Search For:

Displaying 1-50 out of 50 total
50 Years of Image Processing and Pattern Recognition in China
Found in: IEEE Intelligent Systems
By Nanning Zheng, Qubo You, Gaofeng Meng, Jihua Zhu, Shaoyi Du, Jianyi Liu
Issue Date:November 2008
pp. 33-41
This article briefly reviews the development of image recognition in and outside China. It presents theoretical research achievements and applied research as well as several typical applications of image recognition in China. Finally, it discusses future t...
Deterministic Annealing Learning of the Radial Basis Function Nets for Improving the Regression Ability of RBF Network
Found in: Neural Networks, IEEE - INNS - ENNS International Joint Conference on
By Nanning Zheng, Zhihua Zhang, Haibing Zheng, Shi Gang
Issue Date:July 2000
pp. 3601
In this paper, the deterministic annealing method for training the center vectors of RBF network is proposed. The method is a soft-competition scheme and derived from optimizing an objective function using the gradient descent method. To some extent, it ca...
Constructing Adaptive Complex Cells for Robust Visual Tracking
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Dapeng Chen,Zejian Yuan,Yang Wu,Geng Zhang,Nanning Zheng
Issue Date:December 2013
pp. 1113-1120
Representation is a fundamental problem in object tracking. Conventional methods track the target by describing its local or global appearance. In this paper we present that, besides the two paradigms, the composition of local region histograms can also pr...
Modeling 4D Human-Object Interactions for Event and Object Recognition
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Ping Wei,Yibiao Zhao,Nanning Zheng,Song-Chun Zhu
Issue Date:December 2013
pp. 3272-3279
Recognizing the events and objects in the video sequence are two challenging tasks due to the complex temporal structures and the large appearance variations. In this paper, we propose a 4D human-object interaction model, where the two tasks jointly boost ...
Concurrent Action Detection with Structural Prediction
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Ping Wei,Nanning Zheng,Yibiao Zhao,Song-Chun Zhu
Issue Date:December 2013
pp. 3136-3143
Action recognition has often been posed as a classification problem, which assumes that a video sequence only have one action class label and different actions are independent. However, a single human body can perform multiple concurrent actions at the sam...
Nonparametric Illumination Correction for Scanned Document Images via Convex Hulls
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Gaofeng Meng, Shiming Xiang, Nanning Zheng, Chunhong Pan
Issue Date:July 2013
pp. 1730-1743
A scanned image of an opened book page often suffers from various scanning artifacts known as scanning shading and dark borders noises. These artifacts will degrade the qualities of the scanned images and cause many problems to the subsequent process of do...
Scheduling Algorithms for Handling Updates in Shingled Magnetic Recording
Found in: 2013 IEEE 8th International Conference on Networking, Architecture, and Storage (NAS)
By Kalyana Sundaram Venkataraman,Tong Zhang,Wenzhe Zhao,Hongbin Sun,Nanning Zheng
Issue Date:July 2013
pp. 205-214
Shingled recording has recently emerged as one promising candidate to sustain the historical growth of magnetic recording storage areal density. However, since the convenient update-in-place feature is no longer available in shingled recording, many sector...
Evasive bots masquerading as human beings on the web
Found in: 2013 43rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN)
By Jing Jin,Jeff Offutt,Nan Zheng,Feng Mao,Aaron Koehl,Haining Wang
Issue Date:June 2013
pp. 1-12
Web bots such as crawlers are widely used to automate various online tasks over the Internet. In addition to the conventional approach of human interactive proofs such as CAPTCHAs, a more recent approach of human observational proofs (HOP) has been develop...
Improved View Synthesis with Depth Reliability Maps
Found in: Data Compression Conference
By Yi Lai,Xuguang Lan,Yuehu Liu,Nanning Zheng
Issue Date:April 2012
pp. 402
In this paper, an improved view interpolation algorithm with depth reliability maps is presented to enhance the quality of synthesized images. First, a region under the mask within a virtual view image is treated as a set of indicating pixels. Next, based ...
Application in Target Recognition Based on Gray System Theory and Mathematical Morphology Edge Detection
Found in: Computer Science and Electronics Engineering, International Conference on
By Hai-yu Li,Xin-yu Jia,Ying Liu,Hai-feng Tan,Nan Zheng
Issue Date:March 2012
pp. 611-614
This paper explores the gray system theory and mathematical morphology in image edge detection and target recognition applications. Through experiments that ingenious combination of the gray system theory and mathematical morphology, the use of gray system...
