期刊文献+
共找到9篇文章
< 1 >
每页显示 20 50 100
A Concise and Varied Visual Features-Based Image Captioning Model with Visual Selection
1
作者 Alaa Thobhani Beiji Zou +4 位作者 Xiaoyan Kui Amr Abdussalam Muhammad Asim Naveed Ahmed Mohammed Ali Alshara 《Computers, Materials & Continua》 SCIE EI 2024年第11期2873-2894,共22页
Image captioning has gained increasing attention in recent years.Visual characteristics found in input images play a crucial role in generating high-quality captions.Prior studies have used visual attention mechanisms... Image captioning has gained increasing attention in recent years.Visual characteristics found in input images play a crucial role in generating high-quality captions.Prior studies have used visual attention mechanisms to dynamically focus on localized regions of the input image,improving the effectiveness of identifying relevant image regions at each step of caption generation.However,providing image captioning models with the capability of selecting the most relevant visual features from the input image and attending to them can significantly improve the utilization of these features.Consequently,this leads to enhanced captioning network performance.In light of this,we present an image captioning framework that efficiently exploits the extracted representations of the image.Our framework comprises three key components:the Visual Feature Detector module(VFD),the Visual Feature Visual Attention module(VFVA),and the language model.The VFD module is responsible for detecting a subset of the most pertinent features from the local visual features,creating an updated visual features matrix.Subsequently,the VFVA directs its attention to the visual features matrix generated by the VFD,resulting in an updated context vector employed by the language model to generate an informative description.Integrating the VFD and VFVA modules introduces an additional layer of processing for the visual features,thereby contributing to enhancing the image captioning model’s performance.Using the MS-COCO dataset,our experiments show that the proposed framework competes well with state-of-the-art methods,effectively leveraging visual representations to improve performance.The implementation code can be found here:https://github.com/althobhani/VFDICM(accessed on 30 July 2024). 展开更多
关键词 visual attention image captioning visual feature detector visual feature visual attention
下载PDF
Decoding brain responses to pixelized images in the primary visual cortex: implications for visual cortical prostheses 被引量:4
2
作者 Bing-bing Guo Xiao-lin Zheng +4 位作者 Zhen-gang Lu Xing Wang Zheng-qin Yin Wen-sheng Hou Ming Meng 《Neural Regeneration Research》 SCIE CAS CSCD 2015年第10期1622-1627,共6页
Visual cortical prostheses have the potential to restore partial vision. Still limited by the low-resolution visual percepts provided by visual cortical prostheses, implant wearers can currently only "see" pixelized... Visual cortical prostheses have the potential to restore partial vision. Still limited by the low-resolution visual percepts provided by visual cortical prostheses, implant wearers can currently only "see" pixelized images, and how to obtain the specific brain responses to different pixelized images in the primary visual cortex(the implant area) is still unknown. We conducted a functional magnetic resonance imaging experiment on normal human participants to investigate the brain activation patterns in response to 18 different pixelized images. There were 100 voxels in the brain activation pattern that were selected from the primary visual cortex, and voxel size was 4 mm × 4 mm × 4 mm. Multi-voxel pattern analysis was used to test if these 18 different brain activation patterns were specific. We chose a Linear Support Vector Machine(LSVM) as the classifier in this study. The results showed that the classification accuracies of different brain activation patterns were significantly above chance level, which suggests that the classifier can successfully distinguish the brain activation patterns. Our results suggest that the specific brain activation patterns to different pixelized images can be obtained in the primary visual cortex using a 4 mm × 4 mm × 4 mm voxel size and a 100-voxel pattern. 展开更多
关键词 nerve regeneration primary visual cortex electrical stimulation visual cortical prosthesis low resolution vision pixelized image functional magnetic resonance imaging voxel size neural regeneration brain activation pattern
下载PDF
Recent Advances and Challenges of Visual Signal Quality Assessment 被引量:1
3
作者 马林 邓宸伟 +1 位作者 颜庆义 林维斯 《China Communications》 SCIE CSCD 2013年第5期62-78,共17页
