• Complex
  • Title
  • Author
  • Keyword
  • Abstract
  • Scholars
Search
Sort by:
Default
  • Default
  • Title
  • Year
  • WOS Cited Count
  • Impact factor
  • Ascending
  • Descending
< Page ,Total 249 >
Hardware Implementation of Reconfigurable Separable Convolution EI CPCI-S Scopus
会议论文 | 2018 , 232-237 | 17th IEEE-Computer-Society Annual Symposium on VLSI (ISVLSI)
Abstract&Keyword Cite

Abstract :

Convolution operations occupy large amounts of computation resource in convolutional neural networks (CNNs). Separable convolution can greatly reduce computational complexity. Unfortunately, most trained kernels in CNNs are not separable. In this paper, least squares approach is applied to decompose a non-separable 2D kernel into two 1D kernels. A reconfigurable convolutional architecture is proposed to convert a 2D convolution into 1D convolution in convolutional layers. Moreover, a denoising CNN is mapped to the proposed convolution architecture. Experimental results show that the hardware architecture can restore a 1280x 720 image in 0.83s, which achieves an 8.4x speed-up over GPU implementation. Verification experiments demonstrate that our approach and hardware architecture can drastically reduce the computational complexity in convolution operations without sacrificing the performance.

Keyword :

hardware implementation reconfigurable architecture separable convolution convolutional neural networks

Cite:

Copy from the list or Export to your reference management。

GB/T 7714 Rao, Lei , Zhang, Bin , Zhao, Jizhong . Hardware Implementation of Reconfigurable Separable Convolution [C] . 2018 : 232-237 .
MLA Rao, Lei 等. "Hardware Implementation of Reconfigurable Separable Convolution" . (2018) : 232-237 .
APA Rao, Lei , Zhang, Bin , Zhao, Jizhong . Hardware Implementation of Reconfigurable Separable Convolution . (2018) : 232-237 .
Export to NoteExpress RIS BibTex
Deep Feature Aggregation and Image Re-ranking with Heat Diffusion for Image Retrieval EI Scopus
期刊论文 | 2018 | IEEE Transactions on Multimedia
Abstract&Keyword Cite

Abstract :

Image retrieval based on deep convolutional features has demonstrated state-of-the-art performance in popular benchmarks. In this paper, we present a unified solution to address deep convolutional feature aggregation and image re-ranking by simulating the dynamics of heat diffusion. A distinctive problem in image retrieval is that repetitive or bursty features tend to dominate final image representations, resulting in representations less distinguishable. We show that by considering each deep feature as a heat source, our unsupervised aggregation method is able to avoid over-representation of bursty features. We additionally provide a practical solution for the proposed aggregation method and further show the efficiency of our method in experimental evaluation. Inspired by the aforementioned deep feature aggregation method, we also propose a method to re-rank a number of top ranked images for a given query image by considering the query as the heat source. Finally, we extensively evaluate the proposed approach with pre-trained and fine-tuned deep networks on common public benchmarks and show superior performance compared to previous work. IEEE

Keyword :

Aggregation methods Experimental evaluation Feature aggregation Heat equation Image representations Practical solutions Re-ranking State-of-the-art performance

Cite:

Copy from the list or Export to your reference management。

GB/T 7714 Pang, Shanmin , Ma, Jin , Xue, Jianru et al. Deep Feature Aggregation and Image Re-ranking with Heat Diffusion for Image Retrieval [J]. | IEEE Transactions on Multimedia , 2018 .
MLA Pang, Shanmin et al. "Deep Feature Aggregation and Image Re-ranking with Heat Diffusion for Image Retrieval" . | IEEE Transactions on Multimedia (2018) .
APA Pang, Shanmin , Ma, Jin , Xue, Jianru , Zhu, Jihua , Ordonez, Vicente . Deep Feature Aggregation and Image Re-ranking with Heat Diffusion for Image Retrieval . | IEEE Transactions on Multimedia , 2018 .
Export to NoteExpress RIS BibTex
Simultaneous Merging Multiple Grid Maps Using the Robust Motion Averaging EI Scopus
期刊论文 | 2018 | Journal of Intelligent and Robotic Systems: Theory and Applications
Abstract&Keyword Cite

Abstract :

Mapping in the GPS-denied environment is an important and challenging task in the field of robotics. In the large environment, mapping can be significantly accelerated by multiple robots exploring different parts of the environment. Accordingly, a key problem is how to integrate these local maps built by different robots into a single global map. In this paper, we propose an approach for simultaneous merging of multiple grid maps by the robust motion averaging. The main idea of this approach is to recover all global motions for map merging from a set of relative motions. Therefore, it firstly adopts the pair-wise map merging method to estimate relative motions for grid map pairs. To obtain as many reliable relative motions as possible, a graph-based sampling scheme is utilized to efficiently remove unreliable relative motions obtained from the pair-wise map merging. Subsequently, the accurate global motions can be recovered from the set of reliable relative motions by the motion averaging. Experimental results carried on real robot data sets demonstrate that the proposed approach can achieve simultaneous merging of multiple grid maps with good performances. © 2018, Springer Nature B.V.

