检索结果-内蒙古大学图书馆

Energy-Efficient ReS2-Based Optoelectronic Synapse for 3D Object Reconstruction and Recognition

ACS APPLIED MATERIALS & INTERFACES 2023年第50期15卷 58631-58642页

作者： Chen, Yabo Huang, Yujie Zeng, Junwei Kang, Yan Tan, Yinlong Xie, Xiangnan Wei, Bo Li, Cheng Fang, Liang Jiang, Tian Natl Univ Def Technol Inst Quantum Informat Coll Comp Changsha 410073 Peoples R China Natl Univ Def Technol Coll Comp State Key Lab High Performance Comp Changsha 410073 Peoples R China Natl Univ Def Technol Coll Adv Interdisciplinary Studies Changsha 410073 Peoples R China Natl Univ Def Technol Inst Quantum Informat Sci & Technol Coll Sci Changsha 410073 Peoples R China

The neuromorphic vision system (NvS) equipped with optoelectronic synapses integrates perception, storage, and processing and is expected to address the issues of traditional machine vision. However, owing to their lack of stereo vision, existing NvSs focus on 2D image processing, which makes it difficult to solve problems such as spatial cognition errors and low-precision interpretation. Consequently, inspired by the human visual system, an NvS with stereo vision is developed to achieve 3D object recognition, depending on the prepared ReS2 optoelectronic synapse with 12.12 fJ ultralow power consumption. This device exhibits excellent optical synaptic plasticity derived from the persistent photoconductivity effect. As the cornerstone for 3D vision, color planar information is successfully discriminated and stored in situ at the sensor end, benefiting from its wavelength-dependent plasticity in the visible region. Importantly, the dependence of the channel conductance on the target distance is experimentally revealed, implying that the structure information on the object can be directly captured and stored by the synapse. The 3D image of the object is successfully reconstructed via fusion of its planar and depth images. Therefore, the proposed 3D-NvS based on ReS2 synapses for 3D objects achieves a recognition accuracy of 97.0%, which is much higher than that for 2D objects (32.6%), demonstrating its strong ability to prevent 2D-photo spoofing in applications such as face payment, entrance guard systems, and others.

关键词： neuromorphic visionsystem optoelectronic synapse stereo vision 3D object recognition persistentphotoconductivity

来源：评论

学校读者我要写书评

暂无评论

Investigating the efficacy of deep learning networks for 3D imaging and processing

Investigating the efficacy of deep learning networks for 3D ...

引用

3D image Acquisition and Display: Technology, Perception and applications, 3D 2024 - Part of Optica Imaging Congress

作者： Muniraj, Inbarasan LiFE Lab Alliance School of Applied Engineering Alliance University Karnataka Bengaluru562106 India

Artificial intelligence techniques, such as machine learning (ML) and deep learning (DL), are now widely used in various vision-based applications. Here, we summarize some of the most recent advances in Computational ... 详细信息

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Impact of Hybrid [CPU-GPU] Architecture on machine Learning-based image-to-image Translation Using HiDT

Impact of Hybrid [CPU-GPU] Architecture on Machine Learning-...

引用

2024 International Conference on Knowledge Engineering and Communication Systems, ICKECS 2024

作者： Kantharaju, v. Chandrashekhar, B.N. Niranjanamurthy, M. Murthy, S.v.N. Bms Institute of Technology and Management Department of Ai & Ml Bengaluru India Amity University Amity School of Engineering and Technology Department of Cse Bangalore India S J C Institute of Technology Department of Cse Karnataka Chikkaballapur India

