Author image not provided
 Ronghua Liang

Authors:
Add personal information
  Affiliation history
Bibliometrics: publication history
Average citations per article0.72
Citation Count23
Publication count32
Publication years2003-2017
Available for download2
Average downloads per article151.50
Downloads (cumulative)303
Downloads (12 Months)173
Downloads (6 Weeks)15
SEARCH
ROLE
Arrow RightAuthor only


AUTHOR'S COLLEAGUES
See all colleagues of this author

SUBJECT AREAS
See all subject areas




BOOKMARK & SHARE


33 results found Export Results: bibtexendnoteacmrefcsv

Result 1 – 20 of 33
Result page: 1 2

Sort by:

1
December 2017 Neurocomputing: Volume 269 Issue C, December 2017
Publisher: Elsevier Science Publishers B. V.
Bibliometrics:
Citation Count: 0

Image inpainting restores lost or deteriorated parts of images according to the information of known regions. Criminisi has proposed an effective exemplar-based inpainting method, which has the advantages of both texture synthesis and diffusion-based inpainting. Yet, it has its own flaws of fast priority dropping and visual inconsistency. In this ...
Keywords: Image inpainting, Fast Fourier transform, Exemplar-based, Patch matching

2 published by ACM
October 2017 ACM Transactions on Intelligent Systems and Technology (TIST) - Regular Papers: Volume 9 Issue 2, January 2018
Publisher: ACM
Bibliometrics:
Citation Count: 1
Downloads (6 Weeks): 13,   Downloads (12 Months): 144,   Downloads (Overall): 144

Full text available: PDFPDF
Rapid advancement of social media tremendously facilitates and accelerates the information diffusion among users around the world. How and to what extent will the information on social media achieve widespread diffusion across the world? How can we quantify the interaction between users from different geolocations in the diffusion process? How ...
Keywords: Spatio-temporal visualization, information diffusion, social media visualization

3
June 2017 International Journal of Parallel Programming: Volume 45 Issue 3, June 2017
Publisher: Kluwer Academic Publishers
Bibliometrics:
Citation Count: 0

$$l_1$$l1-minimization ($$l_1$$l1-min) algorithms for the $$l_1$$l1-min problem have been widely developed. For most $$l_1$$l1-min algorithms, their main components include dense matrix-vector multiplications such as Ax and $$A^Tx$$ATx, and vector operations. We propose a novel warp-based implementation of the matrix-vector multiplication (Ax) on the graphics processing unit (GPU), called the GEMV ...
Keywords: Matrix-vector multiplication, Augmented Lagrangian multiplier method, $$l_1$$l1-minimization, Fast iterative shrinkage-thresholding algorithm, GPU

4
November 2016 IEEE Transactions on Multimedia: Volume 18 Issue 11, November 2016
Publisher: IEEE Press
Bibliometrics:
Citation Count: 1

We introduce a visual analytics method to analyze eye-tracking data and saliency models for dynamic stimuli, such as video or animated graphics. The focus lies on the analysis of the different performance of saliency models in contrast to human observers to identify trends in the general viewing behavior, including time ...

5 published by ACM
October 2016 ACM Transactions on Parallel Computing (TOPC): Volume 3 Issue 3, December 2016
Publisher: ACM
Bibliometrics:
Citation Count: 0
Downloads (6 Weeks): 2,   Downloads (12 Months): 29,   Downloads (Overall): 159

Full text available: PDFPDF
The preconditioned conjugate gradient (PCG) algorithm is a well-known iterative method for solving sparse linear systems in scientific computations. GPU-accelerated PCG algorithms for large-sized problems have attracted considerable attention recently. However, on a specific multi-GPU platform, producing a highly parallel PCG implementation for any large-sized problem requires significant time because ...
Keywords: Optimization model, multiple GPUs, preconditioned conjugate gradient, sparse matrix-vector multiplication, CUDA

6
February 2016 AAAI'16: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence
Publisher: AAAI Press
Bibliometrics:
Citation Count: 0

Ranking is an important way of retrieving authoritative papers from a large scientific literature database. Current state-of-the-art exploits the flat structure of the heterogeneous academic network to achieve a better ranking of scientific articles, however, ignores the multinomial nature of the multidimensional relationships between different types of academic entities. This ...

