arXiv subjects

Li Cheng

Publications and source records attributed to Li Cheng.

At least 73 records · Page 4Linked to original sources

arXiv2020

SparseFusion: Dynamic Human Avatar Modeling from Sparse RGBD Images

In this paper, we propose a novel approach to reconstruct 3D human body shapes based on a sparse set of RGBD frames using a single RGBD camera. We specifically focus on the realistic settings where human subjects move freely during the capture. The main challenge is how to robustly fuse these sparse frames into a canonical 3D model, under pose changes and surface occlusions. This is addressed by our new framework consisting of the following steps. First, based on a generative human template, for every two frames having sufficient overlap, an initial pairwise alignment is performed; It is followed by a global non-rigid registration procedure, in which partial results from RGBD frames are collected into a unified 3D shape, under the guidance of correspondences from the pairwise alignment; Finally, the texture map of the reconstructed human model is optimized to deliver a clear and spatially consistent texture. Empirical evaluations on synthetic and real datasets demonstrate both quantitatively and qualitatively the superior performance of our framework in reconstructing complete 3D human models with high fidelity. It is worth noting that our framework is flexible, with potential applications going beyond shape reconstruction. As an example, we showcase its use in reshaping and reposing to a new avatar.

cs.CV↗

arXiv2020

WaveletKernelNet: An Interpretable Deep Neural Network for Industrial Intelligent Diagnosis

Convolutional neural network (CNN), with ability of feature learning and nonlinear mapping, has demonstrated its effectiveness in prognostics and health management (PHM). However, explanation on the physical meaning of a CNN architecture has rarely been studied. In this paper, a novel wavelet driven deep neural network termed as WaveletKernelNet (WKN) is presented, where a continuous wavelet convolutional (CWConv) layer is designed to replace the first convolutional layer of the standard CNN. This enables the first CWConv layer to discover more meaningful filters. Furthermore, only the scale parameter and translation parameter are directly learned from raw data at this CWConv layer. This provides a very effective way to obtain a customized filter bank, specifically tuned for extracting defect-related impact component embedded in the vibration signal. In addition, three experimental verification using data from laboratory environment are carried out to verify effectiveness of the proposed method for mechanical fault diagnosis. The results show the importance of the designed CWConv layer and the output of CWConv layer is interpretable. Besides, it is found that WKN has fewer parameters, higher fault classification accuracy and faster convergence speed than standard CNN.

cs.CV↗

arXiv2020

Stabilizing Training of Generative Adversarial Nets via Langevin Stein Variational Gradient Descent

Generative adversarial networks (GANs), famous for the capability of learning complex underlying data distribution, are however known to be tricky in the training process, which would probably result in mode collapse or performance deterioration. Current approaches of dealing with GANs' issues almost utilize some practical training techniques for the purpose of regularization, which on the other hand undermines the convergence and theoretical soundness of GAN. In this paper, we propose to stabilize GAN training via a novel particle-based variational inference -- Langevin Stein variational gradient descent (LSVGD), which not only inherits the flexibility and efficiency of original SVGD but aims to address its instability issues by incorporating an extra disturbance into the update dynamics. We further demonstrate that by properly adjusting the noise variance, LSVGD simulates a Langevin process whose stationary distribution is exactly the target distribution. We also show that LSVGD dynamics has an implicit regularization which is able to enhance particles' spread-out and diversity. At last we present an efficient way of applying particle-based variational inference on a general GAN training procedure no matter what loss function is adopted. Experimental results on one synthetic dataset and three popular benchmark datasets -- Cifar-10, Tiny-ImageNet and CelebA validate that LSVGD can remarkably improve the performance and stability of various GAN models.

cs.LG↗

arXiv2020

Renormalization of the Mott gap by lattice entropy: The case of 1T-TaS2

In many transition-metal oxides and dichalcogenides, the electronic and lattice degrees of freedom are strongly coupled, giving rise to remarkable phenomena, such as metal-insulator transition (MIT) and charge-density wave (CDW) order. We study this interplay by tracing the instant electronic structure under ab initio molecular dynamics. Applying this method to a 1T-TaS2 layer, we show that the CDW-triggered Mott gap undergoes a continuous reduction as the lattice temperature raises, despite a nearly constant CDW amplitude. Before the CDW order undergoes a sharp first-order transition around the room temperature, the dynamical CDW fluctuation already shrinks the Mott gap size by half. The gap size reduction is one order of magnitude larger than the lattice temperature variation. Our calculation not only provides an important clue to understand the thermodynamics behavior in 1T-TaS2, but also demonstrates a general approach to quantify the lattice entropy effect in MIT.

