arXiv subjects

Yi Yang

Publications and source records attributed to Yi Yang.

At least 1,135 records · Page 63Linked to original sources

arXiv2015

Depth-based hand pose estimation: methods, data, and challenges

Hand pose estimation has matured rapidly in recent years. The introduction of commodity depth sensors and a multitude of practical applications have spurred new advances. We provide an extensive analysis of the state-of-the-art, focusing on hand pose estimation from a single depth frame. To do so, we have implemented a considerable number of systems, and will release all software and evaluation code. We summarize important conclusions here: (1) Pose estimation appears roughly solved for scenes with isolated hands. However, methods still struggle to analyze cluttered scenes where hands may be interacting with nearby objects and surfaces. To spur further progress we introduce a challenging new dataset with diverse, cluttered scenes. (2) Many methods evaluate themselves with disparate criteria, making comparisons difficult. We define a consistent evaluation criteria, rigorously motivated by human experiments. (3) We introduce a simple nearest-neighbor baseline that outperforms most existing systems. This implies that most systems do not generalize beyond their training sets. This also reinforces the under-appreciated point that training data is as important as the model itself. We conclude with directions for future progress.

cs.CV↗

arXiv2015

Multiclass Sparse Discriminant Analysis

In recent years many sparse linear discriminant analysis methods have been proposed for high-dimensional classification and variable selection. However, most of these proposals focus on binary classification and they are not directly applicable to multiclass classification problems. There are two sparse discriminant analysis methods that can handle multiclass classification problems, but their theoretical justifications remain unknown. In this paper, we propose a new multiclass sparse discriminant analysis method that estimates all discriminant directions simultaneously. We show that when applied to the binary case our proposal yields a classification direction that is equivalent to those by two successful binary sparse LDA methods in the literature. An efficient algorithm is developed for computing our method with high-dimensional data. Variable selection consistency and rates of convergence are established under the ultrahigh dimensionality setting. We further demonstrate the superior performance of our proposal over the existing methods on simulated and real data.

stat.ME↗

arXiv2015

Unsupervised Domain Adaptation with Feature Embeddings

Representation learning is the dominant technique for unsupervised domain adaptation, but existing approaches often require the specification of "pivot features" that generalize across domains, which are selected by task-specific heuristics. We show that a novel but simple feature embedding approach provides better performance, by exploiting the feature template structure common in NLP problems.

cs.CL↗

arXiv2015

Semi-supervised Feature Analysis by Mining Correlations among Multiple Tasks

In this paper, we propose a novel semi-supervised feature selection framework by mining correlations among multiple tasks and apply it to different multimedia applications. Instead of independently computing the importance of features for each task, our algorithm leverages shared knowledge from multiple related tasks, thus, improving the performance of feature selection. Note that we build our algorithm on assumption that different tasks share common structures. The proposed algorithm selects features in a batch mode, by which the correlations between different features are taken into consideration. Besides, considering the fact that labeling a large amount of training data in real world is both time-consuming and tedious, we adopt manifold learning which exploits both labeled and unlabeled training data for feature space analysis. Since the objective function is non-smooth and difficult to solve, we propose an iterative algorithm with fast convergence. Extensive experiments on different applications demonstrate that our algorithm outperforms other state-of-the-art feature selection algorithms.

cs.LG↗

arXiv2015

Evolution of the 2012 July 12 CME from the Sun to the Earth: Data-Constrained Three-Dimensional MHD Simulations

The dynamic process of coronal mass ejections (CMEs) in the heliosphere provides us the key information for evaluating CMEs' geo-effectiveness and improving the accurate prediction of CME induced Shock Arrival Time (SAT) at the Earth. We present a data constrained three dimensional (3D) magnetohydrodynamic (MHD) simulation of the evolution of the CME in a realistic ambient solar wind for the July 12-16, 2012 event by using the 3D COIN-TVD MHD code. A detailed comparison of the kinematic evolution of the CME between the observations and the simulation is carried out, including the usage of the time-elongation maps from the perspectives of both Stereo A and Stereo B. In this case study, we find that our 3D COIN-TVD MHD model, with the magnetized plasma blob as the driver, is able to re-produce relatively well the real 3D nature of the CME in morphology and their evolution from the Sun to Earth. The simulation also provides a relatively satisfactory comparison with the in-situ plasma data from the Wind spacecraft.

