000China

Recent advancements in artificial intelligence(AI)have shown promising potential for the automated screening and grading of cataracts.However,the different types of Visual impairment caused by cataracts exhibit similar phenotypes,posing significant challenges for accurately assessing the severity of Visual impairment.To address this issue,we propose a dense convolution combined with attention mechanism and multi-level classifier(DAMC_Net)for Visual impairment grading.First,the double-attention mechanism is utilized to enable the DAMC_Net to focus on lesions-related regions.Then,a hierarchical multi-level classifier is constructed to enhance the recognition ability in distinguishing the severities of Visual impairment,while maintaining a better screening rate for normal samples.In addition,a cost-sensitive method is applied to address the problem of higher false-negative rate caused by the imbalanced dataset.Experimental results demonstrated that the DAMC_Net outperformed ResNet50 and dense convolutional network 121(DenseNet121)models,with sensitivity improvements of 6.0%and 3.4%on the category of mild Visual impairment caused by cataracts(MVICC),and 2.1%and 4.3%on the category of moderate to severe Visual impairment caused by cataracts(MSVICC),respectively.The comparable performance on two external test datasets was achieved,further verifying the effectiveness and generalizability of the DAMC_Net.

关键词： Visual classifier algorithm

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Three-dimensional shape space learning for Visual concept construction:challenges and research progress

引用

Frontiers of Information Technology & Electronic Engineering 2022年第9期23卷 1290-1297页

作者： Xin TONG Microsoft Research Asia Beijing100080China

Human beings can casily categorizethreedimensional(3D)objects with similar shapes and functions into a set of"Visual concepts"and learn"Visual knowledge"of the surrounding 3D real world(Pan,2019).Developing efficient methods to learn the computational representation of the Visual concept and the Visual knowledge is a critical task in artificial intelligence(Pan,2021a).A crucial step to this end is to learn the shape space spanned by all 3D objects that belong to one Visual concept.In this paper,we present the key technical challenges and recent research progress in 3D shape space learning and discuss the open problems and research opportunitices in this area.

关键词： Visual shape artificial

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Simulating tactile and Visual multisensory behaviour in humans based on an MoS_(2) field effect transistor

引用

Nano Research 2023年第5期16卷 7405-7412页

作者： Jie You Liming Wang Yichi Zhang Dongdong Lin Bo Wang Zhao Han Ningning Zhang Tian Miao Maliang Liu Zuimin Jiang Hui Guo Yimeng Zhang Jincheng Zhang Huiyong Hu Wide Bandgap Semiconductor Technology Disciplines State Key Laboratory School of Microelectronics Xidian UniversityXi’an 710071China Qian Xuesen Collaborative Research Center of Astrochemistry and Space Life Sciences Department of Microelectronic Science and EngineeringNingbo UniversityNingbo 315211China Department of Physics Fudan UniversityShanghai 200433China

A Visual and tactile multisensory integrated system is essential for human walking due to the demand for real-time interactions between perception and action.Here,a piezoresistor and MoS_(2)field effect transistor are combined to construct an artificial integration nervous system to simulate perception and synaptic plasticity.The key characteristics of synaptic plasticity are successfully demonstrated by individual pressure signals,individual optical signals,the synergy of optical and pressure signals,which are based on the electron trapping–detrapping mechanism at the MoS_(2)/SiO_(2)interface.We demonstrate that perception under synergy is stronger than perception under optical or pressure signal alone,which is similar to a biological system.Moreover,various distinguishable motion scenarios(combination of the following conditions:external lighting environment of day or night,flat or rough road,movement state of walking or running)are simulated and verified by adjusting the amplitude and frequency of the optical and pressure signals.

关键词： Visual tactile multisensory system motion scenarios

来源：

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

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

引用

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

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Attention Field Size Alters Patterns of Population Receptive Fields in the Early Visual Cortex

引用

Neuroscience Bulletin 2022年第2期38卷 205-208页

作者： Bo Liu Xiaochun Wang Le Wang Qiaojun Qu Wei Zhang Bin Wang Jie Xiang Ting Yan Tianyi Yan Hui Zhang College of Medical Imaging Shanxi Medical UniversityTaiyuan 030001China Department of Radiology First Clinical Medical CollegeShanxi Medical UniversityTaiyuan 030001China College of Information and Computer Taiyuan University of TechnologyTaiyuan 030001China Intelligent Imaging Big Data and Functional Nano-imaging Engineering Research Center of Shanxi Province Shanxi Medical UniversityTaiyuan 030001China Translational Medicine Research Center Shanxi Medical UniversityTaiyuan 030001China School of Life Science Beijing Institute of TechnologyBeijing 100081China Ministry of Industry and Information Technology Key Laboratory of Convergence Medical Engineering System and Healthcare TechnologyBeijing Institute of TechnologyBeijing 100081China

Dear Editor,Visual spatial attention is a cognitive process by which prior information about the relevance of spatial locations is used to improve perceptual performance[1].Visual attention is spread across the attention field(AF),a range within Visual space.The AF reshapes the distribution of activity throughout the Visual pathway,including the early Visual cortex(EVC)and all areas along the dorsal and ventral Visual cortical pathways[2,3].Importantly,the effect of attention depends not only on the spatial position of the AF but also on its size[4].

