检索结果-内蒙古大学图书馆

Learning with privileged information using Bayesian networks

Frontiers of computer Science 2015年第2期9卷 185-199页

作者： Shangfei WANG Menghua HE Yachen ZHU Shan HE Yue LIU Qiang JI School of Computer Science and Technology University of Science and Technology of China Hefei 230027 China Key Lab of Computing and Communicating Software of Anhui Province Hefei 230027 China School of Mathematical Sciences University of Science and Technology of China Hefei 230027 China Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute Troy NY 12180-3590 USA

For many supervised learning applications, addi- tional information, besides the labels, is often available dur- ing training, but not available during testing. Such additional information, referred to the privileged information, can be exploited during training to construct a better classifier. In this paper, we propose a Bayesian network （BN） approach for learning with privileged information. We propose to in- corporate the privileged information through a three-node BN. We further mathematically evaluate different topologies of the three-node BN and identify those structures, through which the privileged information can benefit the classifica- tion. Experimental results on handwritten digit recognition, spontaneous versus posed expression recognition, and gender recognition demonstrate the effectiveness of our approach.

关键词： Bayesian network privileged information clas-sification maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

Few-shot Object Detection on Remote Sensing Images

arXiv

引用

arXiv 2020年

作者： Deng, Jingyu Li, Xiang Fang, Yi Multimedia and Visual Computing Lab NYU Tandon and Abu Dhabi Department of Electrical and Computer Engineering NYU Tandon United States Department of Electrical and Computer Engineering NYU Abu Dhabi United Arab Emirates Multimedia and Visual Computing Lab NYU Tandon and Abu Dhabi Department of Electrical and Computer Engineering Abu Dhabi United Arab Emirates

In this paper, we deal with the problem of object detection on remote sensing images. Previous methods have developed numerous deep CNN-based methods for object detection on remote sensing images and the report remarkable achievements in detection performance and efficiency. However, current CNN-based methods mostly require a large number of annotated samples to train deep neural networks and tend to have limited generalization abilities for unseen object categories. In this paper, we introduce a few-shot learning-based method for object detection on remote sensing images where only a few annotated samples are provided for the unseen object categories. More specifically, our model contains three main components: a meta feature extractor that learns to extract feature representations from input images, a reweighting module that learn to adaptively assign different weights for each feature representation from the support images, and a bounding box prediction module that carries out object detection on the reweighted feature maps. We build our few-shot object detection model upon YOLOv3 architecture and develop a multi-scale object detection framework. Experiments on two benchmark datasets demonstrate that with only a few annotated samples our model can still achieve a satisfying detection performance on remote sensing images and the performance of our model is significantly better than the well-established baseline models. Copyright © 2020, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Physically Grounded Deep Learning-Enabled Gold Nanoparticle Localization and Quantification in Photonic Resonator Absorption Microscopy for Digital Resolution Molecular Diagnostics

SSRN

引用

SSRN 2025年

作者： Lee, Hankeun Li, Siyan Liu, Leyang Wang, Weijing Ayupova, Takhmina Tibbs, Joseph Kim, Chansong Fang, Ying Do, Minh N. Cunningham, Brian T. Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign UrbanaIL United States Department of Bioengineering University of Illinois at Urbana-Champaign UrbanaIL United States Department of Chemistry University of Illinois at Urbana-Champaign UrbanaIL United States Department of Pathobiology College of Veterinary Medicine University of Illinois at Urbana-Champaign UrbanaIL United States Department of Materials Science and Engineering University of Illinois at Urbana-Champaign UrbanaIL United States Nick Holonyak Jr. Micro and Nanotechnology Lab University of Illinois at Urbana-Champaign UrbanaIL United States Center for Genomic Diagnostics Woese Institute for Genomic Biology UrbanaIL United States Carl R. Woese Institute for Genomic Biology University of Illinois at Urbana-Champaign UrbanaIL United States Grainger College of Engineering University of Illinois at Urbana-Champaign UrbanaIL United States Siebel School of Computing and Data Science University of Illinois at Urbana-Champaign UrbanaIL United States Carle Illinois College of Medicine University of Illinois at Urbana-Champaign UrbanaIL United States VinUni-Illinois Smart Health Center VinUniversity Hanoi Viet Nam

