检索结果-内蒙古大学图书馆

Autoencoder-Based Latent Block-Diagonal Representation for Subspace Clustering

IEEE Transactions on Cybernetics 2022年第6期52卷 5408-5418页

作者： Xu, Yesong Chen, Shuo Li, Jun Han, Zongyan Yang, Jian Nanjing University of Science and Technology PCA Laboratory Key Lab. of Intelligent Percept. and Syst. for High-Dimensional Information of Ministry of Education Nanjing210094 China Nanjing University of Science and Technology Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing210094 China RIKEN Center for Advanced Intelligence Project Tokyo103-0027 Japan Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China

Block-diagonal representation (BDR) is an effective subspace clustering method. The existing BDR methods usually obtain a self-expression coefficient matrix from the original features by a shallow linear model. However, the underlying structure of real-world data is often nonlinear, thus those methods cannot faithfully reflect the intrinsic relationship among samples. To address this problem, we propose a novel latent BDR (LBDR) model to perform the subspace clustering on a nonlinear structure, which jointly learns an autoencoder and a BDR matrix. The autoencoder, which consists of a nonlinear encoder and a linear decoder, plays an important role to learn features from the nonlinear samples. Meanwhile, the learned features are used as a new dictionary for a linear model with block-diagonal regularization, which can ensure good performances for spectral clustering. Moreover, we theoretically prove that the learned features are located in the linear space, thus ensuring the effectiveness of the linear model using self-expression. Extensive experiments on various real-world datasets verify the superiority of our LBDR over the state-of-the-art subspace clustering approaches. © 2013 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Integrating Dense LiDAR-Camera Road Detection Maps by a Multi-Modal CRF Model

引用

IEEE Transactions on Vehicular Technology 2019年第12期68卷 11635-11645页

作者： Gu, Shuo Zhang, Yigong Tang, Jinhui Yang, Jian Alvarez, Jose M. Kong, Hui PCA Lab Key Lab of Intelligent Percept. and Syst. for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security Sch. of Comp. Sci. and Engineering Nanjing Univ. of Sci. and Technol. Nanjing 210094 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing 210094 China

Road detection is an important task in autonomous navigation systems. In this paper, we propose a road detection method via a LiDAR-camera fusion strategy to exploit both the range and color information. The whole system consists of three parts. In the LiDAR based part, we transform the discrete 3D LiDAR point clouds to continuous 2D LiDAR range images and propose a distance-aware height-difference based scanning approach to get the road estimations quickly. In the camera based part, we apply a light-weight transfer learning based road segmentation network. In the LiDAR-camera fusion part, we transform the detection results from LiDAR and camera to dense and binary ones to solve the data imbalance problem and fuse them in a multi-modal conditional random field (MM-CRF) framework. Experiments show that the proposed MM-CRF fusion method can operate in real-time and achieve competitive performance compared with the state-of-the-art road detection algorithms on the KITTI-Road benchmark. © 1967-2012 IEEE.

关键词： KITTI LiDAR-camera fusion road detection

来源：评论

学校读者我要写书评

暂无评论

Texture image segmentation using Brushlet-domain hidden Markov models

Texture image segmentation using Brushlet-domain hidden Mark...

引用

MIPPR 2009 - Remote Sensing and GIS Data Processing and Other Applications: 6th International Symposium on Multispectral image Processing and Pattern Recognition

作者： Liu, Fang Yang, Kai Hao, Hongxia Hou, Biao Zhong, Hua School of Computer Science and Technology Xidian University Xi'an Shanxi 710071 China Intelligent Perception and Image Understanding Key Lab. of Ministry of Education of China Xi'an Shanxi 710071 China Intelligent Information Processing Laboratory Xidian University Xi'an Shanxi 710071 China

ISBN: (纸本)9780819478092

By researching the Brushlet domain coefficients of texture images, we found that the distribution of the magnitudes of Brushlet domain coefficients roughly meet rayleigh distribution. And there are correlations between Brushlet coefficients in adjacent scales. Therefore, Rayleigh Mixture Model (RMM) is used to characterize the statistics of the magnitudes of Brushlet coefficients. To capture the inter-scale persistence of Brushlet coefficients, a "four to four" models with markov property is adopted in this paper. On the basis, by combining with the multi-scale Bayesian segmentation method, we propose a multiscale Bayesian texture segmentation algorithm that is based on a Brushlet domain hidden Markov tree (BruHMT) model. The experiment results indicate that our method is feasible and effective. Especially for coarse texture, our method is superior than texture segmentation method using Wavelet domain hidden Markov tree (WHMT) model. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

An Improved Real-time Visual Tracking Method for Space Non-cooperate Target

An Improved Real-time Visual Tracking Method for Space Non-c...