An Improvement of Two-Dimensional Maximum Entropy Thresholding Segmentation Algorithm for SAR Image
Found in: Computer Science and Electronics Engineering, International Conference on
By Hai-feng Tan,Guang Yang,Nan Zheng,Tian-wen Luo
Issue Date:March 2012
pp. 379-382
In allusion to complex land SAR images, a modified partition method for two dimensional maximum entropic thresholding method is proposed. In this algorithm, a weighted factor is introduced into the criterion function of detection threshold, which strengthe...
Research on Optimization Mode of Comparable Case Selection Process in the Market Comparison Approach
Found in: International Conference on Information Management, Innovation Management and Industrial Engineering
By Yang Nan,Zheng Junwei
Issue Date:November 2011
pp. 483-486
In order to improve the precision of the real estate appraisal, base on the theory basis of real estate appraisal theory, this paper analyzed the difficulties and problems of the market comparison approach in the real estate valuation practices. The expert...
Automatic salient object extraction with contextual cue
Found in: Computer Vision, IEEE International Conference on
By Le Wang, Jianru Xue,Nanning Zheng,Gang Hua
Issue Date:November 2011
pp. 105-112
We present a method for automatically extracting salient object from a single image, which is cast in an energy minimization framework. Unlike most previous methods that only leverage appearance cues, we employ an auto-context cue as a complementary data t...
Fuzzy Enhancement Based on Transition Zone Edge Detection Algorithm for SAR Image
Found in: Information Technology, Computer Engineering and Management Sciences, International Conference of
By Nan Zheng,Haiyu Li,Haifeng Tan,Tianwen Luo
Issue Date:September 2011
pp. 119-122
Considering small edges, spurious edges and other problems of edge detection on SAR images, an improved edge detection algorithm based on fuzzy enhancement of transition region is proposed. In this paper, the defects of the classical fuzzy enhancement algo...
A Method Integrating Human Visual Attention and Consciousness of Radar and Vision Fusion for Autonomous Vehicle Navigation
Found in: Space Mission Challenges for Information Technology, IEEE International Conference on
By Tao Wang,Jingmin Xin,Nanning Zheng
Issue Date:August 2011
pp. 192-197
This paper attempted to construct an robust method for real-time guidance and navigation for autonomous mobile robot, combinedly using both millimeter wave (MMW) radar and vision sensors. Vision sensor integrated with MMW radar of all-weather application i...
Development of Pricing Models for Intangible Services Based on Conjoint Analysis and Mathematical Programming: A Case Study About the Design of Credit Card Services in China
Found in: Annual SRII Global Conference
By Emmanuel Fragnière, Francesco Moresino, Nan Zheng
Issue Date:April 2011
pp. 653-662
We propose an aggregate planning model based on integer optimization that combines consumers' perception, market share, and cost-benefit analysis. This model provides a new direction to optimize the design of credit card services. The survey was administer...
Explicit Network-Adaptive Robust Multiple Description Coding
Found in: Data Compression Conference
By Meng Yang, Xuguang Lan, Nanning Zheng
Issue Date:March 2011
pp. 485
The data delivery performance of multiple description coding (MDC) over unreliable network with capacity constraints is always related with three factors: redundancy rate, packet loss rate (PLR), bit error rate (BER). It is supposed that the packet losses ...
Learning to Detect a Salient Object
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Tie Liu, Zejian Yuan, Jian Sun, Jingdong Wang, Nanning Zheng, Xiaoou Tang, Heung-Yeung Shum
Issue Date:February 2011
pp. 353-367
In this paper, we study the salient object detection problem for images. We formulate this problem as a binary labeling task where we separate the salient object from the background. We propose a set of novel features, including multiscale contrast, center...
Arbitrary ROI-Based Wavelet Video Coding
Found in: Data Compression Conference
By Xuguang Lan, Nanning Zheng, Wen Ma, Miao Hui, Jianru Xue
Issue Date:March 2010
pp. 537
An arbitrary shape region of interest (ROI) coding is presented for scalable wavelet video codec in this paper. The padding of macroblock and polygon matching are employed to estimate the motion of the ROI. The motion vectors derived are set as the motion ...
Enhanced Location Privacy Protection of Base Station in Wireless Sensor Networks
Found in: Mobile Ad-hoc and Sensor Networks, International Conference on
By Xinfeng Li, Xiaoyuan Wang, Nan Zheng, Zhiguo Wan, Ming Gu
Issue Date:December 2009
pp. 457-464
Location privacy in wireless sensor networks has gained a wide concern. Particularly, the location privacy of base station requires ultimate protection due to its crucial position in wireless sensor networks. In this paper, we propose an efficient scheme, ...