cond-mat.mes-hall↗

arXiv2020

Giant renormalization of correlation strength in 1T-TaS2 by lattice vibration

The lattice thermodynamics of a 1T-TaS2 layer, e.g. the spontaneous formation of a sqrt13*sqrt13 commensurate charge density wave (CCDW) and vibrations around the equilibrium position, is calculated by ab initio molecular dynamics. Based on that, we examine how the ground-state electronic structure is renormalized by lattice temperature. We show that the band gap within the density functional theory plus onsite-U correction shrinks by half when the temperature raises from 0 K to 200 K. The gap size reduction is one order of magnitude larger than the temperature variation in energy. This giant temperature dependence is closely related to the CCDW-triggered Mottness in 1T-TaS2, and is expected to result in unconventional thermodynamic properties.

cond-mat.str-el↗

arXiv2020

Outlier Detection Ensemble with Embedded Feature Selection

Feature selection places an important role in improving the performance of outlier detection, especially for noisy data. Existing methods usually perform feature selection and outlier scoring separately, which would select feature subsets that may not optimally serve for outlier detection, leading to unsatisfying performance. In this paper, we propose an outlier detection ensemble framework with embedded feature selection (ODEFS), to address this issue. Specifically, for each random sub-sampling based learning component, ODEFS unifies feature selection and outlier detection into a pairwise ranking formulation to learn feature subsets that are tailored for the outlier detection method. Moreover, we adopt the thresholded self-paced learning to simultaneously optimize feature selection and example selection, which is helpful to improve the reliability of the training set. After that, we design an alternate algorithm with proved convergence to solve the resultant optimization problem. In addition, we analyze the generalization error bound of the proposed framework, which provides theoretical guarantee on the method and insightful practical guidance. Comprehensive experimental results on 12 real-world datasets from diverse domains validate the superiority of the proposed ODEFS.

cs.LG↗

arXiv2019

TBC-Net: A real-time detector for infrared small target detection using semantic constraint

Infrared small target detection is a key technique in infrared search and tracking (IRST) systems. Although deep learning has been widely used in the vision tasks of visible light images recently, it is rarely used in infrared small target detection due to the difficulty in learning small target features. In this paper, we propose a novel lightweight convolutional neural network TBC-Net for infrared small target detection. The TBCNet consists of a target extraction module (TEM) and a semantic constraint module (SCM), which are used to extract small targets from infrared images and to classify the extracted target images during the training, respectively. Meanwhile, we propose a joint loss function and a training method. The SCM imposes a semantic constraint on TEM by combining the high-level classification task and solve the problem of the difficulty to learn features caused by class imbalance problem. During the training, the targets are extracted from the input image and then be classified by SCM. During the inference, only the TEM is used to detect the small targets. We also propose a data synthesis method to generate training data. The experimental results show that compared with the traditional methods, TBC-Net can better reduce the false alarm caused by complicated background, the proposed network structure and joint loss have a significant improvement on small target feature learning. Besides, TBC-Net can achieve real-time detection on the NVIDIA Jetson AGX Xavier development board, which is suitable for applications such as field research with drones equipped with infrared sensors.

cs.CV↗

arXiv2019

Robust 3D multi-polar acoustic metamaterials with broadband double negativity

Acoustic negative-index metamaterials show promise in achieving superlensing for diagnostic medical imaging. In spite of the recent progress made in this field, most metamaterials suffer from deficiencies such as low spatial symmetry, sophisticated labyrinth topologies and narrow-band features, which make them difficult to be utilized for symmetric subwavelength imaging applications. Here, we propose a category of robust multi-cavity metamaterials and reveal their common double-negative mechanism enabled by multi-polar (dipole, quadrupole and octupole) resonances in both two-dimensional (2D) and three-dimensional (3D) scenarios. In particular, we discover explicit relationships governing the double-negative frequency bounds from equivalent circuit analogy. Moreover, broadband single-source and double-source subwavelength imaging is realized and verified by 2D and 3D superlens. More importantly, the analogical 3D superlens can ensure the subwavelength imaging in all directions. The proposed multi-polar resonance-enabled robust metamaterials and design methodology open horizons for easier manipulation of subwavelength waves and realization of practical 3D metamaterial devices.

physics.app-ph↗

arXiv2019

New theoretical constraints on scalar color octet models

We study theoretical constraints on a model whose scalar sector contains one color octet and one or two color singlet $SU(2)_L$ doublets. Using the unitarity of the theory, we constrain the parameters of the scalar potential for the first time at next-to-leading order in perturbation theory. We also derive new conditions guaranteeing the stability of the potential. We use the HEPfit package to single out the viable parameter regions at the electroweak scale and test the stability of the renormalization group evolution up to the multi-TeV region. Additionally, we set upper limits on the scalar mass splittings. All results are given for both cases, with and without a second scalar color singlet.