引用

International Symposium on Optoelectronic Technology and Application 2016(OTA 2016)——Conf.6 Robot Sensing and Advanced Control

作者： Limin Zhang Feng Zhu Yingming Hao Shenyang institute of automation Chinese academy of sciences University of Chinese Academy of Sciences Key laboratory of optical-electronics information processing Chinese academy of science Key laboratory of image understanding and computer vision

In order to enable the non-cooperative rendezvous, capture, and removal of large space debris, robust and fast tracking of the non-cooperative target is needed. This paper proposes an algorithm of rea

关键词：

来源：评论

学校读者我要写书评

暂无评论

Topic Embedded Representation Enhanced Variational Wasserstein Autoencoder for Text Modeling 5

Topic Embedded Representation Enhanced Variational Wasserste...

引用

5th IEEE International Conference on Electronics Technology, ICET 2022

作者： Xiang, Zheng Liu, Xiaoming Yang, Guan Liu, Yang Zhongyuan University of Technology School of Computer Science Zhengzhou China Henan Key Laboratory on Public Opinion Intelligent Analysis Zhengzhou China Key Laboratory of text processing and image understanding Zhengzhou China Xidian University State Key Laboratory of Integrated Services Networks Xi'an China Shandong University Key Lab of Cryptologic Technology and Information Security Ministry of Education Xi'an China

ISBN: (纸本)9781665485081

Variational Autoencoder (VAE) is now popular in modeling and language generation tasks, which need to pay attention to the diversity of generation results. The existing models are insufficient in capturing the built-in relationships between topic representation and sequential words. At the same time, there is a massive contradiction between the commonly used simple Gaussian prior and the actual complex distribution of languages. To address the above problems, we introduce a hybrid Wasserstein Autoencoder (WAE) with Topic Embedded Representation (TER) for modeling. TER is obtained through an embedding-based topic model and can capture the dependencies and semantic similarities between topics and words. In this case, the learned latent variable has rich semantic knowledge with the help of TER and is easier to explain and control. Our experiments show that our method is competitive with other VAEs in modeling. © 2022 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Shape Matching under Affine Transformation Using Normalization and Multi-scale Area Integral Features

Shape Matching under Affine Transformation Using Normalizati...

引用

International Symposium on Optoelectronic Technology and Application 2016(OTA 2016)——Conf.6 Robot Sensing and Advanced Control

作者： Huiying Cai Feng Zhu Yingming Hao Rongrong Lu Shenyang institute of automation Chinese academy of sciences University of Chinese Academy of Sciences Key laboratory of optical-electronics information processing Chinese academy of science Key laboratory of image understanding and computer vision

Shape refers to the equivalence representation of objects obtained through projecting the objects onto the imaging planes. The projecting action can be fitted by some finite-dimensional transformation

ISBN: (纸本)9781510607729

关键词： Shape matching Orthogonal normalization Equivalent resample Multi-scale area integral features Affine transformation Area integral shape analysis edge pixel Shape normalization multi-scale

来源：评论

学校读者我要写书评

暂无评论

An improved SSD for small target detection 2021

An improved SSD for small target detection

引用

6th International Conference on Multimedia and image Processing, ICMIP 2021

作者： Li, Xiang Luo, Haibo Key Laboratory of Opt-Electronic Information Processing Chinese Academy of Sciences Shenyang110016 China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China The Key Laboratory of Image Understanding and Computer Vision Shenyang Liaoning110016 China