astro-ph.SR↗

arXiv2015

Group $K$-Means

We study how to learn multiple dictionaries from a dataset, and approximate any data point by the sum of the codewords each chosen from the corresponding dictionary. Although theoretically low approximation errors can be achieved by the global solution, an effective solution has not been well studied in practice. To solve the problem, we propose a simple yet effective algorithm \textit{Group $K$-Means}. Specifically, we take each dictionary, or any two selected dictionaries, as a group of $K$-means cluster centers, and then deal with the approximation issue by minimizing the approximation errors. Besides, we propose a hierarchical initialization for such a non-convex problem. Experimental results well validate the effectiveness of the approach.

cs.CV↗

arXiv2014

Balanced k-Means and Min-Cut Clustering

Clustering is an effective technique in data mining to generate groups that are the matter of interest. Among various clustering approaches, the family of k-means algorithms and min-cut algorithms gain most popularity due to their simplicity and efficacy. The classical k-means algorithm partitions a number of data points into several subsets by iteratively updating the clustering centers and the associated data points. By contrast, a weighted undirected graph is constructed in min-cut algorithms which partition the vertices of the graph into two sets. However, existing clustering algorithms tend to cluster minority of data points into a subset, which shall be avoided when the target dataset is balanced. To achieve more accurate clustering for balanced dataset, we propose to leverage exclusive lasso on k-means and min-cut to regulate the balance degree of the clustering results. By optimizing our objective functions that build atop the exclusive lasso, we can make the clustering result as much balanced as possible. Extensive experiments on several large-scale datasets validate the advantage of the proposed algorithms compared to the state-of-the-art clustering algorithms.

cs.LG↗

arXiv2014

A Convex Formulation for Spectral Shrunk Clustering

Spectral clustering is a fundamental technique in the field of data mining and information processing. Most existing spectral clustering algorithms integrate dimensionality reduction into the clustering process assisted by manifold learning in the original space. However, the manifold in reduced-dimensional subspace is likely to exhibit altered properties in contrast with the original space. Thus, applying manifold information obtained from the original space to the clustering process in a low-dimensional subspace is prone to inferior performance. Aiming to address this issue, we propose a novel convex algorithm that mines the manifold structure in the low-dimensional subspace. In addition, our unified learning process makes the manifold learning particularly tailored for the clustering. Compared with other related methods, the proposed algorithm results in more structured clustering result. To validate the efficacy of the proposed algorithm, we perform extensive experiments on several benchmark datasets in comparison with some state-of-the-art clustering approaches. The experimental results demonstrate that the proposed algorithm has quite promising clustering performance.

cs.LG↗

arXiv2014

A Convex Sparse PCA for Feature Analysis

Principal component analysis (PCA) has been widely applied to dimensionality reduction and data pre-processing for different applications in engineering, biology and social science. Classical PCA and its variants seek for linear projections of the original variables to obtain a low dimensional feature representation with maximal variance. One limitation is that it is very difficult to interpret the results of PCA. In addition, the classical PCA is vulnerable to certain noisy data. In this paper, we propose a convex sparse principal component analysis (CSPCA) algorithm and apply it to feature analysis. First we show that PCA can be formulated as a low-rank regression optimization problem. Based on the discussion, the l 2 , 1 -norm minimization is incorporated into the objective function to make the regression coefficients sparse, thereby robust to the outliers. In addition, based on the sparse model used in CSPCA, an optimal weight is assigned to each of the original feature, which in turn provides the output with good interpretability. With the output of our CSPCA, we can effectively analyze the importance of each feature under the PCA criteria. The objective function is convex, and we propose an iterative algorithm to optimize it. We apply the CSPCA algorithm to feature selection and conduct extensive experiments on six different benchmark datasets. Experimental results demonstrate that the proposed algorithm outperforms state-of-the-art unsupervised feature selection algorithms.