关键词： Visual Cortex Visual

来源：

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

Domestication-related changes in seed dispersal and pigmentation:Visual selection and functional trait?

引用

Molecular Plant 2023年第8期16卷 1240-1242页

作者： Petr Smykal Travis Parker Department of Botany Palacky University in Olomouc77900 OlomoucCzech Republic Department of Plant Sciences University of CaliforniaDavisDavisCA 95616USA

The development of agriculture is one of the most transformative changes in the history of humankind.Among the most common changes occurring during plant domestication are reductions in seed dispersal and changes in pigmentation.Although there are archaeological records of these processes,the advancement of genomics offers a tool to achieve greater insight into the process of converting wild plants into crops(Smýkal et al.,2018).This involved and resulted in a set of specific phenotypic changes referred to collectively as the domestication syndrome.Recently,less obvious domestication-related modifications have also been identified,including changes in plant biochemistry.These processes are often intertwined.For example,among visible changes,selection for Visual appearance such as pigmentation is governed by modulation of specific metabolic pathways.Like genomic tools,the improvement of analytical methods provides the opportunity to reveal metabolomic changes involved in plant domestication.

关键词： Visual collective crops

来源：

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

On Visual understanding

引用

Frontiers of Information Technology & Electronic Engineering 2022年第9期23卷 1287-1289页

作者： Yunhe PAN Institute of Artificial Intelligence College of Computer Science and TechnologyZhejiang UniversityHangzhou310027China Zhejiang Lab HangzhouChina

1 Problems and development in the field of Visual recognition From the beginning of artificial intelligence(AI),pattern recognition has been an important aspect of the field.In recent years,the maturity of deep neural networks(DNNs)has significantly improved the accuracy of Visual recognition.DNN has been widely used in applications such as medical image classification,vehicle identification,and facial recognition,and has thus promoted the development of the Al industryto a climax.

关键词： Visual artificial networks

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Visual cognition of birds and its underlying neural mechanism:A review

引用

Avian Research 2022年第2期13卷 216-225页

作者： Xiaoke Niu Zhenyang Jiang Yanyan Peng Shuman Huang Zhizhong Wang Li Shi Henan Key Laboratory of Brain Science and Brain-Computer Interface Technology School of Electrical EngineeringZhengzhou UniversityZhengzhou450001China Department of Automation Tsinghua UniversityBeijing100084China

Birds have acute vision and many remarkable Visual cognition abilities,due to their unique living environment.The underlying neural mechanisms have also attracted interests of researchers in neuroscience.Here,we firstly summarize the Visual cognition abilities of birds,and make a comparison with mammals.Secondly,the underlying neural mechanisms are presented,including histological structure of avian brain and Visual pathways,typical experimental results and conclusions in electrochemistry and electrophysiology.The latter mainly focuses on several higher brain areas related to Visual cognition,including mesopallium ventrolaterale,entopallium,Visual Wulst,and nidopallium caudolaterale.Finally,we make a conclusion and provide a suggestion about future studies on revealing the neural mechanisms of avian Visual cognition.This review presents a detailed understanding of avian Visual cognition and would be helpful in ornithology studies in the field of cognitive neuroscience.

关键词： neural Visual cognition

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Rapid Visual detection of Vibrio parahaemolyticus by combining LAMP-CRISPR/Cas12b with heat-labile uracil-DNA glycosylase to eliminate carry-over contamination

引用

Journal of Zhejiang University-Science B(Biomedicine & Biotechnology) 2023年第8期24卷 749-754页

作者： Fang WU Chen LU Wenhao HU Xin GUO Jiayue CHEN Zhidan LUO Jiangsu Key Laboratory of Marine Biological Resources and Environment Jiangsu Key Laboratory of Marine Pharmaceutical Compound ScreeningJiangsu Ocean UniversityLianyungang 222005China Co-Innovation Center of Jiangsu Marine Bio-industry Technology Jiangsu Ocean UniversityLianyungang 222005China BestEnzymes Biotech Co. Ltd.Lianyungang 222005China

Vibrio parahaemolyticus is a major pathogen frequently found in seafood.Rapid and accurate detection of this pathogen is important for the control of bacterial foodborne diseases and to ensure food safety.In this study,we established a one-pot system that combines uracil-DNA glycosylase(UDG),loopmediated isothermal amplification(LAMP),and clustered regularly interspaced short palindromic repeats(CRISPR)/CRISPR-associated protein 12b(Cas12b)for detecting V.parahaemolyticus in seafood.This detection system can effectively perform identification using a single tube and avoid the risk of carryover contamination.

关键词： LAMP Visual system

来源：

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

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：