Keyword :

Global motion Grid map Iterative closet point Motion averaging Multi-robot systems Multiple robot Relative motion Sampling schemes

Cite:

Copy from the list or Export to your reference management。

GB/T 7714 Jiang, Zutao , Zhu, Jihua , Li, Yaochen et al. Simultaneous Merging Multiple Grid Maps Using the Robust Motion Averaging [J]. | Journal of Intelligent and Robotic Systems: Theory and Applications , 2018 .
MLA Jiang, Zutao et al. "Simultaneous Merging Multiple Grid Maps Using the Robust Motion Averaging" . | Journal of Intelligent and Robotic Systems: Theory and Applications (2018) .
APA Jiang, Zutao , Zhu, Jihua , Li, Yaochen , Wang, Jun , Li, Zhongyu , Lu, Huimin . Simultaneous Merging Multiple Grid Maps Using the Robust Motion Averaging . | Journal of Intelligent and Robotic Systems: Theory and Applications , 2018 .
Export to NoteExpress RIS BibTex
A new identification method of the market downturns in Chinese A-shares using liquidity network EI Scopus
会议论文 | 2018 , 195-200 | 3rd IEEE International Conference on Big Data Analysis, ICBDA 2018
Abstract&Keyword Cite

Abstract :

With an increasing interest in big datasets, there exists a rise in the application of complex networks to financial big data. Many literatures have indicated that liquidity plays a crucial part in interpreting the fluctuation in stock returns. However, most researchers focus on relationship between the liquidity of individual stock and returns but seldom investigate market-wide liquidity. In this paper, we propose a way based on a dynamic stock liquidity network to analyze the change of market-wide liquidity. Then two indexes are built to quantify the daily change of stock liquidity correlation network, which are calculated from the maximum connected subgraph. When comparing our indexes with market index in Chinese A-shares, we empirically find that they are sensitive to market downturns and can recognize the tendency of stock market. Furthermore, the stock market investment behavior in Chinese A-shares tends to keep the same with previous investment behavior during market upturns and it differs apparently when market downturns. © 2018 IEEE.

Keyword :

Connected Subgraph Correlation network Daily change Identification method Market downturn Stock returns

Cite:

Copy from the list or Export to your reference management。

GB/T 7714 Li, Qunce , Peng, Qinke , Chai, Ling et al. A new identification method of the market downturns in Chinese A-shares using liquidity network [C] . 2018 : 195-200 .
MLA Li, Qunce et al. "A new identification method of the market downturns in Chinese A-shares using liquidity network" . (2018) : 195-200 .
APA Li, Qunce , Peng, Qinke , Chai, Ling , Owais, Muhammad . A new identification method of the market downturns in Chinese A-shares using liquidity network . (2018) : 195-200 .
Export to NoteExpress RIS BibTex
Research Progress on Emotional Computation Technology Based on Semantic Analysis EI Scopus CSCD PKU
期刊论文 | 2018 , 29 (8) , 2397-2426 | Ruan Jian Xue Bao/Journal of Software
Abstract&Keyword Cite

Abstract :

With the development of machine learning and application of big data, semantic-based emotional computing and analysis technology plays a significant role in the research on human perception, attention, memory, decision-making, and social communication. It affects not only the development in artificial intelligence technology, but also human/machine interaction and smart robot technology, therefore drawing widespread interest from the academic and business communities. In this paper, based on the definition of affection and the analysis of more than 90 emotional models, six vital problems and challenges in emotional computing are summarized as follows: where is emotion stem from and how to represent their essential features; how to analyze and compute the emotion under the multi-model environment; how to measure the influence of external factors on the process of emotional evolution; how to measure individual emotion by various of personalized characteristic; how to measure the crowed psychology and emotion and to analyze the mechanism about propagation dynamics; and how to express the subtle emotion and optimize algorithms. Meanwhile, some theoretical research, technical analysis and practical application are brought up to introduce the current work progress and trend for these technical challenges in order to provide new research clues and directions for further study in the field of the semantic-based emotional computing. © Copyright 2018, Institute of Software, the Chinese Academy of Sciences. All rights reserved.