ISBN: (数字)9798350359688

ISBN: (纸本)9798350359688

image-to-image translation is the process of transforming an image from one domain to another, where the goal is to learn the mapping between an input image and an output image. This task has been generally performed by using a training set of aligned image pairs on fewer cores-based CPU-based architecture, which mainly aims to transfer images from a source domain to a target domain while preserving the content representations by consuming more execution time. Due to its broad range of applications in numerous computer vision and image processing problems, including image synthesis, segmentation, style transfer, restoration, and pose estimation, GPU-based image-to-image has attracted growing attention and made enormous progress in recent years. It can be utilized for a variation of principles, including photo enhancement, object transformation, season transfer, and collection style transfer. Only CPU and only GPU-based architecture are difficult in order to speed up the image processing task, especially during re-rendering the same scene under various illuminations characteristic for day, night, or dawn. To address this issue, in this work, we are proposing the Hybrid CPU-GPU-based architecture with HiDT technology for implementing the image translation works at tremendous speed. On the hybrid CPU-GPU-based architecture, it is possible to train a multi-domain image-to-image translation model with HiDT on variable size of dataset unaligned images without domain labels using this technology when it is integrated into an application. The speed of the mentioned application can be achieved by using emerging technologies such as pix2pixHD and HiDT on hybrid architecture, where pix2pixHD is a deep learning-based technique for high-resolution photorealistic image-to-image translation, and it is implemented in PyTorch. This article represents Impact of Hybrid Architecture on machine Learning-based image-toimage Translation Using HiDT. © 2024 IEEE.

关键词： Training Knowledge engineering image segmentation image resolution image synthesis Pose estimation Lighting

来源：评论

学校读者我要写书评

暂无评论

A survey of human-in-the-loop for machine learning

引用

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 2022年 135卷 364-381页

作者： Wu, Xingjiao Xiao, Luwei Sun, Yixuan Zhang, Junhang Ma, Tianlong He, Liang East China Normal Univ Shanghai Key Lab Multidimens Informat Proc Shanghai Peoples R China East China Normal Univ Sch Comp Sci & Technol Shanghai Peoples R China Fudan Univ Shanghai Peoples R China

machine learning has become the state-of-the-art technique for many tasks including computer vision, natural language processing, speech processing tasks, etc. However, the unique challenges posed by machine learning suggest that incorporating user knowledge into the system can be beneficial. The purpose of integrating human domain knowledge is also to promote the automation of machine learning. Human-in-the-loop is an area that we see as increasingly important in future research due to the knowledge learned by machine learning cannot win human domain knowledge. Human-in-the-loop aims to train an accurate prediction model with minimum cost by integrating human knowledge and experience. Humans can provide training data for machine learning applications and directly accomplish tasks that are hard for computers in the pipeline with the help of machine-based approaches. In this paper, we survey existing works on human-in-the-loop from a data perspective and classify them into three categories with a progressive relationship: (1) the work of improving model performance from data processing, (2) the work of improving model performance through interventional model training, and (3) the design of the system independent human-in-the-loop. Using the above categorization, we summarize the major approaches in the field;along with their technical strengths/weaknesses, we have a simple classification and discussion in natural language processing, computer vision, and others. Besides, we provide some open challenges and opportunities. This survey intends to provide a high-level summarization for human-in-the-loop and to motivate interested readers to consider approaches for designing effective human-in-the-loop solutions. Keywords: Human-in-the-loop machine learning Deep learning Data processing Computer vision Natural language processing (C) 2022 Elsevier B.v. All rights reserved.

关键词： Human-in-the-loop machine learning Deep learning Data processing Computer vision Natural language processing

来源：评论

学校读者我要写书评

暂无评论

A Systematic Review: How Computer vision is Transforming Agriculture in Economic Growth 3rd

A Systematic Review: How Computer Vision is Transforming Agr...

引用

3rd International Conference on Artificial Intelligence and Knowledge processing (AIKP)

作者： Karanam, Santoshachandra Rao Kumar, A. B. Pradeep Yandrapati, Prakash Babu Tangudu, Naresh Peddada, Nagamani Bollipelly, PruthviRaj Goud GITAM Deemed Univ CSE Dept Hyderabad India Aditya Inst Technol & Management CSD & MCA Dept Tekkali Srikakulam India Anurag Univ IT Dept Hyderabad India