hep-ph↗

arXiv2018

Systematic design and realization of double-negative acoustic metamaterials by topology optimization

Double-negative acoustic metamaterials (AMMs) offer the promising ability of superlensing for applications in ultrasonography, biomedical sensing and nondestructive evaluation. Here, under the simultaneous increasing or non-increasing mechanisms, we develop a unified topology optimization framework considering the different microstructure symmetries, minimal structural feature sizes and dispersion extents of effective parameters. Then we apply the optimization framework to furnish the heuristic resonance-cavity-based and space-coiling metamaterials with broadband double negativity. Meanwhile, we demonstrate the essences of double negativity derived from the novel artificial multipolar LC and Mie resonances which can be induced by controlling mechanisms in optimization. Furthermore, abundant numerical simulations validate the double negativity, negative refraction, enhancements of evanescent waves and subwavelengh imaging for the optimized AMMs. Finally, we experimentally show the desired broadband subwavelengh imaging using the 3D-printed optimized space-coiling metamaterial. The present methodology and broadband metamaterials provide the ideal strategy of constructing AMMs for subwavelengh imaging technology.

physics.app-ph↗

arXiv2017

Multivariate Regression with Gross Errors on Manifold-valued Data

We consider the topic of multivariate regression on manifold-valued output, that is, for a multivariate observation, its output response lies on a manifold. Moreover, we propose a new regression model to deal with the presence of grossly corrupted manifold-valued responses, a bottleneck issue commonly encountered in practical scenarios. Our model first takes a correction step on the grossly corrupted responses via geodesic curves on the manifold, and then performs multivariate linear regression on the corrected data. This results in a nonconvex and nonsmooth optimization problem on manifolds. To this end, we propose a dedicated approach named PALMR, by utilizing and extending the proximal alternating linearized minimization techniques. Theoretically, we investigate its convergence property, where it is shown to converge to a critical point under mild conditions. Empirically, we test our model on both synthetic and real diffusion tensor imaging data, and show that our model outperforms other multivariate regression models when manifold-valued responses contain gross errors, and is effective in identifying gross errors.

stat.ML↗

arXiv2017

Too Far to See? Not Really! --- Pedestrian Detection with Scale-aware Localization Policy

A major bottleneck of pedestrian detection lies on the sharp performance deterioration in the presence of small-size pedestrians that are relatively far from the camera. Motivated by the observation that pedestrians of disparate spatial scales exhibit distinct visual appearances, we propose in this paper an active pedestrian detector that explicitly operates over multiple-layer neuronal representations of the input still image. More specifically, convolutional neural nets such as ResNet and faster R-CNNs are exploited to provide a rich and discriminative hierarchy of feature representations as well as initial pedestrian proposals. Here each pedestrian observation of distinct size could be best characterized in terms of the ResNet feature representation at a certain layer of the hierarchy; Meanwhile, initial pedestrian proposals are attained by faster R-CNNs techniques, i.e. region proposal network and follow-up region of interesting pooling layer employed right after the specific ResNet convolutional layer of interest, to produce joint predictions on the bounding-box proposals' locations and categories (i.e. pedestrian or not). This is engaged as input to our active detector where for each initial pedestrian proposal, a sequence of coordinate transformation actions is carried out to determine its proper x-y 2D location and layer of feature representation, or eventually terminated as being background. Empirically our approach is demonstrated to produce overall lower detection errors on widely-used benchmarks, and it works particularly well with far-scale pedestrians. For example, compared with 60.51% log-average miss rate of the state-of-the-art MS-CNN for far-scale pedestrians (those below 80 pixels in bounding-box height) of the Caltech benchmark, the miss rate of our approach is 41.85%, with a notable reduction of 18.68%.

cs.CV↗

arXiv2017

Synthesizing Filamentary Structured Images with GANs

This paper aims at synthesizing filamentary structured images such as retinal fundus images and neuronal images, as follows: Given a ground-truth, to generate multiple realistic looking phantoms. A ground-truth could be a binary segmentation map containing the filamentary structured morphology, while the synthesized output image is of the same size as the ground-truth and has similar visual appearance to what have been presented in the training set. Our approach is inspired by the recent progresses in generative adversarial nets (GANs) as well as image style transfer. In particular, it is dedicated to our problem context with the following properties: Rather than large-scale dataset, it works well in the presence of as few as 10 training examples, which is common in medical image analysis; It is capable of synthesizing diverse images from the same ground-truth; Last and importantly, the synthetic images produced by our approach are demonstrated to be useful in boosting image analysis performance. Empirical examination over various benchmarks of fundus and neuronal images demonstrate the advantages of the proposed approach.