ISBN: (纸本)9781450389167

SSD is one of heuristic one-stage target detection approaches. Although it has got impressive results in general target detection, it still struggles in small-size object detection and precise location. In this paper, we proposed an improved SSD which forces on the small-size target detection. We include a shallow and high resolution feature into the hierarchical detection feature which are used for prediction. Then, we fuse the detection features (including the shallow and high resolution one) as a feature pyramid through some convolution layers and unsample operations to pass information from deep features to the shallow ones, aiming to enrich the semantic information of the shallow features. To make the network easier to converge, we add a L2 normalization to the bottom detection feature of the feature pyramid to make a norm balance between each pyramid feature. The experimental results on the VEDAI dataset show that the proposed method has obtained impressive progress than the original SSD for the small targets detection. © 2021 ACM.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Terahertz image Restoration Based on CycleGan 3

Unsupervised Terahertz Image Restoration Based on CycleGan

引用

3rd International Conference on Defence Technology, ICDT 2022

作者： Su, Zhipeng Zhang, Yixiong Qi, Feng Shi, Jianghong School of Informatics Xiamen University National Demonstrative Software School Xiamen361005 China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Opto-Electronic Information Process Shenyang110016 China Key Laboratory of Image Understanding and Computer Vision Shenyang110016 China

Terahertz (THz) is considered as one of the key technologies for sixth generation communications, military, medical imaging and industrial inspection. THz images are susceptible to degradation due to system noise and point spread functions during transmission. The existing deep learning methods use ground truth and input images for supervised training that can recover THz images very well. But it's difficult to obtain labeled THz data in practical application. In this paper, we propose an attentional adversarial cycle generation network for THz image restoration (CycleTHz) based on CycleGan to address this problem. The CycleTHz generates clean images firstly by an attention-guided generation network and then discriminates the quality of the generators by an attention discriminator. In addition, RGB color loss is used for image channels for constraint. To the best of our knowledge, this is the first THz dataset to be trained using an unsupervised approach. Extensive experiments show that the proposed method improves the PSNR and SSIM by 43.4% and 101.7% compared with CycleGan, which is a benchmark method for the unsupervised development in THz image restoration. The code is available at https://***/hellogry/UnsupervisedCycleTHz © Published under licence by IOP Publishing Ltd.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

The correction method of computation of heat flux over dome based on turbulence models

The correction method of computation of heat flux over dome ...

引用

International Symposium on Optoelectronic Technology and Application 2016(OTA 2016)——Conf.12 Infrared Technology and Application

作者： ZHANG Daijun LUO Haibo ZHANG Junchao ZHANG Xiangyue Shenyang Institute of Automation Chinese Academy of Science University of Chinese Academy of Science Key Laboratory of Optical-Electronics Information Processing Chinese Academy of Science Key Laboratory of Image Understanding and Computer Vision

Aerodynamic heating effect caused by high speed flight of optical guidance system will lead to optical dome fracture failure or thermal barrier effect, which results in the inefficiency of the optical

关键词：

来源：评论

学校读者我要写书评

暂无评论

Inference guided feature generation for generalized zero-shot learning

引用

Neurocomputing 2021年 430卷 150-158页

作者： Zongyan Han Zhenyong Fu Guangyu Li Jian Yang PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Jiangsu 210094 China

Generalized zero-shot learning suffers from an extreme data imbalance problem, that is, the training data only come from seen classes while no unseen class data are available. Recently, a number of feature generation methods based on generative adversarial networks (GAN) have been proposed to address this problem. Existing feature generation methods, however, have never considered the under-constrained problem, and thus could generate an unrestricted visual feature corresponding to no meaningful object class. In this paper, we propose to equip the feature generation framework with a parallel inference network that projects visual feature to the semantic descriptor space, constraining to avoid the generation of unrestricted visual features. The two-parallel-stream framework (1) enables our method, termed inference guided feature generation (Inf-FG), to mitigate the under-constrained problem and (2) makes our Inf-FG applicable to transductive ZSL. Our Inf-FG learns the feature generator and the inference network simultaneously by aligning the joint distribution of visual features and semantic descriptors from the feature generator and the joint distribution from the inference network. We evaluate our approach on four benchmark ZSL datasets, including AWA, CUB, SUN, and FLO, on which our method improves our baselines on generalized zero-shot learning.

关键词： Feature generation Generalized zero-shot learning image classification Transfer learning

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：