7
February 2016 Information Sciences—Informatics and Computer Science, Intelligent Systems, Applications: An International Journal: Volume 330 Issue C, February 2016
Publisher: Elsevier Science Inc.
Bibliometrics:
Citation Count: 0

High angular resolution diffusion imaging (HARDI) is an effective method for characterizing complex neural fiber paths in the human brain. However, visualizing and analyzing the fibers is often challenging because of the complexity of the fiber orientation distribution function used to describe the crossing, kissing, and fanning fibers. In this ...
Keywords: Probabilistic tractography, 3D ellipsoidal glyghs, Pixel bar, Fiber bundle classification

8
November 2015 Information Sciences—Informatics and Computer Science, Intelligent Systems, Applications: An International Journal: Volume 320 Issue C, November 2015
Publisher: Elsevier Science Inc.
Bibliometrics:
Citation Count: 3

Due to the difficulties associated with the collection of 3D samples, 3D face recognition technologies often have to work with smaller than desirable sample sizes. With the aim of enlarging the training number for each subject, we divide each training image into several patches. However, this immediately introduces two further ...
Keywords: Single training sample per person, 3D face recognition, Bayesian learning, Depth image

9
July 2015 IJCAI'15: Proceedings of the 24th International Conference on Artificial Intelligence
Publisher: AAAI Press
Bibliometrics:
Citation Count: 0

Mixed occlusions commonly consist in real-world face images and bring with it great challenges for automatic face recognition. The existing methods usually utilize the same reconstruction error to code the occluded test image with respect to the labeled training set and simultaneously to estimate the occlusion/ feature support. However, this ...

10
May 2015 Signal Processing: Volume 110 Issue C, May 2015
Publisher: Elsevier North-Holland, Inc.
Bibliometrics:
Citation Count: 0

Motion synthesis and recognition based on 3D motion data has been extensively studied in recent years. In this paper, we extract a dimensional representation of human motions from 3D spatial-temporal features and map this representation to low-dimensionality subspaces, which can preserve the intrinsic properties of original data. A method for ...
Keywords: Sparse representation, Subspace, Motion recognition, Motion synthesis, Spatial-temporal feature

11
May 2015 Journal of Visualization: Volume 18 Issue 2, May 2015
Publisher: Springer-Verlag New York, Inc.
Bibliometrics:
Citation Count: 4

Keywords: Taxi O/D data, Human movement patterns, Spatio-temporal visualization, Visual analytics

12
June 2014 Neurocomputing: Volume 133, June, 2014
Publisher: Elsevier Science Publishers B. V.
Bibliometrics:
Citation Count: 3

A counting approach for crowd flow based on feature points is proposed. The objective is to obtain the characteristics of the crowd flow in a scene, including the crowd orientation and numeric count. For the feature point detection, a three-frame difference algorithm is used to obtain a foreground containing only ...
Keywords: Three-frame difference, Hessian matrix, DBSCAN clustering algorithm, Optical flow, SURF feature point, Support vector regression

13
March 2014 PACIFICVIS '14: Proceedings of the 2014 IEEE Pacific Visualization Symposium
Publisher: IEEE Computer Society
Bibliometrics:
Citation Count: 2

It is often necessary to analyze spatio-temporal data such as traffic flow, air pollution, and vehicle trajectories in a city. A map is often used to show the spatial context while various temporal displays like time series plots can be used to present the changes in the data over time. ...
Keywords: spatio-temporal visualization, time direction, seam carving, traffic flow, Spatio-temporal visualization Seam carving

14
February 2014 Journal of Parallel and Distributed Computing: Volume 74 Issue 2, February, 2014
Publisher: Academic Press, Inc.
Bibliometrics:
Citation Count: 1