Keyword :

Artificial emotions Artificial intelligence technologies Crowd emotion Emotional semantic Evolutionary computing Multi-model environments Problems and challenges Social communications

Cite:

Copy from the list or Export to your reference management。

GB/T 7714 Rao, Yuan , Wu, Lian-Wei , Wang, Yi-Ming et al. Research Progress on Emotional Computation Technology Based on Semantic Analysis [J]. | Ruan Jian Xue Bao/Journal of Software , 2018 , 29 (8) : 2397-2426 .
MLA Rao, Yuan et al. "Research Progress on Emotional Computation Technology Based on Semantic Analysis" . | Ruan Jian Xue Bao/Journal of Software 29 . 8 (2018) : 2397-2426 .
APA Rao, Yuan , Wu, Lian-Wei , Wang, Yi-Ming , Feng, Cong . Research Progress on Emotional Computation Technology Based on Semantic Analysis . | Ruan Jian Xue Bao/Journal of Software , 2018 , 29 (8) , 2397-2426 .
Export to NoteExpress RIS BibTex
The design and implementation of supercapacitor charging device and monitor system for electrical trams EI Scopus
会议论文 | 2018 , 5893-5897 | 30th Chinese Control and Decision Conference, CCDC 2018
Abstract&Keyword Cite

Abstract :

The requirements of power supply system for supercapacitor-based non-contact trams are quite different from those of the conventional catenary power supply system, especially in terms of the charging rate and system stability. This article proposes an improved super-capacitor charging system and user-friendly UCOS-II based real-time monitoring system to improve the system performance in terms of convenience, stability and less equipment costs. © 2018 IEEE.

Cite:

Copy from the list or Export to your reference management。

GB/T 7714 Du, Yudong , Zhang, Aimin , Zhang, Yupei . The design and implementation of supercapacitor charging device and monitor system for electrical trams [C] . 2018 : 5893-5897 .
MLA Du, Yudong et al. "The design and implementation of supercapacitor charging device and monitor system for electrical trams" . (2018) : 5893-5897 .
APA Du, Yudong , Zhang, Aimin , Zhang, Yupei . The design and implementation of supercapacitor charging device and monitor system for electrical trams . (2018) : 5893-5897 .
Export to NoteExpress RIS BibTex
A bidirectional information aggregation architecture for scene text detection EI Scopus
会议论文 | 2018 , 91-96 | 13th IAPR International Workshop on Document Analysis Systems, DAS 2018
Abstract&Keyword Cite

Abstract :

TextBoxes[1] is one of the most advanced text detection method in both aspects of accuracy and efficiency, but it is still not very sensitive to the small text in natural scenes and often can not localize text regions precisely. To tackle these problems, we first present a Bidirectional Information Aggregation (BIA) architecture by effectively aggregating multi-scale feature maps to enhance local details and strengthen context information, making the detector not only work reliably on multi-scale text, especially the small text, but also predict more precise boxes for texts. This architecture also results in a single classifier network, which allows our model to be trained much faster and easily with better generalization power. Then, we propose to use multiple symmetrical feature maps for feature extraction in the test stages for further improving the performance on the small text. To further promote precise predicting boxes, we present a statistical grouping method that operates on the training set bounding boxes to generate aspect ratios for default boxes. Finally, our model not only outperforms the TextBoxes without much time overhead, but also provides promising performance compared to the recent state-of-theart methods on the ICDAR 2011 and 2013 database. © 2018 IEEE.

Keyword :

Context information Feature map Information aggregation Multi-scale features Natural scenes Text detection Time overheads Training sets

Cite:

Copy from the list or Export to your reference management。

GB/T 7714 Li, Xiaoyu , Song, Yonghong , Zhang, Yuanlin . A bidirectional information aggregation architecture for scene text detection [C] . 2018 : 91-96 .
MLA Li, Xiaoyu et al. "A bidirectional information aggregation architecture for scene text detection" . (2018) : 91-96 .
APA Li, Xiaoyu , Song, Yonghong , Zhang, Yuanlin . A bidirectional information aggregation architecture for scene text detection . (2018) : 91-96 .
Export to NoteExpress RIS BibTex
Enhancing Outlier Detection by an Outlier Indicator EI Scopus
会议论文 | 2018 , 10934 LNAI , 393-405 | 14th International Conference on Machine Learning and Data Mining in Pattern Recognition, MLDM 2018
Abstract&Keyword Cite

Abstract :

Outlier detection is an important task in data mining and has high practical value in numerous applications such as astronomical observation, text detection, fraud detection and so on. At present, a large number of popular outlier detection algorithms are available, including distribution-based, distance-based, density-based, and clustering-based approaches and so on. However, traditional outlier detection algorithms face some challenges. For one example, most distance-based and density-based outlier detection methods are based on k-nearest neighbors and therefore, are very sensitive to the value of k. For another example, some methods can only detect global outliers, but fail to detect local outliers. Last but not the least, most outlier detection algorithms do not accurately distinguish between boundary points and outliers. To partially solve these problems, in this paper, we propose to augment some boundary indicators to classical outlier detection algorithms. Experiments performed on both synthetic and real data sets demonstrate the efficacy of enhanced outlier detection algorithms. © 2018, Springer International Publishing AG, part of Springer Nature.