3D DRAM Design and Application to 3D Multicore Systems
Found in: IEEE Design and Test of Computers
By Hongbin Sun, Jibang Liu, Rakesh S. Anigundi, Nanning Zheng, Jian-Qiang Lu, Kenneth Rose, Tong Zhang
Issue Date:September 2009
pp. 36-47
<p>Editor's note:</p><p>From a system architecture perspective, 3D technology can satisfy the high memory bandwidth demands that future multicore/manycore architectures require. This article presents a 3D DRAM architecture design and the ...
A Visual Brain Chip Based on Selective Attention for Robot Vision Application
Found in: Space Mission Challenges for Information Technology, IEEE International Conference on
By Tao Wang, Nanning Zheng, Kuizhi Mei
Issue Date:July 2009
pp. 93-97
Due to huge computational loads and the state of art of current hardware, nowadays how to implement real-time vision tasks on a signal chip is still a great interesting work. It is critical for eventually accomplishing biointelligence on robots, whatever h...
Complete Decentralized Mechanism Design for Online Machine Scheduling
Found in: Embedded Software and Systems, Second International Conference on
By Yuan Zhang, Chi-Hung Chi, Shengqing Zhang, Nan Zheng
Issue Date:May 2009
pp. 530-535
We study an online version of the classical parallel scheduling problem to minimize the total weighted completion time in a total decentralized setting: both the jobs and the machines are selfish entities who try to maximize their own interest. We study th...
Leveraging Access Locality for the Efficient Use of Multibit Error-Correcting Codes in L2 Cache
Found in: IEEE Transactions on Computers
By Hongbin Sun, Nanning Zheng, Tong Zhang
Publication Date: March 2009
pp. 1297-1306
It is almost evident that SRAM-based cache memories will be subject to a significant degree of parametric random defects if one wants to leverage the technology scaling to its full extent. Although strong multibit error-correcting codes (ECC) appear to be ...
Joint Network-Source Video Coding Based on Lagrangian Rate Allocation
Found in: Data Compression Conference
By Xuguang Lan, Nanning Zheng, Jianru Xue, Ce Li, Songlin Zhao
Issue Date:March 2009
pp. 454
Joint network-source video coding (JNSC) is targeted to achieve the optimum delivery of a video source to a number of destinations over network with capacity constraints. In this paper, a practical scalable multiple description coding is proposed for JNSC,...
DRM Oriented Authenticated Group Key Agreement Scheme from Multilinear Form
Found in: Communications and Mobile Computing, International Conference on
By Xiaofeng Wang, Nanning Zheng, Lihua Tian
Issue Date:January 2009
pp. 101-105
We propose a DRM oriented authenticated group key agreement scheme from multilinear forms. The new scheme is ID-based, but need not trusted PKG and random oracle model, which effectively solves the key escrow problem. Our scheme can be used to replace the ...
A CAVLC-Based Blind Watermarking Method for H.264/AVC Compressed Video
Found in: Asia-Pacific Conference on Services Computing. 2006 IEEE
By Lihua Tian, Nanning Zheng, Jianru Xue, Tao Xu
Issue Date:December 2008
pp. 1295-1299
Streaming media services have been applied in many applications. At the same time, the security of it should be considered. To protect the video content, watermarking data (image) is usually embedded into the quantized DCT coefficients of video. At the sam...
ID-Based Authenticated Multi-party Key Agreement Protocol to Multimedia Applications Systems
Found in: Computer Science and Software Engineering, International Conference on
By Xiaofeng Wang, Nanning Zheng
Issue Date:December 2008
pp. 1007-1010
An ID-based authenticated multi-party key agreementscheme without trusted PKG is proposed in this paper. The proposed scheme is ID-based, but without any assumption of prefixed trust relationship between members, which effectively solves the problem that e...
Realization of L2 Cache Defect Tolerance Using Multi-bit ECC
Found in: Defect and Fault-Tolerance in VLSI Systems, IEEE International Symposium on
By Hongbin Sun, Nanning Zheng, Tong Zhang
Issue Date:October 2008
pp. 254-262
This paper presents a design solution that enables the use of powerful multi-bit error-correcting code (ECC) to realize L2 cache defect tolerance at minimal latency and silicon area cost. This work is motivated by the observation that the continuous CMOS T...
Combine EMD and ICA to Learn Image Bases
Found in: Image and Signal Processing, Congress on
By Fang Dai, Jianru Xue, Nanning Zheng
Issue Date:May 2008
pp. 494-497
A method of learning image bases from natural images is proposed in this paper. Natural image is decomposed into structure mode and non-structure mode by using Empirical Mode Decomposition (EMD) technique. The structure mode is made up of the first two Int...