Accurate molecular biomarker detection with digital-resolution sensitivity is essential for applications such as disease diagnostics, therapeutic studies, and biomedical research. Here, we present LOCA-PRAM (LOcalization with Context Awareness), a deep learning-based method integrated with a Photonic Resonator Absorption Microscope (PRAM) to achieve digital-resolution detection of biomolecules using gold nanoparticles (AuNPs) as molecular tags. LOCA-PRAM leverages photonic crystal (PC)-AuNP resonant-coupling to enhance signal contrast, facilitating precise quantification of target molecules without partitioning the sample into droplets or enzymatic amplification. Through registration of PRAM images with Scanning Electron Microscopy (SEM) images, we empirically obtain the point spread function (PSF) of AuNP tags, enabling realistic training data generation for the deep learning framework. LOCA-PRAM surpasses conventional image processing method in accuracy and sensitivity, achieving reliable AuNP detection and localization even in high-density conditions, minimizing false-positive and false-negative quantifications and expending the dynamic range of assay. Benchmarking with SEM-derived ground truth confirms LOCA-PRAM’s sub-pixel resolution and ability to accurately quantify AuNPs with overlapping PSF. Overall, the PRAM combined with LOCA-based AuNP digital counting enables real-time, high-precision detection of molecular biomarkers, advancing digital-resolution biosensing for biomedical research and diagnostics. © 2025, The Authors. All rights reserved.

关键词： Gold nanoparticles

来源：评论

学校读者我要写书评

暂无评论

Text Detection in Natural Images Using Bio-inspired Models

Text Detection in Natural Images Using Bio-inspired Models

引用

International Conference on Document Analysis and Recognition

作者： Konstantinos Zagoris Ioannis Pratikakis Visual Computing Group Department of Electrical and Computer Engineering Democritus University of Thrace Xanthi Greece

ISBN: (纸本)9781479901937

Textual information in images constitutes a very rich source of high-level semantics for multimedia indexing and retrieval. In this paper, a new approach is proposed for detecting text in natural images inspired by the properties of the Human visual System (HVS). In particular, the detection is based upon the functionality of the OFF and ON center-surround cells of the HVS. Cells are combined at different scales to guide a both efficient and effective algorithm. Performance evaluation relies on the ICDAR 2011 Robust Reading Dataset.

关键词： Image edge detection visualization Retina Filtering Cells (biology) Text analysis Brightness

来源：评论

学校读者我要写书评

暂无评论

Scalable video coding using H.263

Scalable video coding using H.263

引用

Canadian Conference on electrical and computer engineering (CCECE)

作者： Yuen-Pang Ko S. Panchanathan Visual Computing and Communications Laboratory VCCL Department of Electrical and Computer Engineering University of Ottawa Ottawa ONT Canada Visual Computing and Communications Laboratory VCCLDepartment of Electrical and Computer Engineering University of Ottawa Ottawa ONT Canada

Scalable video compression is very useful for multimedia communications and other applications such as video browsing and interactive TV. In this paper, we have proposed a scalable algorithm for the H.263 coder which makes possible the generation of a multiple rate video stream from a single compressed H.263 video stream. The proposed algorithm has comparable performance at lower bit rates and a superior performance at higher bit rates.

关键词： Video coding Video compression Bit rate Videoconference Scalability Streaming media Transform coding Discrete cosine transforms Multimedia communication TV

来源：评论

学校读者我要写书评

暂无评论

Beyond Accuracy: Evaluating certainty of AI models for brain tumour detection

引用

computers in Biology and Medicine 2025年 193卷 110375-110375页

作者： Nisa, Zaib Un Bhatti, Sohail Masood Jaffar, Arfan Mazhar, Tehseen Shahzad, Tariq Ghadi, Yazeed Yasin Almogren, Ahmad Hamam, Habib Department of Computer Science and Information Technology The Superior University Lahore 54600 Pakistan Intelligent Data Visual Computing Research (IDVCR) Lahore 54600 Pakistan School of Computer Science National College of Business Administration and Economics Lahore 54000 Pakistan Department of Computer Science School Education Department Government of Punjab Layyah 31200 Pakistan Department of Computer Engineering COMSATS University Islamabad Sahiwal Campus Sahiwal 57000 Pakistan Department of Computer Science and Software Engineering Al Ain University Abu Dhabi 12555 United Arab Emirates Department of Computer Science College of Computer and Information Sciences King Saud University Riyadh 11633 Saudi Arabia School of Electrical Engineering University of Johannesburg Johannesburg 2006 South Africa International Institute of Technology and Management (IITG) Av. Grandes Ecoles Libreville BP 1989 Gabon College of Computer Science and Eng. (Invited Prof.) University of Ha'il Ha'il 55476 Saudi Arabia Faculty of Engineering Uni de Moncton Moncton NB E1A3E9 Canada

AbstractBrain tumors pose a severe health risk, often leading to fatal outcomes if not detected early. While most studies focus on improving classification accuracy, this research emphasizes prediction certainty, quantified through loss values. Traditional metrics like accuracy and precision do not capture confidence in predictions, which is critical for medical applications. This study establishes a correlation between lower loss values and higher prediction certainty, ensuring more reliable tumor classification. We evaluate CNN, ResNet50, XceptionNet, and a Proposed Model (VGG19 with customized classification layers) using accuracy, precision, recall, and loss. Results show that while accuracy remains comparable across models, the Proposed Model achieves the best performance (96.95 % accuracy, 0.087 loss), outperforming others in both precision and recall. These findings demonstrate that certainty-aware AI models are essential for reliable clinical decision-making. This study highlights the potential of AI to bridge the shortage of medical professionals by integrating reliable diagnostic tools in healthcare. AI-powered systems can enhance early detection and improve patient outcomes, reinforcing the need for certainty-driven AI adoption in medical imaging.