While quality assessment is essential for testing, optimizing, benchmarking, monitoring, and inspecting related systems and services, it also plays an essential role in the design of virtually all visual signal proces... While quality assessment is essential for testing, optimizing, benchmarking, monitoring, and inspecting related systems and services, it also plays an essential role in the design of virtually all visual signal processing and communication algorithms, as well as various related decision-making processes. In this paper, we first provide an overview of recently derived quality assessment approaches for traditional visual signals (i.e., 2D images/videos), with highlights for new trends (such as machine learning approaches). On the other hand, with the ongoing development of devices and multimedia services, newly emerged visual signals (e.g., mobile/3D videos) are becoming more and more popular. This work focuses on recent progresses of quality metrics, which have been reviewed for the newly emerged forms of visual signals, which include scalable and mobile videos, High Dynamic Range (HDR) images, image segmentation results, 3D images/videos, and retargeted images. 展开更多
关键词 objective quality assessment 2D images and videos human perception newly emerged visual signals Human visual System
下载PDF
THE SIGNIFICANCE OF TESTING PREOPERATIVE VISUAL FUNCTION IN CATARACT USING LASER INTERFEROMETRIC VISUAL ACUITY AND ERG 被引量:2
4
作者 De-Zheng Wu Lezheng Wu Xijing Xu Hui Chen Taiqing Luo Zhongshan Ophthalmic Center Sun Yat-sen University of Medical Sciences Guangzhou 510060, China 《眼科学报》 1991年第1期21-24,共4页
Tests of preoperative visual function and prediction of postoperative E chart visual acuity(ECVA) using laser interferometric visual acuity(LIVA) and electroretinogram(ERG) were performed in 16 cases(19 eyes) of catar... Tests of preoperative visual function and prediction of postoperative E chart visual acuity(ECVA) using laser interferometric visual acuity(LIVA) and electroretinogram(ERG) were performed in 16 cases(19 eyes) of cataract. The results showed that the coincident rate between preoperative LIVA and postoperative ECVA was 63.2%, and there was a parallel correlation between preoperative amplitude of photopic ERG b-wave and postoperative ECVA in 79.0% of the eyes. Comparing these two methods, the test of LIVA ... 展开更多
关键词 THE SIGNIFICANCE OF TESTING PREOPERATIVE visual FUNCTION IN CATARACT USING LASER INTERFEROMETRIC visual ACUITY AND ERG
下载PDF
Systematic Review of Graphical Visual Methods in Honeypot Attack Data Analysis
5
作者 Gbenga Ikuomenisan Yasser Morgan 《Journal of Information Security》 2022年第4期210-243,共34页
Mitigating increasing cyberattack incidents may require strategies such as reinforcing organizations’ networks with Honeypots and effectively analyzing attack traffic for detection of zero-day attacks and vulnerabili... Mitigating increasing cyberattack incidents may require strategies such as reinforcing organizations’ networks with Honeypots and effectively analyzing attack traffic for detection of zero-day attacks and vulnerabilities. To effectively detect and mitigate cyberattacks, both computerized and visual analyses are typically required. However, most security analysts are not adequately trained in visualization principles and/or methods, which is required for effective visual perception of useful attack information hidden in attack data. Additionally, Honeypot has proven useful in cyberattack research, but no studies have comprehensively investigated visualization practices in the field. In this paper, we reviewed visualization practices and methods commonly used in the discovery and communication of attack patterns based on Honeypot network traffic data. Using the PRISMA methodology, we identified and screened 218 papers and evaluated only 37 papers having a high impact. Most Honeypot papers conducted summary statistics of Honeypot data based on static data metrics such as IP address, port, and packet size. They visually analyzed Honeypot attack data using simple graphical methods (such as line, bar, and pie charts) that tend to hide useful attack information. Furthermore, only a few papers conducted extended attack analysis, and commonly visualized attack data using scatter and linear plots. Papers rarely included simple yet sophisticated graphical methods, such as box plots and histograms, which allow for critical evaluation of analysis results. While a significant number of automated visualization tools have incorporated visualization standards by default, the construction of effective and expressive graphical methods for easy pattern discovery and explainable insights still requires applied knowledge and skill of visualization principles and tools, and occasionally, an interdisciplinary collaboration with peers. We, therefore, suggest the need, going forward, for non-classical graphical methods for visualizing attack patterns and communicating analysis results. We also recommend training investigators in visualization principles and standards for effective visual perception and presentation. 展开更多
关键词 Honeypot Data Analysis Network Intrusion Detection visualization and visual Analysis Graphical Methods and Perception Systematic Literature Review
下载PDF
Visualization and visual analysis of vessel trajectory data: A survey 被引量:3
6
作者 Haiyan Liu Xiaohui Chen +4 位作者 Yidi Wang Bing Zhang Yunpeng Chen Ying Zhao Fangfang Zhou 《Visual Informatics》 EI 2021年第4期1-10,共10页
