检索结果-内蒙古大学图书馆

BURST-LDA: A NEW TOPIC MODEL FOR DETECTING BURSTY TOPICS FROM STREAM TEXT

Journal of Electronics(China) 2014年第6期31卷 565-575页

作者： Qi Xiang Huang Yu Chen Ziyan Liu Xiaoyan Tian Jing Huang Tinglei Wang Hongqi Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences University of Chinese Academy of Sciences

Topic models such as Latent Dirichlet Allocation(LDA) have been successfully applied to many text mining tasks for extracting topics embedded in corpora. However, existing topic models generally cannot discover bursty topics that experience a sudden increase during a period of time. In this paper, we propose a new topic model named Burst-LDA, which simultaneously discovers topics and reveals their burstiness through explicitly modeling each topic's burst states with a first order Markov chain and using the chain to generate the topic proportion of documents in a Logistic Normal fashion. A Gibbs sampling algorithm is developed for the posterior inference of the proposed model. Experimental results on a news data set show our model can efficiently discover bursty topics, outperforming the state-of-the-art method.

关键词： Text mining Burst detection Topic model Graphical model Bayesian inference

来源：评论

学校读者我要写书评

暂无评论

NON-PARAMETRIC TOPIC MODEL FOR DISCOVERING GEOGRAPHICAL TOPIC VARIATIONS

引用

Journal of Electronics(China) 2014年第6期31卷 576-586页

作者： Qi Xiang Huang Yu Song Jun Huang Tinglei Wang Hongqi Fu Kun Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences University of Chinese Academy of Sciences

This paper presents a non-parametric topic model that captures not only the latent topics in text collections, but also how the topics change over space. Unlike other recent work that relies on either Gaussian assumptions or discretization of locations, here topics are associated with a distance dependent Chinese Restaurant Process(ddC RP), and for each document, the observed words are influenced by the document's GPS-tag. Our model allows both unbound number and flexible distribution of the geographical variations of the topics' content. We develop a Gibbs sampler for the proposal, and compare it with existing models on a real data set basis.

关键词： Text mining Topic model Geographical topics Bayesian non-parameter

来源：评论

学校读者我要写书评

暂无评论

Stabilization of time-delay Markovian jump systems via probability rate synthesis and state feedback 19

Stabilization of time-delay Markovian jump systems via proba...

引用

19th IFAC World Congress on International Federation of Automatic Control, IFAC 2014

作者： Ma, Shan Xiong, Junlin CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230026 China

ISBN: (纸本)9783902823625

This paper considers the stabilization problem for Markovian jump systems with time delays. Both the probability rate matrix and the state feedback control law are to be designed. A sufficient condition is established for such designs such that the resulting closed-loop Markovian jump system is stochastically stable. This condition is given in terms of a system of linear matrix inequalities with rank constraints, and can be solved using some existing algorithms. When the system has polytopic uncertainties, the robust stabilization problem is studied as well. Finally, a numerical example is given to show the validity of the proposed method. © IFAC.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

A novel synthetic aperture radar scattering model for sea surface with breaking waves

引用

Acta Oceanologica Sinica 2022年第4期41卷 138-145页

作者： Xiaochen Wang Yuxin Hu Bing Han Wei Tian Chunhua Zhang Aerospace Information Research Institute Chinese Academy of SciencesBeijing 100094China Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of SciencesBeijing 100190China The box51111 Beijing 100190China

In this study a novel synthetic aperture radar(SAR)scattering model for sea surface with breaking waves is *** with existing models,the proposed model considers an empirical relationship between wind speed and wave breaking scattering to present the contribution of wave ***,the scattering weight factor p,and wave breaking rate q,are performed to present the contribution of the quasi-specular scattering term,Bragg scattering term,and wave breaking scattering term to the total scattering from the sea *** explore the modeling accuracy of sea-surface scattering,a simulated normalized radar cross-section(NRCS)and measured NRCS are *** proposed model generated the simulated NRCS and a matching GF-3 dataset was used for the measured *** was revealed that the performance of the VV polarization of our model was much better than that of HH polarization,with a correlation of 0.91,bias of-0.14 dB,root mean square error(RMSE)of 1.26 dB,and scattering index(SI)*** addition,the novel model is explored and compared with the geophysical model of CMODs and satellite-measured NRCS from GF-3 SAR wave mode *** an incidence angle 40°–41°,the relationship between the NRCS and wind speed,relative wind direction is *** with the SAR-measured NRCS,the performance of VV polarization was much better than HH polarization,with a correlation of 0.99,bias of-0.25 dB,RMSE of 0.64 dB,and SI of-0.04.