Manageable peer-to-peer architecture for video-on-demand
Found in: Parallel and Distributed Processing Symposium, International
By Xuguang Lan, Nanning Zheng, Jianru Xue, Weike Chen, Bin Wang, Wen Ma
Issue Date:April 2008
pp. 1-7
An efficiently manageable overlay network architecture, called AIRVoD, is proposed for video-on-demand, based on a distributed-centralized P2P network. The system consists of distributed servers, peers, SuperNodes and sub-SuperNodes. The distributed centra...
An Efficient Motion Adaptive De-interlacing and Its VLSI Architecture Design
Found in: VLSI, IEEE Computer Society Annual Symposium on
By Hongbin Sun, Nanning Zheng, Chenyang Ge, Dong Wang, Pengju Ren
Issue Date:April 2008
pp. 455-458
This paper presents an efficient motion adaptive de-interlacing technique that consists of two main steps, i.e. 4-field extended Gaussian filtering motion detection and adjustable window ELA de-interlacing. Four consecutive interlaced fields are used to de...
A Peer-to-Peer Architecture Based on Scalable Video Coding
Found in: Data Compression Conference
By Xuguang Lan, Nanning Zheng, Jianru Xue, Weike Chen, Bin Wang, Wen Ma, Songlin Zhao
Issue Date:March 2008
pp. 529
Combining the advantages of the centralized P2P structure and the data-driven structure with scalable video coding, we propose an adaptive P2P architecture for live video based on scalable wavelet video coding over internet. The core operations are simple:...
Eye Synthesis Using the Eye Curve Model
Found in: Tools with Artificial Intelligence, IEEE International Conference on
By Lei Xiong, Nanning Zheng, Qubo You, Jianyi Liu, Shaoyi Du
Issue Date:October 2007
pp. 531-534
Eyes are a critical part of facial expressions. Because of the appearance diversity of eyes due to motion, it is difficult to synthesize eye with a particular facial expression. Traditional methods have failed to adequately catch motion-related appearance ...
Automatic ROI Selection for JPEG2000 Compression of Remote Sensing Images
Found in: International Conference on Semantic Computing
By Fei Wang, Jishang Wei, Nanning Zheng, Shaoyi Du, Bin Gao
Issue Date:September 2007
pp. 615-621
Recently, remote sensing images increase greatly in the repositories. To achieve efficient storage and indexing, we introduce a JPEG2000 compression frame which puts emphasis on selection and designation of regions of interest (ROI). Firstly, SIFT is appli...
A Regeneration Based Lines Restoration Method
Found in: Intelligent Systems Design and Applications, International Conference on
By Lei Yang, Nanning Zheng, Yonghong Song, Yuanlin Zhang
Issue Date:October 2006
pp. 767-772
Lines restoration is a specific research issue needed attentions in the image restoration and representation field. Imitating the mechanism of human perception, this article proposes a novel regeneration based method for eliminating degradations of lines i...
An Approach for Constructing Sparse Kernel Classifier
Found in: Pattern Recognition, International Conference on
By Zejian Yuan, Yanyun Qu, Yang Yang, Nanning Zheng
Issue Date:August 2006
pp. 560-563
This paper presents a new approach for constructing sparse kernel classifier with large margin. Firstly, we propose a kernel function pursuit strategy for selecting a small number of kernel functions which are used for expanding final classifier. And then ...
Boosted Gabor Features Applied to Vehicle Detection
Found in: Pattern Recognition, International Conference on
By Hong Cheng, Nanning Zheng, Chong Sun
Issue Date:August 2006
pp. 662-666
<p>Robust vehicle detection is a challenging task given vehicles with different types, and sizes, and at different distances. This paper proposes a Boosted Gabor Features (BGF) approach for vehicle detection. The two main conventional Gabor filter de...
Neighborhood Discriminant Projection for Face Recognition
Found in: Pattern Recognition, International Conference on
By Qubo You, Nanning Zheng, Shaoyi Du, Yang Wu
Issue Date:August 2006
pp. 532-535
We propose a novel manifold learning approach, called Neighborhood Discriminant Projection (NDP), for robust face recognition. The purpose of NDP is to preserve the within-class neighboring geometry of the image space, while keeping away the projected vect...
An integrated Monte Carlo data association framework for multi-object tracking
Found in: Pattern Recognition, International Conference on
By Jianru Xue, Nanning Zheng, Xiaopin Zhong
Issue Date:August 2006
pp. 703-706
We propose a sequential Monte Carlo data association algorithm based on a two-level computational framework for tracking varying number of interacting objects in dynamic scene. Firstly, we propose a hybrid measurements generation process to facilitate vary...
