检索结果-内蒙古大学图书馆

Fgsd: A dataset for fine-grained ship detection in high resolution satellite images

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Chen, Kaiyan Wu, Ming Liu, Jiaming Zhang, Chuang Pattern Recognition and Intelligent System Lab Beijing University of Posts and Telecommunications Beijing China

Ship detection using high-resolution remote sensing images is an important task, which contribute to sea surface regulation. The complex background and special visual angle make ship detection relies in high quality datasets to a certain extent. However, there is few works on giving both precise classification and accurate location of ships in existing ship detection datasets. To further promote the research of ship detection, we introduced a new fine-grained ship detection datasets, which is named as FGSD. The dataset collects high-resolution remote sensing images that containing ship samples from multiple large ports around the world. Ship samples were fine categorized and annotated with both horizontal and rotating bounding boxes. To further detailed the information of the dataset, we put forward a new representation method of ships orientation. For future research, the dock as a new class was annotated in the dataset. Besides, rich information of images were provided in FGSD, including the source port, resolution and corresponding GoogleEarth's resolution level of each image. As far as we know, FGSD is the most comprehensive ship detection dataset currently and it'll be availab.e soon. Some baselines for FGSD are also provided in this paper. You are also welcome to contact us at ckyan@*** to get the dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Remote sensing

C-DLinkNet: Considering Multi-level semantic features for human parsing

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Lu, Yu Feng, Muyan Wu, Ming Zhang, Chuang Pattern Recognition and Intelligent System Lab Beijing University of Posts and Telecommunications Beijing China

Human parsing is an essential branch of semantic segmentation, which is a fine-grained semantic segmentation task to identify the constituent parts of human. The challenge of human parsing is to extract effective semantic features to resolve deformation and multi-scale variations. In this work, we proposed an end-to-end model called C-DLinkNet based on LinkNet, which contains a new module named Smooth Module to combine the multi-level features in Decoder part. C-DLinkNet is capable of producing competitive parsing performance compared with the state-of-the-art methods with smaller input sizes and no additional information, i.e., achiving mIoU=53.05 on the validation set of LIP dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantics

Histogram transform-based speaker identification

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Ma, Zhanyu Yu, Hong Pattern Recognition and Intelligent System Lab Beijing University of Posts and Telecommunications Beijing China

A novel text-independent speaker identification (SI) method is proposed. This method uses the Mel-frequency Cepstral coefficients (MFCCs) and the dynamic information among adjacent frames as feature sets to capture speaker’s characteristics. In order to utilize dynamic information, we design super-MFCCs features by cascading three neighboring MFCCs frames together. The probability density function (PDF) of these super-MFCCs features is estimated by the recently proposed histogram transform (HT) method, which generates more training data by random transforms to realize the histogram PDF estimation and recedes the commonly occurred discontinuity problem in multivariate histograms computing. Compared to the conventional PDF estimation methods, such as Gaussian mixture models, the HT model shows promising improvement in the SI performance. Copyright © 2018, The Authors. All rights reserved.

关键词： Gaussian distribution

Language identification with deep bottleneck features

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Ma, Zhanyu Yu, Hong Pattern Recognition and Intelligent System Lab Beijing University of Posts and Telecommunications Beijing China

In this paper we proposed an end-to-end short utterances speech language identification(SLD) approach based on a Long Short Term Memory (LSTM) neural network which is special suitable for SLD application in intelligent vehicles. Features used for LSTM learning are generated by a transfer learning method. Bottle-neck features of a deep neural network (DNN) which are trained for mandarin acoustic-phonetic classification are used for LSTM training. In order to improve the SLD accuracy of short utterances a phase vocoder based time-scale modification(TSM) method is used to reduce and increase speech rated of the test utterance. By splicing the normal, speech rate reduced and increased utterances, we can extend length of test utterances so as to improved improved the performance of the SLD system. The experimental results on AP17-OLR database shows that the proposed methods can improve the performance of SLD, especially on short utterance with 1s and 3s durations. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks

TA4REC: Recurrent Neural Networks with Time Attention Factors for Session-based Recommendations

学校读者我要写书评

暂无评论

TA4REC: Recurrent Neural Networks with Time Attention Factor...

International Joint Conference on Neural Networks

作者： Yu Sun Peize Zhao Honggang Zhang Pattern Recognition and Intelligent System lab Beijing University of Posts and Telecommunications Beijing China

Recommender systems show increasingly importance with the development of E-commerce, news and multimedia applications. Traditional recommendation algorithms such as collab.rative-filtering-based methods and graph-based methods mainly use items' original attributes and relationships between items and users, ignoring items' chronological order in browsing sessions. In recent years, RNN-based methods show their superiority when dealing with the sequential data, and some modified RNN models have been proposed. However, these RNN models only use the sequence order of items and neglect items' browsing time information. It is widely accepted that users tend to spend more time on their interested items, and these interested items are always closely related to users' current target. Based on the above view, items' browsing time is an important feature in recommendations. In this paper, we propose a modified RNN-based recommender system called TA4Rec, which can recommend the probable Item that may be clicked in the next moment. Our main contribution is to introduce a method to calculate the time-attention factors from browsing items' duration time and add time-attention factors to the RNN-based model. We conduct experiments on RecSys Challenge 2015 dataset and the result shows that TA4Rec model has gained obvious improvement on session-based recommendations than the classic session-based recommender method.