In this study, we discover the parallelism of the forward/backward substitutions (FBS) for two cases and thus propose an efficient preconditioned conjugate gradient algorithm with the modified incomplete Cholesky preconditioner on the GPU (GPUMICPCGA). For our proposed GPUMICPCGA, the following are distinct characteristics: (1) the vector operations are optimized by ...
Keywords: Conjugate gradient algorithm, Modified incomplete Cholesky preconditioner, CUDA, GPU

15
June 2012 The Visual Computer: International Journal of Computer Graphics - CGI'2012 Conference: Volume 28 Issue 6-8, June 2012
Publisher: Springer-Verlag New York, Inc.
Bibliometrics:
Citation Count: 1

Maximum Intensity Difference Accumulation (MIDA) combines the advantage of Direct Volume Rendering (DVR) and Maximum Intensity Projection (MIP). However, many features with local maximum intensity are still missing in the final rendering image. This paper presents a novel approach to focus on features with local maximum intensity within the dataset. ...
Keywords: Moving least squares, Local intensity difference accumulation, Local minimum-point searching, Tone reduction

16
May 2011 NCIS '11: Proceedings of the 2011 International Conference on Network Computing and Information Security - Volume 01
Publisher: IEEE Computer Society
Bibliometrics:
Citation Count: 1

Current medical image processing applications require management of huge amounts of data and executive high-performance computing. How to manage and analysis this large amount of data effectively is a major challenge. This paper shows the initial formulation of medical information integration model, it is designed to help medical workers and ...
Keywords: cloud computing, service computing, medical information integrate, medical image processing, hadoop, mapreduce

17
January 2011 Transactions on edutainment V
Publisher: Springer-Verlag
Bibliometrics:
Citation Count: 0

Visual sensor is widely used in the robotics industry for its cheapness and acquiring information-rich. In this paper we study on vision-based robot programming system and represent the system architecture including the whole framework, the hardware and software components, the visual feedback control loop structure. The relative techniques include robot ...
Keywords: graphics simulation platform, vision calibration, visual feedback, open robot controller

18
December 2010 APSCC '10: Proceedings of the 2010 IEEE Asia-Pacific Services Computing Conference
Publisher: IEEE Computer Society
Bibliometrics:
Citation Count: 0

Constructing Web service workflow faces huge challenges in the volatile, heterogeneous, distributed environment: it is necessary to consider the dynamic changes in web services, but also take into account the rapid method of modeling workflow. Comparing workflow modeling and artificial intelligence planning process, if the Web service as a planned ...
Keywords: Distributed Computing, Services Workflow, Artificial Intelligence Planning, Workflow Modeling

19
August 2010 ICIE '10: Proceedings of the 2010 WASE International Conference on Information Engineering - Volume 01
Publisher: IEEE Computer Society
Bibliometrics:
Citation Count: 0

The classical Mean Shift algorithm has some limitations in target tracking of gray image sequences for it only adopts the simple gray color information. We present an improved Mean Shift tracking algorithm in this paper. Our approach employs the information of gray spatial texture which is used to characterize the ...
Keywords: Mean Shift, Bhattacharyya coefficient, spatial texture, target tracking

20
July 2010 WSEAS Transactions on Computers: Volume 9 Issue 7, July 2010
Publisher: World Scientific and Engineering Academy and Society (WSEAS)
Bibliometrics:
Citation Count: 1

Moving least squares (MLS) has wide applications in scattering points approximation fitting and interpolation. In this paper, we improve a novel MLS approach, adaptive MLS, for non-uniform sample points fitting. The size of radius for MLS can be adaptively adjusted according to the consistency of the sampled data points. Experiments ...
Keywords: MLS, interpolation, sample points, approximation fitting, non-uniform, points set



The ACM Digital Library is published by the Association for Computing Machinery. Copyright © 2018 ACM, Inc.
Terms of Usage   Privacy Policy   Code of Ethics   Contact Us