Surface modification of insulating polymers by using APGD and DBD in air
Found in: International Symposium on Electrical Insulating Materials
By Yun Yang, Guan-Jun Zhang, Wen-Bin Zhao, Nan Zheng
Issue Date:June 2005
pp. 320-323 Vol. 2
Since the last decade, the atmospheric pressure glow discharge (APGD) and dielectric barrier discharge (DBD) has utilized for numerous applications. An experimental setup is constructed for generating the APGD or DBD. When inserting a mesh wire between the...
Leveraging Heterogeneous Power for Improving Datacenter Efficiency and Resiliency
Found in: IEEE Computer Architecture Letters
By Longjun Liu,Chao Li,Hongbin Sun,Yang Hu,Jingmin Xin,Nanning Zheng,Tao Li
Issue Date:February 2015
pp. 1
Power mismatching between supply and demand has emerged as a top issue in modern datacenters that are under-provisioned or powered by intermittent power supplies. Recent proposals are primarily limited to leveraging uninterruptible power supplies (UPS) to ...
Salient Object Detection: A Discriminative Regional Feature Integration Approach
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Huaizu Jiang,Jingdong Wang,Zejian Yuan,Yang Wu,Nanning Zheng,Shipeng Li
Issue Date:June 2013
pp. 2083-2090
Salient object detection has been attracting a lot of interest, and recently various heuristic computational models have been designed. In this paper, we regard saliency map computation as a regression problem. Our method, which is based on multi-level ima...
Integrating EMD and Gradient for Generating Primal Sketch of Natural Images
Found in: Pattern Recognition, International Conference on
By Fang Dai, Nanning Zheng, Jianru Xue
Issue Date:August 2006
pp. 429-432
Primal sketch performs an important role in early vision. In this paper, we propose a novel method to obtain the primal sketch of natural images by integrating empirical mode decomposition (EMD) techniques and image gradient. 2D EMD approach can decompose ...
Moment feature based forensic detection of resampled digital images
Found in: Proceedings of the 21st ACM international conference on Multimedia (MM '13)
By Lu Li, Jianru Xue, Nanning Zheng, Zhiqiang Tian
Issue Date:October 2013
pp. 569-572
Forensic detection of resampled digital images has become an important technology among many others to establish the integrity of digital visual content. This paper proposes a moment feature based method to detect resampled digital images. Rather than conc...
Locality preserving verification for image search
Found in: Proceedings of the 21st ACM international conference on Multimedia (MM '13)
By Qi Tian, Shanmin Pang, Jianru Xue, Nanning Zheng
Issue Date:October 2013
pp. 529-532
Establishing correct correspondences between two images has a wide range of applications, such as 2D and 3D registration, structure from motion, and image retrieval. In this paper, we propose a new matching method based on spatial constraints. The proposed...
Key object-based static video summarization
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Ce Li, Jianru Xue, Nanning Zheng, Xuguang Lan, Zhiqiang Tian
Issue Date:November 2011
pp. 1301-1304
In this paper, we present a system for object-based video summarization facilitated by an efficient video object segmentation system. We eliminate the redundancy not only from spatial and temporal domain, but also from content domain. First, we detect shot...
Nonparametric bottom-up saliency detection using hypercomplex spectral contrast
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Ce Li, Jianru Xue, Nanning Zheng, Zhiqiang Tian
Issue Date:November 2011
pp. 1157-1160
Saliency detection is an useful technique for image semantic analysis such as auto image segmentation, image retargeting, advertising design and image compression. Inspired by two existing saliency detection algorithms, named spectral residual (SR) and pha...
Design techniques to improve the device write margin for MRAM-based cache memory
Found in: Proceedings of the 21st edition of the great lakes symposium on Great lakes symposium on VLSI (GLSVLSI '11)
By Chuanyin Liu, Hongbin Sun, Nanning Zheng, Tai Min, Tong Zhang
Issue Date:May 2011
pp. 97-102
As one promising non-volatile memory technology, magnetoresistive RAM (MRAM) based on magnetic tunneling junctions (MTJs) has recently attracted much attention. However, latest device research has discovered that, in order to maintain sufficient MTJ write ...
Flickr group recommendation based on tensor decomposition
Found in: Proceeding of the 33rd international ACM SIGIR conference on Research and development in information retrieval (SIGIR '10)
By Leiming Zhang, Nan Zheng, Qiudan Li, Shengcai Liao
Issue Date:July 2010
pp. 737-738
Over the last few years, Flickr has gained massive popularity and groups in Flickr are one of the main ways for photo diffusion. However, the huge volume of groups brings troubles for users to decide which group to choose. In this paper, we propose a tenso...