关键词： Logic gates Training Recommender systems Standards Recurrent neural networks Logistics

Low complexity reconfigurable architecture for the 5/3 and 9/7 discrete wavelet transform

学校读者我要写书评

暂无评论

Journal of systems Engineering and Electronics 2006年第2期17卷 303-308页

作者： Xiong Cheng yi Tian Jinwen Liu Jian Coll. of Electronic Information Engineering South Center Univ. for Nationalities Wuhan 430074 P.R. China Inst. of Pattern Recognition & Artificial Intelligence Key Lab. of Education Ministry for Image Processing and Intelligent Control Huazhong Univ. of Science & Technology Wuhan 430074 P.R. China

Efficient reconfigurable VLSI architecture for 1-D 5/3 and 9/7 wavelet transforms adopted in JPEG2000 proposal, based on lifting scheme is proposed. The embedded decimation technique based on fold and time multiplexing, as well as embedded boundary data extension technique, is adopted to optimize the design of the architecture. These reduce significantly the required numbers of the multipliers, adders and registers, as well as the amount of accessing external memory, and lead to decrease efficiently the hardware cost and power consumption of the design. The architecture is designed to generate an output per clock cycle, and the detailed component and the approximation of the input signal are availab.e alternately. Experimental simulation and comparison results are presented, which demonstrate that the proposed architecture has lower hardware complexity, thus it is adapted for embedded applications. The presented architecture is simple, regular and scalab.e, and well suited for VLSI implementation.

关键词： VLSI discrete wavelet transform lifting scheme embedded decimation reeonfigurable.

Activation force-based air pollution observation station clustering

学校读者我要写书评

暂无评论

Activation force-based air pollution observation station clu...

International Conference on Quality of Service in Heterogeneous Wired/Wireless Networks (QSHINE)

作者： Di Huang Ni Zhang Hong Yu Huanyu Zhou Zhanyu Ma Weisong Hu Jun Guo Pattern Recognition and Intelligent System Lab. Beijing University of Posts and Telecommunications Beijing China NEC Labs China Beijing China

With huge amount of observed air quality and components data, it is of great challenge to analyze and trace the pollutant diffusion path. Partitioning the air pollution sources (air quality observation stations) into subnetworks will help a lot in tracing the air pollution diffusion path. Conventional air pollution sources clustering methods, which are based on geography or pollutant levels, present weak correlation with pollution transmission links. In order to overcome such problem, a method of air pollution sources clustering via activation force (AF) model is introduced in this paper. We model the connections of the pollution sources by AF so that the relationship among the observation stations and the coincidence of the transmission links can be modeled effectively. With the affinity matrix obtained via AF modeling, we conduct clustering of the air pollution sources via modularity measurement. Compared to K-means clustering method purely, which is based on the air quality index of pollutants, the proposed approach shows several advantages in air pollution network clustering.

关键词： Air pollution Geography Atmospheric modeling Atmospheric measurements Particle measurements Pollution measurement

A FOREGROUND SEGMENTATION METHOD FOR MOBILE IMAGE RETRIEVAL system

学校读者我要写书评

暂无评论

A FOREGROUND SEGMENTATION METHOD FOR MOBILE IMAGE RETRIEVAL ...

The 3rd IEEE International Conference on Network Infrastructure and Digital Content (2012年第三届IEEE网络基础设施与数字内容国际会议(IEEE IC-NIDC2012))

作者： Yuhan Liu Honggang Zhang Lunshao Chai Yonggang Qi Pattern Recognition and Intelligent System Lab Beijing University of Posts and Telecommunications Beijing 100876 China

Content-based image retrieval (CBIR) is an application of computer vision techniques to the image retrieval *** is,the problem of searching for digital images in large *** this paper,we apply an image segmentation technique to an image retrieval system which is designed for the use on mobile *** an image captured by the mobile devices,edge detection and region merging mechanisms are used in this segmentation technique to extract the ROI from a complex background *** proposed method automatically merges the regions that are initially segmented by mean shift segmentation,and then effectively extracts the object contour by the lab.led regions as either background or *** no users interaction,the experimental results show the method is more effective than other automatic segmentation methods.

关键词： Image segmentation Mobile image retrieval Mean shift Region merging

RESEARCH ON WEB FILTERING TECHNOLOGY BASED ON THE DUAL FEATURE SELECTION

学校读者我要写书评

暂无评论

RESEARCH ON WEB FILTERING TECHNOLOGY BASED ON THE DUAL FEATU...

The 3rd IEEE International Conference on Network Infrastructure and Digital Content (2012年第三届IEEE网络基础设施与数字内容国际会议(IEEE IC-NIDC2012))

作者： Bin Zhang Miao Xu Minli Wu Pattern Recognition and Intelligent System Lab Beijing University of Posts and Telecommunications Beijing 100876 China

In the topic search system,some of web pages got by crawling are inconsistent with user *** this situation,this paper had a research on content-based web filtering *** paper proposed a dual feature selection method based on the CHI statistical method and N-gram,and then made binary text classification by SVM in order to achieve Web *** experiments showed that the proposed web filtering method has better results.

关键词： Web filtering Feature selection CHI statistical method TF-IDF