cs.LG↗

arXiv2014

A Discriminative CNN Video Representation for Event Detection

In this paper, we propose a discriminative video representation for event detection over a large scale video dataset when only limited hardware resources are available. The focus of this paper is to effectively leverage deep Convolutional Neural Networks (CNNs) to advance event detection, where only frame level static descriptors can be extracted by the existing CNN toolkit. This paper makes two contributions to the inference of CNN video representation. First, while average pooling and max pooling have long been the standard approaches to aggregating frame level static features, we show that performance can be significantly improved by taking advantage of an appropriate encoding method. Second, we propose using a set of latent concept descriptors as the frame descriptor, which enriches visual information while keeping it computationally affordable. The integration of the two contributions results in a new state-of-the-art performance in event detection over the largest video datasets. Compared to improved Dense Trajectories, which has been recognized as the best video representation for event detection, our new representation improves the Mean Average Precision (mAP) from 27.6% to 36.8% for the TRECVID MEDTest 14 dataset and from 34.0% to 44.6% for the TRECVID MEDTest 13 dataset. This work is the core part of the winning solution of our CMU-Informedia team in TRECVID MED 2014 competition.

cs.CV↗

arXiv2014

Explain Images with Multimodal Recurrent Neural Networks

In this paper, we present a multimodal Recurrent Neural Network (m-RNN) model for generating novel sentence descriptions to explain the content of images. It directly models the probability distribution of generating a word given previous words and the image. Image descriptions are generated by sampling from this distribution. The model consists of two sub-networks: a deep recurrent neural network for sentences and a deep convolutional network for images. These two sub-networks interact with each other in a multimodal layer to form the whole m-RNN model. The effectiveness of our model is validated on three benchmark datasets (IAPR TC-12, Flickr 8K, and Flickr 30K). Our model outperforms the state-of-the-art generative method. In addition, the m-RNN model can be applied to retrieval tasks for retrieving images or sentences, and achieves significant performance improvement over the state-of-the-art methods which directly optimize the ranking objective function for retrieval.

cs.CV↗

arXiv2014

Multiferroic interfaces composed of d0 perovskites oxides

We investigate the electronic, ferroelectric and magnetic properties of KTaO3/PbTiO3 interfaces by using conventional density functional theory (DFT) and advanced DFT such as hybrid functional HSE06. We show that doped holes in valence bands or electrons in conduction bands give rise to ferromagnetism at the interfaces. The ferromagnetic states are ground states for both hole-doped (p-type) and electron-doped (n-type) interfaces by comparison with their corresponding nonmagnetic and antiferromagnetic states. Carriers (holes or electrons) concentrate near the interface to screen the polarization charge and thus the concentration of carrier varies with the ferroelectric polarization. Furthermore, the interface magnetization, which is nearly proportional to the concentration of carrier, can be tuned by ferroelectric polarization reversal, leading to strong intrinsic magnetoelectric effects at the interface of originally nonmagnetic KTaO3 and PbTiO3. Interestingly, a ferromagnetic-nonmagnetic transition tuned by an applied electric field can be realized at the p-type interface. This suggests an illuminating approach to multiferroic materials beyond conventional single-phase multiferroics and multi-phase multiferroics such as ferroelectric/ferromagnet heterostructures. The KTaO3/PbTiO3 interfaces may be promising in future multiferroic devices applications.

cond-mat.mtrl-sci↗

arXiv2014

A Refined Holographic QCD Model and QCD Phase Structure

We consider the Einstein-Maxwell-dilaton system with an arbitrary kinetic gauge function and a dilaton potential. A family of analytic solutions is obtained by the potential reconstruction method. We then study its holographic dual QCD model. The kinetic gauge function can be fixed by requesting the linear Regge spectrum of mesons. We calculate the free energy to obtain the phase diagram of the holographic QCD model.