Keyword :

Astronomical observation Boundary detection Boundary points Distance based outlier detection K-nearest neighbors Outlier Detection Outlier detection algorithm Synthetic and real data

Cite:

Copy from the list or Export to your reference management。

GB/T 7714 Li, Xiaqiong , Wang, Xiaochun , Wang, Xia Li . Enhancing Outlier Detection by an Outlier Indicator [C] . 2018 : 393-405 .
MLA Li, Xiaqiong et al. "Enhancing Outlier Detection by an Outlier Indicator" . (2018) : 393-405 .
APA Li, Xiaqiong , Wang, Xiaochun , Wang, Xia Li . Enhancing Outlier Detection by an Outlier Indicator . (2018) : 393-405 .
Export to NoteExpress RIS BibTex
Research progress of knowledge graph based on knowledge base embedding EI Scopus
会议论文 | 2018 , 902 , 176-191 | 4th International Conference of Pioneer Computer Scientists, Engineers and Educators, ICPCSEE 2018
Abstract&Keyword Cite

Abstract :

The knowledge Graph (KGs) is a valuable tool and useful resource to describe the entities and their relationships in various natural language processing tasks. Especially, the insufficient semantic of entities and relationship in text limited the efficiency and accuracy of knowledge representation. With the increasing of knowledge base resources, many scholars began to study the knowledge graph’s construction technology based on knowledge base embedding. The basic idea is that the knowledge graph will be treated as a recursive process. Through utilizing the knowledge base’s resources and the semantic representation of text characteristic, we can extend the new features that improve learning performance and knowledge graph completeness. In this paper, we give a general overview of knowledge graph’s construction research based on knowledge embedding, including knowledge representation, knowledge embedding and so on. Then we summarize the challenge for the knowledge graph and the future development trend. © Springer Nature Singapore Pte Ltd. 2018.

Keyword :

Construction research Construction technologies Development trends Knowledge embedding Knowledge graphs Learning performance Recursive process Semantic representation

Cite:

Copy from the list or Export to your reference management。

GB/T 7714 Caifang, Tang , Yuan, Rao , Hualei, Yu et al. Research progress of knowledge graph based on knowledge base embedding [C] . 2018 : 176-191 .
MLA Caifang, Tang et al. "Research progress of knowledge graph based on knowledge base embedding" . (2018) : 176-191 .
APA Caifang, Tang , Yuan, Rao , Hualei, Yu , Jiamin, Cheng . Research progress of knowledge graph based on knowledge base embedding . (2018) : 176-191 .
Export to NoteExpress RIS BibTex
A high energy physical metadata directory structure based on RAMCloud EI Scopus
会议论文 | 2018 , 2018-January , 301-304 | 14th Web Information Systems and Applications Conference, WISA 2017
Abstract&Keyword Cite

Abstract :

In recent years, with the large-scale growth of the high-energy physics experimental data, the performance of metadata retrieval based on disk storage has been gradually reduced, which can not meet the retrieval performance requirements of EB-level high-energy physics experimental metadata. To solve this problem, a method of converting traditional directory structure storage into RAMCloud storage is proposed. The core idea of this method is to use Key-Value non-relational database to re-design the traditional directory tree, separate directory structure and directory node content, and add a secondary index for parent directory, which can give full play to Key-Value retrieval and memory storage advantages, improve search efficiency. Through the implementation of the test, showed that the method has a better performance. Compared to the storage based on Mysql, the retrieval time drops significantly in the case of increased data. © 2017 IEEE.

Keyword :

Directory structure Directory trees Kay-Value Non-Relational Databases RAMCloud Retrieval performance Retrieval time Search efficiency

Cite:

Copy from the list or Export to your reference management。

GB/T 7714 Hou, Zhiqi , Hou, Di , Qi, Yong . A high energy physical metadata directory structure based on RAMCloud [C] . 2018 : 301-304 .
MLA Hou, Zhiqi et al. "A high energy physical metadata directory structure based on RAMCloud" . (2018) : 301-304 .
APA Hou, Zhiqi , Hou, Di , Qi, Yong . A high energy physical metadata directory structure based on RAMCloud . (2018) : 301-304 .
Export to NoteExpress RIS BibTex
10| 20| 50 per page
< Page ,Total 249 >

Export

Results:

Selected

to

Format:
FAQ| About| Online/Total:3973/65801331
Address:XI'AN JIAOTONG UNIVERSITY LIBRARY(No.28, Xianning West Road, Xi'an, Shaanxi Post Code:710049) Contact Us:029-82667865
Copyright:XI'AN JIAOTONG UNIVERSITY LIBRARY Technical Support:Beijing Aegean Software Co., Ltd.