The adaptivity of thresholding wavelet estimators in heteroscedastic nonparametric model with negatively super-additive dependent errors

Yu Yuncai,Liu Xinsheng,Liu Ling,Sief Mohamed 한국통계학회 2020 Journal of the Korean Statistical Society Vol.49 No.4

In this paper, we consider two estimators, a hard thresholding wavelet estimator and a block thresholding wavelet estimator, for the regression function in heteroscedastic nonparametric model with negatively super-additive dependent (NSD) errors. The random design distribution is known or unknown, and the corresponding adaptive properties of these estimators are investigated over Besov spaces, for the L2 risk. The results indicate that the block thresholding estimator is theoretically and computationally superior to the hard thresholding estimator with the former attains the optimal convergence rates, while the later achieves the nearly optimal convergence rates. Thus the block thresholding estimator provides extensive adaptivity to many irregular function classes even though with the presence of heteroscedastic NSD errors.

Collaborative Similarity Metric Learning for Semantic Image Annotation and Retrieval

( Bin Wang ),( Yuncai Liu ) 한국인터넷정보학회 2013 KSII Transactions on Internet and Information Syst Vol.7 No.5

Automatic image annotation has become an increasingly important research topic owing to its key role in image retrieval. Simultaneously, it is highly challenging when facing to large-scale dataset with large variance. Practical approaches generally rely on similarity measures defined over images and multi-label prediction methods. More specifically, those approaches usually 1) leverage similarity measures predefined or learned by optimizing for ranking or annotation, which might be not adaptive enough to datasets; and 2) predict labels separately without taking the correlation of labels into account. In this paper, we propose a method for image annotation through collaborative similarity metric learning from dataset and modeling the label correlation of the dataset. The similarity metric is learned by simultaneously optimizing the 1) image ranking using structural SVM (SSVM), and 2) image annotation using correlated label propagation, with respect to the similarity metric. The learned similarity metric, fully exploiting the available information of datasets, would improve the two collaborative components, ranking and annotation, and sequentially the retrieval system itself. We evaluated the proposed method on Corel5k, Corel30k and EspGame databases. The results for annotation and retrieval show the competitive performance of the proposed method.

Bio-Inspired Object Recognition Using Parameterized Metric Learning

( Xiong Li ),( Bin Wang ),( Yuncai Liu ) 한국인터넷정보학회 2013 KSII Transactions on Internet and Information Syst Vol.7 No.4

Computing global features based on local features using a bio-inspired framework has shown promising performance. However, for some tough applications with large intra-class variances, a single local feature is inadequate to represent all the attributes of the images. To integrate the complementary abilities of multiple local features, in this paper we have extended the efficacy of the bio-inspired framework, HMAX, to adapt heterogeneous features for global feature extraction. Given multiple global features, we propose an approach, designated as parameterized metric learning, for high dimensional feature fusion. The fusion parameters are solved by maximizing the canonical correlation with respect to the parameters. Experimental results show that our method achieves significant improvements over the benchmark bio-inspired framework, HMAX, and other related methods on the Caltech dataset, under varying numbers of training samples and feature elements.

Learning Discriminative Fisher Kernel for Image Retrieval

( Bin Wang ),( Xiong Li ),( Yuncai Liu ) 한국인터넷정보학회 2013 KSII Transactions on Internet and Information Syst Vol.7 No.3

Content based image retrieval has become an increasingly important research topic for its wide application. It is highly challenging when facing to large-scale database with large variance. The retrieval systems rely on a key component, the predefined or learned similarity measures over images. We note that, the similarity measures can be potential improved if the data distribution information is exploited using a more sophisticated way. In this paper, we propose a similarity measure learning approach for image retrieval. The similarity measure, so called Fisher kernel, is derived from the probabilistic distribution of images and is the function over observed data, hidden variable and model parameters, where the hidden variables encode high level information which are powerful in discrimination and are failed to be exploited in previous methods. We further propose a discriminative learning method for the similarity measure, i.e., encouraging the learned similarity to take a large value for a pair of images with the same label and to take a small value for a pair of images with distinct labels. The learned similarity measure, fully exploiting the data distribution, is well adapted to dataset and would improve the retrieval system. We evaluate the proposed method on Corel-1000, Corel5k, Caltech101 and MIRFlickr 25,000 databases. The results show the competitive performance of the proposed method.

The inflammation regulation effects of Enterococcus faecium HDRsEf1 on human enterocyte-like HT-29 cells

Zhongyuan Tian,Lu Yang,Penghui Li,Yuncai Xiao,Jian Peng,Xiliang Wang,Zili Li,Mei Liu,Dingren Bi,Deshi Shi 한국통합생물학회 2016 Animal cells and systems Vol.20 No.2

Enterococcus faecium HDRsEf1 strain used as a probiotic to inhibit intestine inflammation and improve animal growth performance has been proved by our research team; however, it remains unclear how HDRsEf1 was recognized by intestine cells and how it activates the downstream pathway which benefit intestine health. In this study, HDRsEf1 was used to stimulate HT-29 cell line to partially uncover the intestine benefit mechanism of HDRsEf1. The results of cell viability assays showed that HDRsEf1 had no toxicity on HT-29 at concentrations up to 1 × 108 CFU/mL, HDRsEf1 could upregulate the TLR1, TLR2, and TLR6 mRNA level, especially TLR2, and significantly downregulate the mRNA level of TLR4, TLR5, TLR7, TLR8, but did not significantly affect the mRNA or protein level of MyD88, which suggests that HDRsEf1 activates the TLR2 pathway in an MyD88-independent pattern. HDRsEf1 could significantly downregulate the mRNA level of pro-inflammatory factors IL-1β, IL-6, IL-8, IL-12p35, IL-17, and TNF-α and did not affect the anti-inflammatory factors IL-10, PPAR-γ, and TSLP; besides HDRsEf1 did not upregulate the degradation of IκB in HT-29 cells. By contrast, enterohemorrhagic E. coli (EHEC) O157:H7 strongly up-regulated the mRNA level of pro-inflammatory factors IL-1β, IL-6, IL-8, IL-23, and TNF-α, downregulated obviously anti-inflammatory factor PPAR-ɣ, and obviously upregulated the degradation of IκB, which suggested that HDRsEf1 may act as an antagonist to regulate intestine inflammation response to intestine pathogen. These findings shed a light on the intestine benefit mechanism of HDRsEf1.

