Searcharxiv⌕ Search

arXiv subjects

Chunlei Liu

Publications and source records attributed to Chunlei Liu.

At least 37 records · Page 2Linked to original sources
arXiv2019

Aggregation Signature for Small Object Tracking

Small object tracking becomes an increasingly important task, which however has been largely unexplored in computer vision. The great challenges stem from the facts that: 1) small objects show extreme vague and variable appearances, and 2) they tend to be lost easier as compared to normal-sized ones due to the shaking of lens. In this paper, we propose a novel aggregation signature suitable for small object tracking, especially aiming for the challenge of sudden and large drift. We make three-fold contributions in this work. First, technically, we propose a new descriptor, named aggregation signature, based on saliency, able to represent highly distinctive features for small objects. Second, theoretically, we prove that the proposed signature matches the foreground object more accurately with a high probability. Third, experimentally, the aggregation signature achieves a high performance on multiple datasets, outperforming the state-of-the-art methods by large margins. Moreover, we contribute with two newly collected benchmark datasets, i.e., small90 and small112, for visually small object tracking. The datasets will be available in https://github.com/bczhangbczhang/.

cs.CV↗
arXiv2019

RBCN: Rectified Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs

Binarized convolutional neural networks (BCNNs) are widely used to improve memory and computation efficiency of deep convolutional neural networks (DCNNs) for mobile and AI chips based applications. However, current BCNNs are not able to fully explore their corresponding full-precision models, causing a significant performance gap between them. In this paper, we propose rectified binary convolutional networks (RBCNs), towards optimized BCNNs, by combining full-precision kernels and feature maps to rectify the binarization process in a unified framework. In particular, we use a GAN to train the 1-bit binary network with the guidance of its corresponding full-precision model, which significantly improves the performance of BCNNs. The rectified convolutional layers are generic and flexible, and can be easily incorporated into existing DCNNs such as WideResNets and ResNets. Extensive experiments demonstrate the superior performance of the proposed RBCNs over state-of-the-art BCNNs. In particular, our method shows strong generalization on the object tracking task.

cs.CV↗
arXiv2019

Learning-based Single-step Quantitative Susceptibility Mapping Reconstruction Without Brain Extraction

Quantitative susceptibility mapping (QSM) estimates the underlying tissue magnetic susceptibility from MRI gradient-echo phase signal and typically requires several processing steps. These steps involve phase unwrapping, brain volume extraction, background phase removal and solving an ill-posed inverse problem. The resulting susceptibility map is known to suffer from inaccuracy near the edges of the brain tissues, in part due to imperfect brain extraction, edge erosion of the brain tissue and the lack of phase measurement outside the brain. This inaccuracy has thus hindered the application of QSM for measuring the susceptibility of tissues near the brain edges, e.g., quantifying cortical layers and generating superficial venography. To address these challenges, we propose a learning-based QSM reconstruction method that directly estimates the magnetic susceptibility from total phase images without the need for brain extraction and background phase removal, referred to as autoQSM. The neural network has a modified U-net structure and is trained using QSM maps computed by a two-step QSM method. 209 healthy subjects with ages ranging from 11 to 82 years were employed for patch-wise network training. The network was validated on data dissimilar to the training data, e.g. in vivo mouse brain data and brains with lesions, which suggests that the network has generalized and learned the underlying mathematical relationship between magnetic field perturbation and magnetic susceptibility. AutoQSM was able to recover magnetic susceptibility of anatomical structures near the edges of the brain including the veins covering the cortical surface, spinal cord and nerve tracts near the mouse brain boundaries. The advantages of high-quality maps, no need for brain volume extraction and high reconstruction speed demonstrate its potential for future applications.

eess.IV↗
arXiv2019

Proof of Mining in Blockchain Systems

We propose a proof of mining system. Roughly speaking, in this system the mining stake ${\rm mstak}(A)$ with discrimination index $a\in[0,1]$ of an account $A$ is defined by the formula: $${\rm mstak}(A)=(1-a)\cdot\frac{1}{\rm NOM}+a\cdot\frac{{\rm NOBM}(A)}{L},$$ where $L$ is the length of the block-chain, ${\rm NOM}$ is the number of miners in the block-chain, and ${\rm NOBM}(A)$ is the number of blocks mined by $A$.

cs.CR↗
arXiv2018

Multivariate MR Biomarkers Better Predict Cognitive Dysfunction in Mouse Models of Alzheimers Disease