关键词： Brain tumour detection Deep learning Pre-trained models Confidence

来源：评论

学校读者我要写书评

暂无评论

Robust image-based landing control of a quadrotor on an unknown moving platform using circle features

Robust image-based landing control of a quadrotor on an unkn...

引用

2021 IEEE International Conference on Real-Time computing and Robotics, RCAR 2021

作者： Lin, Jie Wang, Yaonan Miao, Zhiqiang Zhong, Hang Nie, Jingmou Fierro, Rafael College of Electrical and Information Engineering Hunan University Changsha410082 China National Engineering Laboratory for Robot Visual Perception and Control Changsha China University of New Mexico MARHES Lab Department of Electrical and Computer Engineering AlbuquerqueNM87131-0001 United States

ISBN: (纸本)9781665436786

This paper addresses the robust image-based landing control problem for a landing system, including an underactuated quadrotor and an unknown moving platform. Firstly, an image kinematics is constructed by using an image moment based on a circle feature in the virtual image plane, which decouples the landing system into a translation and a rotation control module. Exploiting the funnel control techniques with barrier Lyapunov functions (BLFs), the proposed IBVS control law does not depend on relative height needed by IBVS-like approaches and the explicit knowledge of moving platforms. Besides, it guarantees feature errors with prescribed transient and steady-state behavior. Finally, A simulation study is presented to verify the efficacy of the proposed control scheme. © 2021 IEEE.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

User-interface for relative performance evaluation of compression techniques

User-interface for relative performance evaluation of compre...

引用

Canadian Conference on electrical and computer engineering (CCECE)

作者： S. Padhy O. Hage S. Panchanathan Visual Computing and Communications Laboratory Department of Electrical and Computer Engineering University of Ottawa Ottawa ONT Canada

Several techniques for video compression have appeared in literature namely JPEG, MPEG, H.263, wavelet, vector quantization, sub-bands, etc. In this paper, we present a user interface design which allows subjective comparison by simultaneous display of the encoded sequences (along with the original) at a variety of compression ratios in a synchronized manner. The proposed interface is extremely useful for relative performance evaluation of various compression techniques and can be easily extended to incorporate evaluation of new compression techniques.

关键词： Image coding Transform coding Video compression Redundancy Signal to noise ratio Discrete cosine transforms Decoding Vector quantization User interfaces PSNR

来源：评论

学校读者我要写书评

暂无评论

Estimation of articulated motion using kinematically constrained mixture densities

Estimation of articulated motion using kinematically constra...

引用

IEEE Nonrigid and Articulated Motion Workshop

作者： E.A. Hunter P.H. Kelly R.C. Jain Department of Electrical and Computer Engineering Visual Computing Laboratory University of California San Diego CA USA

We address the problem of articulated posture estimation in its general form. Namely, the recovery of full 3D articulated posture parameters from an uncontrolled scene. Stochastic modeling of low-level segmented image data is unified with models of object kinematic structure through a constrained mixture of observation processes. A modified expectation-maximization algorithm is proposed for this purpose. Early experiments qualitatively demonstrate the efficacy of our approach, and provide a context for integration for more sophisticated image cues.

关键词： Motion estimation Kinematics Layout State estimation Humans laboratories Stochastic processes Image segmentation Expectation-maximization algorithms Image sequences

来源：评论

学校读者我要写书评

暂无评论

Color correction for tone reproduction

Color correction for tone reproduction

引用

21st Color and Imaging Conference 2013: Color Science and engineering Systems, Technologies, and Applications, CIC 2013

作者： Pouli, Tania Artusi, Alessandro Banterle, Francesco Akyüz, Ahmet Oǧuz Seidel, Hans-Peter Reinhard, Erik Technicolor Research and Innovation France Department of Computer Science and Applied Mathematics University of Girona Spain Visual Computing Lab ISTI-CNR Italy Department of Computer Engineering Middle East Technical University Turkey Max-Plack-lnsitut für Informatik Germany

ISBN: (纸本)9781632660145

High dynamic range images require tone reproduction to match the range of values to the capabilities of the display. For computational reasons as well as absence of fully calibrated imagery, rudimentary color reproduction is often added as a post-processing step rather than integrated into the tone reproduction algorithm. However, in the general case this currently requires manual parameter tuning, although for some global tone reproduction operators, parameter settings can be inferred from the tone curve. We present a novel and fully automatic saturation correction technique, suitable for any tone reproduction operator, which exhibits better color reproduction than the state-of-the-art and we validate its comparative effectiveness through psychophysical experimentation.

关键词： Color

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：