关键词： synthetic aperture radar scattering model sea surface wave breaking

来源：评论

学校读者我要写书评

暂无评论

FAN: Frequency Aggregation Network for Real Image Super-Resolution 16th

FAN: Frequency Aggregation Network for Real Image Super-Reso...

引用

Workshops held at the 16th European Conference on Computer Vision, ECCV 2020

作者： Pang, Yingxue Li, Xin Jin, Xin Wu, Yaojun Liu, Jianzhao Liu, Sen Chen, Zhibo CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

ISBN: (纸本)9783030670696

Single image super-resolution (SISR) aims to recover the high-resolution (HR) image from its low-resolution (LR) input image. With the development of deep learning, SISR has achieved great progress. However, It is still a challenge to restore the real-world LR image with complicated authentic degradations. Therefore, we propose FAN, a frequency aggregation network, to address the real-world image super-resolu-tion problem. Specifically, we extract different frequencies of the LR image and pass them to a channel attention-grouped residual dense network (CA-GRDB) individually to output corresponding feature maps. And then aggregating these residual dense feature maps adaptively to recover the HR image with enhanced details and textures. We conduct extensive experiments quantitatively and qualitatively to verify that our FAN performs well on the real image super-resolution task of AIM 2020 challenge. According to the released final results, our team SR-IM achieves the fourth place on the X4 track with PSNR of 31.1735 and SSIM of 0.8728. © 2020, Springer Nature Switzerland AG.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

LIRA: Lifelong Image Restoration from Unknown Blended Distortions 16th

LIRA: Lifelong Image Restoration from Unknown Blended Distor...

引用

16th European Conference on Computer Vision, ECCV 2020

作者： Liu, Jianzhao Lin, Jianxin Li, Xin Zhou, Wei Liu, Sen Chen, Zhibo CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

ISBN: (纸本)9783030585228

Most existing image restoration networks are designed in a disposable way and catastrophically forget previously learned distortions when trained on a new distortion removal task. To alleviate this problem, we raise the novel lifelong image restoration problem for blended distortions. We first design a base fork-join model in which multiple pre-trained expert models specializing in individual distortion removal task work cooperatively and adaptively to handle blended distortions. When the input is degraded by a new distortion, inspired by adult neurogenesis in human memory system, we develop a neural growing strategy where the previously trained model can incorporate a new expert branch and continually accumulate new knowledge without interfering with learned knowledge. Experimental results show that the proposed approach can not only achieve state-of-the-art performance on blended distortions removal tasks in both PSNR/SSIM metrics, but also maintain old expertise while learning new restoration tasks. © 2020, Springer Nature Switzerland AG.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

CNN-BASED DEPTH MAP PREDICTION FOR FAST BLOCK PARTITIONING IN HEVC INTRA CODING

CNN-BASED DEPTH MAP PREDICTION FOR FAST BLOCK PARTITIONING I...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Feng, Aolin Gao, Changsheng Li, Li Liu, Dong Wu, Feng CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

ISBN: (纸本)9781665438643

High Efficiency Video Coding (HEVC) achieves significant improvement in compression efficiency by introducing quadtree-based block partition. However, in the HEVC reference software-HM, the optimal partition is found by a recursive rate-distortion optimization (RDO) process, which is computationally expensive and not friendly to hardware implementation. We propose a fast block partitioning algorithm using convolutional neural network (CNN) based depth map prediction for HEVC intra coding. We use the depth map to represent the block partition of a coding tree unit (CTU). Then, we design a CNN to predict the depth map for a CTU, and we construct a large-scale dataset to train the CNN. Through the depth map prediction, we obtain a block partitioning structure for the entire CTU, and then we could directly compress each coding unit, getting rid of the recursive RDO process for partitioning. Experimental results show that our proposed method reduces 65.55% encoding time of HM at the cost of 2.02% Bjøntegaard Delta rate (BD-rate) increase on the common test sequences. For 4K sequences, our method achieves 76.97% time saving with 2.89% BD-rate increase. © 2021 IEEE