To understand multifactorial conditions such as Alzheimers disease (AD) we need brain signatures that predict the impact of multiple pathologies and their interactions. To help uncover the relationships between brain circuits and cognitive markers we have used mouse models that represent, at least in part, the complex interactions altered in AD. In particular, we aimed to understand the relationship between vulnerable brain circuits and memory deficits measured in the Morris water maze, and we tested several predictive modeling approaches. We used in vivo manganese enhanced MRI voxel based analyses to reveal regional differences in volume (morphometry), signal intensity (activity), and magnetic susceptibility (iron deposition, demyelination). These regions included the hippocampus, olfactory areas, entorhinal cortex and cerebellum. The image based properties of these regions were used to predict spatial memory. We next used eigenanatomy, which reduces dimensionality to produce sets of regions that explain the variance in the data. For each imaging marker, eigenanatomy revealed networks underpinning a range of cognitive functions including memory, motor function, and associative learning. Finally, the integration of multivariate markers in a supervised sparse canonical correlation approach outperformed single predictor models and had significant correlates to spatial memory. Among a priori selected regions, the fornix also provided good predictors, raising the possibility of investigating how disease propagation within brain networks leads to cognitive deterioration. Our results support that modeling approaches integrating multivariate imaging markers provide sensitive predictors of AD-like behaviors. Such strategies for mapping brain circuits responsible for behaviors may help in the future predict disease progression, or response to interventions.

q-bio.QM↗
arXiv2018

Subadditive stake systems

Stake systems which issue stakes as well as coins are proposed. Two subadditive stake systems are studied: one is the radical stake system, the other is the logarithmic stake system. Securities of both systems are analysed.

cs.CR↗
arXiv2018

Proof of spending in block-chain systems

We introduce proof of spending in a block-chain system. In this system the probability for a node to create a legal block is proportional to the total amount of coins it has spent in history.

cs.CR↗
arXiv2015

Linearized Reed-Solomon codes and linearized Wenger graphs

A codeword is associated to a linearized polynomial. The weight distribution of the codewords is determined as the linearized polynomial varies in a family of fixed degree. There is a corresponding result on Wenger graphs from linearized polynomials.

cs.IT↗
arXiv2015

A class of cyclic codes whose dual have five zeros

In this paper, a family of cyclic codes over $\mathbb{F}_{p}$ whose duals have five zeros is presented, where $p$ is an odd prime. Furthermore, the weight distributions of these cyclic codes are determined.

cs.IT↗
arXiv2013

Incidence Matrices of Polarized Projective Spaces

In this paper, we first define a non-degenerate symmetric bilinear form on Fq^4. Then we get an incidence matrix G of Fq^4 by the bilinear form. By its corresponding quadratic form Q, the lines of Fq^4 are classified as isotropic and anisotropic lines. Under this classification, we can get two sub-matrices of G and prove their 2-rank. Key words and phrases: finite field, quadratic form, incidence matrix.

math.NT↗
arXiv2013

Incidence Matrices of Finite Quadratic Spaces

In this paper, we first prove the 2-rank of full incidence matrix of PG(n,q) with $q$ an odd prime power. Then by the quadratic form defined on PG(n,q), the points of it are classified as isotropic and anisotropic points. We divide the full incidence matrix into four sub-matrices. Then by using the software package Magma, we give a general conjecture for the 2-rank of sub-matrices of the full incidence matrix in PG(n,q) and prove it in the case of n=1, 2.

math.NT↗
arXiv2013

Semileptonic Charm Decays: mini review

One important task in the field of flavor physics is to over-constrain the CKM matrix. To best extract CKM matrix elements, we need inputs from both experimental data and theoretical calculations. Latest knowledge about the CKM matrix shows our understanding about sin$2β$ is the best thanks to clean theory and large statistics from experiments. In contrast, our understanding of both mixing and $|V_{ub}|$ have limitations from theoretical predictions. In order to extract the value of $|V_{ub}|$ from the branching fraction measurement, we need information on the hadronic form factor $f_+(q^2)$. Our best understanding about $f_+(q^2)$ is from lattice QCD calculations. To validate improved lattice QCD calculations for the form factor in semi-leptonic B decays, we can use semi-leptonic $D$ decays as a test and calibration. Since the CKM matrix elements $|V_{cs(d)}|$ can be obtained precisely from unitarity, we have a reliable method to check the lattice QCD calculations. The experimental results of $D$ semi-leptonic decays can be summarized in two main categories: the exclusive decays and the inclusive decays. Latest measurements from the exclusive semi-leptonic $D$ decays are discussed here.

hep-ex↗