Unsupervised Motion Pattern Mining for Crowded Scenes Analysis

( Chongjing Wang ),( Xu Zhao ),( Yi Zou ),( Yuncai Liu ) 한국인터넷정보학회 2012 KSII Transactions on Internet and Information Syst Vol.6 No.12

Crowded scenes analysis is a challenging topic in computer vision field. How to detect diverse motion patterns in crowded scenarios from videos is the critical yet hard part of this problem. In this paper, we propose a novel approach to mining motion patterns by utilizing motion information during both long-term period and short interval simultaneously. To capture long-term motions effectively, we introduce Motion History Image (MHI) representation to access to the global perspective about the crowd motion. The combination of MHI and optical flow, which is used to get instant motion information, gives rise to discriminative spatial-temporal motion features. Benefitting from the robustness and efficiency of the novel motion representation, the following motion pattern mining is implemented in a completely unsupervised way. The motion vectors are clustered hierarchically through automatic hierarchical clustering algorithm building on the basis of graphic model. This method overcomes the instability of optical flow in dealing with time continuity in crowded scenes. The results of clustering reveal the situations of motion pattern distribution in current crowded videos. To validate the performance of the proposed approach, we conduct experimental evaluations on some challenging videos including vehicles and pedestrians. The reliable detection results demonstrate the effectiveness of our approach.

Constrained High Accuracy Stereo Reconstruction Method for Surgical Instruments Positioning

( Chenhao Wang ),( Yi Shen ),( Wenbin Zhang ),( Yuncai Liu ) 한국인터넷정보학회 2012 KSII Transactions on Internet and Information Syst Vol.6 No.10

In this paper, a high accuracy stereo reconstruction method for surgery instruments positioning is proposed. Usually, the problem of surgical instruments reconstruction is considered as a basic task in computer vision to estimate the 3-D position of each marker on a surgery instrument from three pairs of image points. However, the existing methods considered the 3-D reconstruction of the points separately thus ignore the structure information. Meanwhile, the errors from light variation, imaging noise and quantization still affect the reconstruction accuracy. This paper proposes a method which takes the structure information of surgical instruments as constraints, and reconstructs the whole markers on one surgical instrument together. Firstly, we calibrate the instruments before navigation to get the structure parameters. The structure parameters consist of markers` number, distances between each markers and a linearity sign of each instrument. Then, the structure constraints are added to stereo reconstruction. Finally, weighted filter is used to reduce the jitter. Experiments conducted on surgery navigation system showed that our method not only improve accuracy effectively but also reduce the jitter of surgical instrument greatly.

Multiple-Shot Person Re-identification by Features Learned from Third-party Image Sets

( Yanna Zhao ),( Lei Wang ),( Xu Zhao ),( Yuncai Liu ) 한국인터넷정보학회 2015 KSII Transactions on Internet and Information Syst Vol.9 No.2

Person re-identification is an important and challenging task in computer vision with numerous real world applications. Despite significant progress has been made in the past few years, person re-identification remains an unsolved problem. This paper presents a novel appearance-based approach to person re-identification. The approach exploits region covariance matrix and color histograms to capture the statistical properties and chromatic information of each object. Robustness against low resolution, viewpoint changes and pose variations is achieved by a novel signature, that is, the combination of Log Covariance Matrix feature and HSV histogram (LCMH). In order to further improve re-identification performance, third-party image sets are utilized as a common reference to sufficiently represent any image set with the same type. Distinctive and reliable features for a given image set are extracted through decision boundary between the specific set and a third-party image set supervised by max-margin criteria. This method enables the usage of an existing dataset to represent new image data without time-consuming data collection and annotation. Comparisons with state-of-the-art methods carried out on benchmark datasets demonstrate promising performance of our method.

An Improved Privacy Preserving Construction for Data Integrity Verification in Cloud Storage

( Yingjie Xia ),( Fubiao Xia ),( Xuejiao Liu ),( Xin Sun ),( Yuncai Liu ),( Yi Ge ) 한국인터넷정보학회 2014 KSII Transactions on Internet and Information Syst Vol.8 No.10

The increasing demand in promoting cloud computing in either business or other areas requires more security of a cloud storage system. Traditional cloud storage systems fail to protect data integrity information (DII), when the interactive messages between the client and the data storage server are sniffed. To protect DII and support public verifiability, we propose a data integrity verification scheme by deploying a designated confirmer signature DCS as a building block. The DCS scheme strikes the balance between public verifiable signatures and zero-knowledge proofs which can address disputes between the cloud storage server and any user, whoever acting as a malicious player during the two-round verification. In addition, our verification scheme remains blockless and stateless, which is important in conducting a secure and efficient cryptosystem. We perform security analysis and performance evaluation on our scheme, and compared with the existing schemes, the results show that our scheme is more secure and efficient.