Maritime transports play a critical role in international trade and commerce.Massive vessels sailing around the world continuously generate vessel trajectory data that contain rich spatial–temporal patterns of vessel... Maritime transports play a critical role in international trade and commerce.Massive vessels sailing around the world continuously generate vessel trajectory data that contain rich spatial–temporal patterns of vessel navigations.Analyzing and understanding these patterns are valuable for maritime traffic surveillance and management.As essential techniques in complex data analysis and understanding,visualization and visual analysis have been widely used in vessel trajectory data analysis.This paper presents a literature review on the visualization and visual analysis of vessel trajectory data.First,we introduce commonly used vessel trajectory data sets and summarize main operations in vessel trajectory data preprocessing.Then,we provide a taxonomy of visualization and visual analysis of vessel trajectory data based on existing approaches and introduce representative works in details.Finally,we expound on the prospects of the remaining challenges and directions for future research. 展开更多
关键词 Maritime traffic Vessel trajectory data Automatic identification system visualization and visual analysis
原文传递
Guest Editorial: Special Issue on Visualization and Visual Analytics
7
作者 Aidong Lu David Ebert +2 位作者 Jinzhu Gao Song Zhang Alark Joshi 《Tsinghua Science and Technology》 SCIE EI CAS 2013年第2期109-110,共2页
This special issue is devoted to the new research addressing challenges in the areas of visualization and visual analytics. Visualization and visual analytics are closely related research areas, both concentrating on ... This special issue is devoted to the new research addressing challenges in the areas of visualization and visual analytics. Visualization and visual analytics are closely related research areas, both concentrating on developing visual techniques to reveal meaningful information out of various data in real-life applications. Visualization as a field has its roots in Computer Graphics and has become a popular research area over the years. The field of visual analytics is relatively young with a concentration on analytical reasoning facilitated by interactive visual interfaces. In general, visualization and visual analytics research is tightly connected with certain types of data or applications and researchers in both fields strive to discover known or unknown data patterns for domain users. 展开更多
关键词 Guest Editorial Special Issue on visualization and visual Analytics
原文传递
Objective visual performance evaluation with visual evoked potential measurements based on an adaptive optics system 被引量:1
8
作者 Yanrong Yang Junlei Zhao +4 位作者 Haoxin Zhao Fei Xiao Jiaxin Xie Wiejun Liu Yun Dai 《Chinese Optics Letters》 SCIE EI CAS CSCD 2018年第5期82-86,共5页
An objective visual performance evaluation with visual evoked potential (VEP) measurements was first inte- grated into an adaptive optics (AO) system. The optical and neural limits to vision can be bypassed throug... An objective visual performance evaluation with visual evoked potential (VEP) measurements was first inte- grated into an adaptive optics (AO) system. The optical and neural limits to vision can be bypassed through this system. Visual performance can be measured electrophysiologically with VEP, which reflects the objective func- tion from the retina to the primary visual cortex. The VEP ts without and with AO correction were preliminarily carried out using this system, demonstrating the great potential of this system in the objective visual performance evaluation. The new system will provide the necessary technique and equipment support for the further study of human visual function. 展开更多
关键词 VEP AO Objective visual performance evaluation with visual evoked potential measurements based on an adaptive optics system PSF
原文传递
Long-term in vivo monitoring of injury induced brain regeneration of the adult zebrafish by using spectral domain optical coherence tomography 被引量:5
9
作者 张建 张志伟 +1 位作者 葛伟 袁振 《Chinese Optics Letters》 SCIE EI CAS CSCD 2016年第8期81-84,共4页
Brain regenerative studies require precise visualization of the morphological structures. However, few imaging methods can effectively detect the adult zebrafish brain in real time with high resolution and good penetr... Brain regenerative studies require precise visualization of the morphological structures. However, few imaging methods can effectively detect the adult zebrafish brain in real time with high resolution and good penetration depth. Long-term in vivo monitoring of brain injuries and brain regeneration on adult zebrafish is achieved in this study by using 1325 nm spectral-domain optical coherence tomography(SD-OCT). The SD-OCT is able to noninvasively visualize the skull injury and brain lesion of adult zebrafish. Valuable phenomenon such as the fractured skull, swollen brain tissues, and part of the brain regeneration process can be conducted based on the SD-OCT images at different time points during a period of 43 days. 展开更多
关键词 regeneration coherence skull visualization fractured visualize penetration injured morphological reconstructed
原文传递
上一页 1 下一页 到第
使用帮助 返回顶部