ISBN: (纸本)9783031686160;9783031686177

Recent years have seen the emergence of computer vision, a subfield of artificial intelligence (AI), as a technology that has the potential to revolutionize agricultural practices. This might have an impact on many agricultural practices and crop management techniques. This is due to the fact that computer vision can examine pictures and identify patterns of data. This article provides a summary of the uses of computer vision in agriculture as well as the consequences such applications have had. The issues of precision agriculture, disease diagnosis, crop monitoring, and yield computation may be overcome with the use of computer vision technologies such as image recognition, object detection, and pattern analysis. Specifically, it investigates the ways in which these strategies are useful. In addition to this, it investigates the benefits, drawbacks, and possible future applications of computer vision in agriculture, with a particular emphasis on the potential for the sector to improve its levels of productivity, sustainability, and profitability. According to this in-depth analysis, computer vision has revolutionized the agricultural industry and contributed significantly to economic growth. In order to evaluate the financial impacts that computer vision has had on the agricultural industry, this study looks at a wide range of academic papers, publications, and reports. The findings highlight the advancements, benefits, challenges, and future opportunities presented by computer vision technology in the areas of crop monitoring, precision farming, animal management, and harvesting. According to the evaluation, computer vision has the potential to improve farming in terms of productivity, resource allocation, cost reduction, and sustainable practices.

关键词： Computer vision Artificial Intelligence Economic Growth Agriculture Management Agricultural Automation machine Learning

来源：评论

学校读者我要写书评

暂无评论

A comprehensive analysis for crowd counting methodologies and algorithms in Internet of Things

引用

CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND applications 2024年第1期27卷 859-873页

作者： Gao, Mingliang Souri, Alireza Zaker, Mayram Zhai, Wenzhe Guo, Xiangyu Li, Qilei Shandong Univ Technol Sch Elect & Elect Engn Zibo 255000 Peoples R China Halic Univ Dept Software Engn TR-34060 Istanbul Turkiye Islamic Azad Univ Dept Comp Engn Sci & Res Branch Tehran Iran Queen Mary Univ London Sch Elect Engn & Comp Sci London E1 4NS England

The Internet of Things (IoT) provides a collaborative infrastructure to communicate smart devices with cloud-edge healthcare applications, medical devices, wearable biosensors, etc. On the other hand, crowd counting as one of computer vision approaches is an emerging topic to detect any objects with static or dynamic mobility in the IoT environments. Smart crowd counting enables pattern recognition for many intelligent applications such as microbiology, surveillance, healthcare systems, crowdedness estimation, and other environmental case studies. According to complicated capturing systems in the IoT environments, crowd counting methods can influence on performance of object detection in the critical case studies using Artificial Intelligence (AI)-based approaches such as machine learning, deep learning, collaborative learning, fuzzy logic and meta-heuristic algorithms. This paper provides a new comprehensive technical analysis for existing AI-based crowd counting approaches in healthcare and medical systems, biotechnology and IoT environments. Meanwhile, it presents a discussion on the existing case studies with respect to analyzing technical aspects and applied algorithms to enhance pattern prediction factors. Finally, some new innovative efforts and challenges are presented for new research upcoming and open issues.

关键词： Internet of Things (IoT) Artificial Intelligence Crowd counting WiFi sensing image processing

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Few-Shot Incremental Learning for Point-Cloud Recognition

Cross-Domain Few-Shot Incremental Learning for Point-Cloud R...

引用

IEEE/CvF Winter Conference on applications of Computer vision (WACv)

作者： Tan, Yuwen Xiang, Xiang Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Minist Educ Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China

ISBN: (纸本)9798350318920;9798350318937

Sensing 3D objects is critical when 2D object recognition is not accessible. A robot pre-trained on a large point-cloud dataset will encounter unseen classes of 3D objects after deploying it. Therefore, the robot should be able to learn continuously in real-world scenarios. Few-shot class-incremental learning (FSCIL) requires the model to learn from few-shot new examples continually and not forget past classes. However, there is an implicit but strong assumption in the FSCIL that the distribution of the base and incremental classes is the same. In this paper, we focus on cross-domain FSCIL for point-cloud recognition. We decompose the catastrophic forgetting into base class forgetting and incremental class forgetting and alleviate them separately. We utilize the base model to discriminate base samples and new samples by treating base samples as in-distribution samples, and new objects as out-of-distribution samples. We retain the base model to avoid catastrophic forgetting of base classes and train an extra domain-specific module for all new samples to adapt to new classes. At inference, we first discriminate whether the sample belongs to the base class or the new class. Once classified at the model level, test samples are then passed to the corresponding model for class-level classification. To better mitigate the forgetting of new classes, we adopt the soft label and hard label replay together. Extensive experiments on synthetic-to-real incremental 3D datasets show that our proposed method can balance the performance between the base and new objects and outperforms the previous state-of-the-art methods.