hep-th↗

arXiv2014

The Appell Function $F_1$ and Regge String Scattering Amplitudes

We show that each 26D open bosonic Regge string scattering amplitude (RSSA) can be expressed in terms of one single Appell function $F_1$ in the Regge limit. This result enables us to derive infinite number of recurrence relations among RSSA at arbitrary mass levels, which are conjectured to be related to the known SL(5,C) dynamical symmetry of $F_1$. In addition, we show that these recurrence relations in the Regge limit can be systematically solved so that all RSSA can be expressed in terms of one amplitude. All these results are dual to high energy symmetries of fixed angle string scattering amplitudes discovered previously [4-8].

hep-th↗

arXiv2014

Analytical Perspective for Photonic Bound States in the Continuum in Photonic Crystal Slabs

We investigate the formation of photonic bound states in the continuum (BICs) in photonic crystal slabs from an analytical perspective. Unlike the stationary at-$Γ$ BICs which origin from the geometric symmetry, the tunable off-$Γ$ BICs are due to the weighted destructive via-the-continuum interference in the vicinity of accidental symmetry when the majority of the radiation is pre-canceled. The symmetric compatible nature of the off-$Γ$ BICs leads to a trapping of light that can be tuned through continuously varying the wavevector. With the analytical approach, we explain a reported experiment and predict the existence of a new BIC at an unrevealed symmetry.

physics.optics↗

arXiv2014

Production of Gadolinium-loaded Liquid Scintillator for the Daya Bay Reactor Neutrino Experiment

We report on the production and characterization of liquid scintillators for the detection of electron antineutrinos by the Daya Bay Reactor Neutrino Experiment. One hundred eighty-five tons of gadolinium-loaded (0.1% by mass) liquid scintillator (Gd-LS) and two hundred tons of unloaded liquid scintillator (LS) were successfully produced from a linear-alkylbenzene (LAB) solvent in six months. The scintillator properties, the production and purification systems, and the quality assurance and control (QA/QC) procedures are described.

physics.ins-det↗

arXiv2013

A New Approach to the Yang-Mills Gauge Theory of Gravity and its Applications

We shall give dynamics to our spacetime manifold by first identifying the local affine symmetry as the characterizing symmetry for our geometry a'la Felix Klein, this symmetry is imposed on us by the Law of Inertia and the Law of Causality. We then prescribe 16 gauge vector bosons to this symmetry a'la Yang and Mills. The locally affine symmetric Yang-Mills Lagrangian in the presence of a background world metric, and the corresponding equations of motion, are respectively constructed and derived. Spontaneous breaking of the local affine symmetry to the local Lorentz symmetry is achieved by classical solutions to the equations of motion. In these classical solutions, the 16 gauge vector bosons are shown to select the Schwarzschild metric as one among the admissible background world metrics. Classical gravity is thus be expressed by a spontaneously broken Erlangen program. We shall also show that this Yang-Mills gauge theory of gravity can give an explanation of the form of the galactic rotation curves, of the amount of intergalactic gravitational lensing, and of the accelerating expansion of the Universe.

physics.gen-ph↗

arXiv2013

BCFW Deformation and Regge Limit

BCFW deformation has served as an extremely useful tool in providing a recursive approach in studying color-ordered gauge amplitudes. This procedure has also been generalized to the study of graviton scattering. An important ingredient of this approach is the ability to identify amplitudes satisfying convergent dispersion relation when the BCFW parameter, z, is treated as a complex variable. In a modified BCFW treatment, we show in what sense the BCFW deformation in the large-z limit can be understood as the Regge limit. We also discuss how the issue of convergent dispersion integral for amplitudes involving external spins relates to the study of super-convergence relation which served as the precursor to the s-t duality relation for flat space string amplitudes.

hep-th↗