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Learning Disentangled Feature Representation for Hybrid-Distorted Image Restoration 1

引用

16th European Conference on Computer Vision, ECCV 2020

作者： Li, Xin Jin, Xin Lin, Jianxin Liu, Sen Wu, Yaojun Yu, Tao Zhou, Wei Chen, Zhibo CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

ISBN: (数字)9783030585266

ISBN: (纸本)9783030585259

Hybrid-distorted image restoration (HD-IR) is dedicated to restore real distorted image that is degraded by multiple distortions. Existing HD-IR approaches usually ignore the inherent interference among hybrid distortions which compromises the restoration performance. To decompose such interference, we introduce the concept of Disentangled Feature Learning to achieve the feature-level divide-and-conquer of hybrid distortions. Specifically, we propose the feature disentanglement module (FDM) to distribute feature representations of different distortions into different channels by revising gain-control-based normalization. We also propose a feature aggregation module (FAM) with channel-wise attention to adaptively filter out the distortion representations and aggregate useful content information from different channels for the construction of raw image. The effectiveness of the proposed scheme is verified by visualizing the correlation matrix of features and channel responses of different distortions. Extensive experimental results also prove superior performance of our approach compared with the latest HD-IR schemes. © 2020, Springer Nature Switzerland AG.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

iWavePro: An improved framework for iWave++ 56

iWavePro: An improved framework for iWave++

引用

56th IEEE International Symposium on Circuits and systems, ISCAS 2023

作者： Xue, Dongmei Dong, Cunhui Ye, Fan Chen, Hang Kang, Bowei Li, Li Liu, Dong University of Science and Technology of China Cas Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Hefei230027 China

ISBN: (纸本)9781665451093

End-to-end image coding methods based on wavelet-like transform have made great progress in recent years. The most advanced one is iWave++, which adopts multi-level lifting schemes based on convolutional neural networks. However, iWave++ still has many unresolved problems. First, the independent entropy coding of each component makes it impossible to use the correlation between components better. Secondly, additive wavelet transform limits the nonlinear ability of learnable wavelet transform. Moreover, the offline training strategy makes the iWave++ unable to adjust according to the content. In this paper, we propose an improved framework for iWave++ called iWave-Pro. iWavePro is designed with several techniques to overcome the problems mentioned above. These techniques are the joint multi-component Gaussian mixture entropy coding, the affine wavelet-like transform, and the online training. Experimental results show that our method can save 10.73% bit rate compared with iWave++ at the same quality. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A decomposed dual-cross generative adversarial network for image rain removal 29

A decomposed dual-cross generative adversarial network for i...

引用

29th British Machine Vision Conference, BMVC 2018

作者： Jin, Xin Chen, Zhibo Lin, Jianxin Chen, Jiale Zhou, Wei Shan, Chaowei CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Rain removal is important for many computer vision applications, such as surveillance, autonomous car, etc. Traditionally, rain removal is regarded as a signal removal problem which usually causes over-smoothing by removing texture details in non-rain background regions. This paper considers the issue of rain removal from a completely different perspective, to treat rain removal as a signal decomposition problem. Specifically, we decompose the rain image into two components, namely non-rain background image and rain streaks image. Then, we introduce an adversarial training mechanism to synthesize non-rain background image and rain streaks image in a Dual-Cross manner, which makes the two adversarial branches interact with each other, archiving a win-win result ultimately. The proposed Decomposed Dual-Cross Generative Adversarial Network (DDC-GAN) shows significantly performance improvement compared with state-of-the-art methods on both synthetic and real-world images in terms of qualitative and quantitative measures (over 3dB gains in PSNR). © 2018. The copyright of this document resides with its authors.

关键词： Rain

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：