关键词： 3D computer vision Algorithms Algorithms Algorithms and algorithms formulations image recognition and understanding machine learning architectures

来源：评论

学校读者我要写书评

暂无评论

A Review on Quantum machine Learning in Different Computer vision Fields

A Review on Quantum Machine Learning in Different Computer V...

引用

2024 IEEE International Performance, Computing, and Communications Conference, IPCCC 2024

作者： Islam, Md Majedul He, Jing Selena Kennesaw State University Department of Computer Science Marietta United States

ISBN: (纸本)9798350367942

Quantum machine Learning (QML) promises the transformative potential in computer vision by utilizing quantum computing to facilitate faster high-dimensional data processing. In this paper, we will go through some of the recent works that employ QML for computer vision problems such as image Segmentation, Classification, and Generation. Demonstrations aimed at showing where QML methods beat the state of art techniques in particular applications like facial recognition, medical imaging, and satellite imagery. QML aspires to make pathbreaking changes in a field limited by current hardware capabilities. This poster abstract summarizes the important studies, methodologies and findings to inform further research in this developing field. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

ENvQA: Improving visual Question Answering model by enriching the visual feature

引用

ENGINEERING applications OF ARTIFICIAL INTELLIGENCE 2025年 142卷

作者： Chowdhury, Souvik Soni, Badal Natl Inst Technol Silchar CSE Dept NIT Rd Silchar 788010 Assam India

visual Question Answering (vQA) is pivotal in various industries, including medicine. Current approaches typically rely on identifying patterns between image regions and questions, using attention-learning techniques to highlight essential information and suppress noise. However, existing vQA systems often overlook crucial foreground and background-related features in images, limiting their ability to tackle complex questions effectively. Most vQA models employ either spatial or channel attention mechanisms. Spatial attention localizes the region of interest (ROI) but may overlook global semantic relationships between salient objects. Conversely, channel attention enhances feature representation but disregards spatial dynamics within images. To address these limitations, we propose "ENvQA" (Enriching v in vQA), a novel vQA model that integrates enriched visual features by leveraging both spatial and object-level features, alongside spatial and channel attention networks. Our model aims to enhance understanding by capturing both local and global contexts within images. Experimental evaluations on benchmark datasets such as vQA 2.0, TDIUC, and GQA demonstrate that ENvQA outperforms state-of-the-art (SOTA) models utilizing attention mechanisms.

关键词： visual Question Answering Computer vision Natural language processing visual and language

来源：评论

学校读者我要写书评

暂无评论

Synthetic Data Generation for AI-based machine vision applications

Synthetic Data Generation for AI-based Machine Vision Applic...

引用

IS and T International Symposium on Electronic Imaging 2024: Intelligent Robotics and Industrial applications using Computer vision, IRIACv 2024

作者： Seiler, Frederik Eichinger, verena Effenberger, Ira Fraunhofer IPA Stuttgart Germany

This paper presents a method for synthesizing 2D and 3D sensor data for various machine vision tasks. Depending on the task, different processing steps can be applied to a 3D model of an object. For object detection, segmentation and pose estimation, random object arrangements are generated automatically. In addition, objects can be virtually deformed in order to create realistic images of non-rigid objects. For automatic visual inspection, synthetic defects are introduced into the objects. Thus sensor-realistic datasets with typical object defects for quality control applications can be created, even in the absence of defective parts. The simulation of realistic images uses physically based rendering techniques. Material properties and different lighting situations are taken into account in the 3D models. The resulting tuples of 2D images and their ground truth annotations can be used to train a machine learning model, which is subsequently applied to real data. In order to minimize the reality gap, a random parameter set is selected for each image, resulting in images with high variety. Considering the use cases damage detection and object detection, it has been shown that a machine learning model trained only on synthetic data can also achieve very good results on real data. © 2024, Society for Imaging Science and Technology.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：