cs.CV↗

arXiv2017

Validity of two Higgs doublet models with a scalar color octet up to a high energy scale

We have recently studied theoretical constraints on the parameters of a 2HDM augmented with a color-octet scalar. In this paper we consider the consequences of requiring the model to remain valid up to very high energy scales, such as the GUT scale. The acceptable region of parameter space is reduced when one insists on vacuum stability, perturbative unitarity and the absence of Landau poles below a given scale. As the scale to which we require the model to be valid is increased, the acceptable region of parameter space for the 2HDM sector is reduced in such a way that it approaches the alignment limit, $\cos(β-α)\to 0$, and the masses of $H^0$, $A$ and $H^\pm$ are pushed closer to each other. The parameters of the color octet sector are also restricted to an increasingly smaller region.

hep-ph↗

arXiv2017

Multivariate Regression with Grossly Corrupted Observations: A Robust Approach and its Applications

This paper studies the problem of multivariate linear regression where a portion of the observations is grossly corrupted or is missing, and the magnitudes and locations of such occurrences are unknown in priori. To deal with this problem, we propose a new approach by explicitly consider the error source as well as its sparseness nature. An interesting property of our approach lies in its ability of allowing individual regression output elements or tasks to possess their unique noise levels. Moreover, despite working with a non-smooth optimization problem, our approach still guarantees to converge to its optimal solution. Experiments on synthetic data demonstrate the competitiveness of our approach compared with existing multivariate regression models. In addition, empirically our approach has been validated with very promising results on two exemplar real-world applications: The first concerns the prediction of \textit{Big-Five} personality based on user behaviors at social network sites (SNSs), while the second is 3D human hand pose estimation from depth images. The implementation of our approach and comparison methods as well as the involved datasets are made publicly available in support of the open-source and reproducible research initiatives.

stat.ML↗

arXiv2017

An Interval-Based Bayesian Generative Model for Human Complex Activity Recognition

Complex activity recognition is challenging due to the inherent uncertainty and diversity of performing a complex activity. Normally, each instance of a complex activity has its own configuration of atomic actions and their temporal dependencies. We propose in this paper an atomic action-based Bayesian model that constructs Allen's interval relation networks to characterize complex activities with structural varieties in a probabilistic generative way: By introducing latent variables from the Chinese restaurant process, our approach is able to capture all possible styles of a particular complex activity as a unique set of distributions over atomic actions and relations. We also show that local temporal dependencies can be retained and are globally consistent in the resulting interval network. Moreover, network structure can be learned from empirical data. A new dataset of complex hand activities has been constructed and made publicly available, which is much larger in size than any existing datasets. Empirical evaluations on benchmark datasets as well as our in-house dataset demonstrate the competitiveness of our approach.

stat.ML↗

arXiv2016

Learning to Search on Manifolds for 3D Pose Estimation of Articulated Objects

This paper focuses on the challenging problem of 3D pose estimation of a diverse spectrum of articulated objects from single depth images. A novel structured prediction approach is considered, where 3D poses are represented as skeletal models that naturally operate on manifolds. Given an input depth image, the problem of predicting the most proper articulation of underlying skeletal model is thus formulated as sequentially searching for the optimal skeletal configuration. This is subsequently addressed by convolutional neural nets trained end-to-end to render sequential prediction of the joint locations as regressing a set of tangent vectors of the underlying manifolds. Our approach is examined on various articulated objects including human hand, mouse, and fish benchmark datasets. Empirically it is shown to deliver highly competitive performance with respect to the state-of-the-arts, while operating in real-time (over 30 FPS).

cs.CV↗

arXiv2016

Lie-X: Depth Image Based Articulated Object Pose Estimation, Tracking, and Action Recognition on Lie Groups

Pose estimation, tracking, and action recognition of articulated objects from depth images are important and challenging problems, which are normally considered separately. In this paper, a unified paradigm based on Lie group theory is proposed, which enables us to collectively address these related problems. Our approach is also applicable to a wide range of articulated objects. Empirically it is evaluated on lab animals including mouse and fish, as well as on human hand. On these applications, it is shown to deliver competitive results compared to the state-of-the-arts, and non-trivial baselines including convolutional neural networks and regression forest methods.

cs.CV↗